Roberto Rodrigues-Filho, Iwens Sene, Barry Porter, Luiz F. Bittencourt, Fabio Kon and Fábio M. Costa. Exploring Emergent Microservice Evolution in Elastic Deployment Environments. Journal of Systems and Software, 2024.
Microservices have become an important technology to enable the dynamic composition of large-scale
self-adaptive systems. Although modern microservice ecosystems provide a variety of autonomous
adaptation mechanisms, when focusing on the microservice itself, they can only account for changes
in the sheer increase in workload volume. On the other hand, when workload patterns change, efficient
treatment requires the intervention of DevOps experts to manually evolve the internal architecture of
services. Given the need to quickly adapt systems to respond to changes, solely relying on DevOps
to react to workload pattern changes becomes a bottleneck for future systems. To address this issue,
we advance the concept of emergent microservices, that autonomously adapt and evolve their internal
architectural composition to better handle changes in the pattern of incoming requests without human
intervention. We demonstrate the effectiveness of our approach by exploring this novel concept in the
context of a microservice-based Smart City platform.
Vladimir Rocha, Arlindo Flavio da Conceição, and Dario Vieira. Blockchain Technology: A Game Changer for Smart Healthcare Systems. Internet of Everything for Smart City and Smart Healthcare Applications, Part of the Signals and Communication Technology book series (SCT), 2024.
Blockchain technology enables reliable, secure, traceable, distributed, and fault-tolerant data storage. With the emergence of smart contracts (programs that run above the blockchain), the technology is no longer used only for financial purposes but also for more complex applications. This chapter aims to present the fundamental characteristics of blockchain and how it works. We show the main use cases of blockchain and examples of their use focused on the health area. Also, we discuss the application scenarios and the challenges to be overcome for the implementation and deployment of the technology.
Thatiane de Oliveira Rosaa, Eduardo Martins Guerra, Filipe Figueiredo Correiac, and Alfredo Goldman. CharM – evaluating a model for characterizing service-based architectures. Journal of Systems & Software, 2023.
Service-based architecture is an approach that emerged to overcome software development challenges such as difficulty to scale, low productivity, and strong dependence between elements. Microservice, an architectural style that follows this approach, offers advantages such as scalability, agility, resilience, and reuse. This architectural style has been well accepted and used in industry and has been the target of several academic studies. However, analyzing the state-of-the-art and -practice, we can notice a fuzzy limit when trying to classify and characterize the architecture of service-based systems. Furthermore, it is possible to realize that it is difficult to analyse the trade-offs to make decisions regarding the design and evolution of this kind of system. Some concrete examples of these decisions are related to how big the services should be, how they communicate, and how the data should be divided/shared. Based on this context, we developed the CharM, a model for characterizing the architecture of service-based systems that adopts microservices guidelines. To achieve this goal, we followed the guidelines of the Design Science Research in five iterations, composed of an ad-hoc literature review, discussions with experts, two case studies, and a survey. As a contribution, the CharM is an easily understandable model that helps professionals with different profiles to understand, document, and maintain the architecture of service-based systems.
Ana Yoon Faria de Lima Advisor, Fabio Kon. Impacts of the COVID-19 pandemic on the bicycle sharing system in São Paulo. Technical Report RT-MAC-2023-01. Department of Computer Science, Institute of Mathematics and Statistics, University of São Paulo, 2023.
Alexandre Siqueira, Arlindo Conceição, and Vladimir Rocha. Performance Evaluation of Self-Sovereign Identity Use Cases. IEEE International Conference on Decentralized Applications and Infrastructures (DAPPS), 2023.
Self-sovereign identity (SSI) enables the creation of user-centric applications where the user has complete control over his data. This research evaluates the performance of SSI-based applications; to do this, we implemented healthcare use cases using Hyperledger Indy and Hyperledger Aries frameworks, deployed it in a cloud environment, and executed their empirical evaluation. The results indicate that the bottleneck is the CPU; a simple setup can support up to 80 concurrent users without relevant errors and 120 simultaneous users before system degradation. Finally, we discuss the system bottlenecks and possible optimization techniques.
Thiago Oliveira, Fábio Costa, Les Foulds, and Humberto Longo. Scheduling distributed multiway spatial join queries: optimization models and algorithms. International Journal of Geographical Information Science, 2023.
Multiway spatial joins are a commonly occurring and fundamental type of query for spatial data processing. This article presents models and algorithms to schedule this type of query in distributed database systems while attempting to strike a balance between makespan and communication costs. We propose three algorithms based on combinatorial optimization methods: the well-known linear relaxation technique of rounding a solution generated by linear programming (LP), a more sophisticated Lagrangian Relaxation method (LR), as well as a greedy heuristic (GR) for baseline comparison. Our evaluation shows that a schedule built using GR consumes, on average, 22% more processing and communication resources than a more elaborate schedule constructed via the LR method, when scheduling a query for 64 machines. The schedule provided by LR is also, on average, an order of magnitude closer to the optimal schedule for a query compared to GR. We show that scheduling Gigabyte-size multiway queries before execution can reduce its processing time by an order of magnitude compared to state-of-the-art frameworks for spatial data processing that do not have this capability, and can significantly reduce the amount of shuffled data in the network.
Thiago J. B. Pena, Higor A. de Souza, Letícia L. Lemos, and Fabio Kon. BikeScienceWeb: a tool for bicycle-related urban planning. Proceedings of the XXIV Brazilian Symposium on Geoinformatics (GEOINFO 2023), 2023.
BikeScienceWeb is a data science tool containing analytic resources for active urban mobility planning. The tool aims to enable specialists to carry out their analyses without the need for programming knowledge. BikeScienceWeb can be used to include and exclude layers of subject-related geolocation information, import custom layers, compare two maps with different scenarios, and evaluate bicycle travel flows using travel survey data. The tool is available for use at the São Paulo Traffic Engineering Company (CET) and for the general public. A survey carried out with specialists in urban mobility showed that 70% deemed the tool as easy to use, 76% deemed it as useful for planning active mobility, and 88% had an intention to use the tool for their activities.
Eduardo Bouhid Neto, Paulo Pedro, Alvaro Fazenda, and Fabio Faria. A Landsat-8 Band Selection Framework based on UMDA for Deforestation Detection (in Portuguese). Workshop of Undergraduate Works (WUW), SIBGRAPI, 2023.
The conservation of tropical forests is a current subject of social and ecological relevance due to their crucial role in the global ecosystem. Unfortunately, millions of hectares are deforested and degraded each year. Therefore, government or private initiatives are needed for monitoring tropical forests. In this sense, this work proposes a novel framework, which uses of distribution estimation algorithm (UMDA) to select spectral bands from Landsat-8 that yield a better representation of deforestation areas to guide a semantic segmentation architecture called DeepLabv3+. In performed experiments, it was possible to find several compositions that reach balanced accuracy superior to 90% in segment classification tasks. Furthermore, the best composition (651) found by UMDA algorithm fed the DeepLabv3+ architecture and surpassed in efficiency and effectiveness all compositions compared in this work.
Best Paper Award at the Workshop of Undergraduate Works (WUW), SIBGRAPI 2023.
Walter Willinger, Arpit Gupta, Arthur S. Jacobs, Roman Beltiukov, Ronaldo A. Ferreira, and Lisandro Z. Granville. A NetAI Manifesto (Part I): Less Explorimentation, More Science. ACM SIGMETRICS Performance Evaluation Review, Vol. 51, Issue 2, 2023.
The application of the latest techniques from artificial intelligence (AI) and machine learning (ML) to improve and automate the decision-making required for solving realworld network security and performance problems (NetAI, for short) has generated great excitement among networking researchers. However, network operators have remained very reluctant when it comes to deploying NetAI-based solutions in their production networks, mainly because the black-box nature of the underlying learning models forces operators to blindly trust these models without having any understanding of how they work, why they work, or when they don’t work (and why not). Paraphrasing [1], we argue that to overcome this roadblock and ensure its future success in practice, NetAI “has to get past its current stage of explorimentation, or the practice of poking around to see what happens, and has to start employing tools of the scientific method.”
Ana Yoon Faria de Lima, Flavio Soares de Freitas, Tainá Souza Pacheco, Higor Amario de Souza, Frauke Behrendt, Ruth Oldenziel, and Fabio Kon. Cycling promotion using financial incentives: A case study in São Paulo, Brazil. Cycling Research Board, 2023.
The promotion of cycling as a mode of transportation has been recognized as a key strategy for achieving sustainable urban mobility and improving public health. Regardless, cycling remains a marginal mode of transport in many cities around the world. In São Paulo, Brazil’s largest city with more than 12 million inhabitants and 28 million trips daily, only 0.8% of all trips were made by bicycle in 2017 (Metrô São Paulo, 2017). This is far below the potential demand for cycling estimated at 17% by our research group in a recent study (Freire et al., 2023). Despite the expansion of the cycling network from 5.8 km before 2007 to 722 km in 2023 (CET, 2023; City Hall of São Paulo, 2020), the desired related increase in bike trips has not been achieved.
In response to this challenge, São Paulo’s City Hall approved the Bike SP Program in 2016 (Municipal legislation, 2016), an innovative legislation aimed at encouraging cycling by granting mobility credits to individuals who utilize bicycles as a means of transportation. In the literature, personal economic incentives have been demonstrated to be successful in promoting several health-related behaviors, including smoking cessation, weight loss, physical activity, and vaccination (Kane et al., 2004; Mantzari et al., 2015; Vlaev et al., 2019). However, the use of financial incentives to promote cycling as a mode of transportation on a large scale in a metropolis is still relatively rare and under-researched.
This lack of relevant large-scale precedents and scientific studies hampered the operationalization of the Bike SP Program. In response, we are designing, conducting, and evaluating a pilot research project in collaboration with municipal agencies and cycle mobility experts. This paper focuses on the design stage of the pilot. Across all stages, we adopt a multidisciplinary approach that combines data science and experimental modeling techniques with social science concepts on mobility data justice and cycling cities. The overall aim of the pilot is to reach a deeper understanding of the complex dynamics between financial incentives, cycling behavior, urban context, and social justice to inform the policy process of upscaling and wider implementation of the Bike SP program in São Paulo.
The objectives of the overall study are to: (1) evaluate the impact of the Bike SP program on the volume of bicycle trips made in São Paulo; (2) estimate the price elasticity of the Bike SP program, i.e., how the bicycle travel demand responds to different remuneration levels; (3) identify the demographic and socioeconomic profiles and the regions of the city that are most responsive to the Bike SP program and should be prioritized for policy targeting; and (4) consider the social justice implications at design, implementation, and evaluation stages. This paper discusses how these objectives can be addressed in the pilot’s design phase.
The design phase takes place in spring-autumn 2023, with a view toward implementing a six-month pilot with 600 to 900 participants from late 2023 to early 2024. We report initial findings and insights from this stage, specifically around the following four areas.
Considering a social justice perspective: The pilot project’s recruitment strategy and selection criteria will take into account demographic factors, income disparities, access to cycling infrastructure, and other elements, with an attempt to balance these aspects among participants. This is informed by the five factors identified by Cycling Cities (Oldenziel et al., 2016) and the mobility data justice framework (Behrendt & Sheller, 2023). This framework will be applied in the pilot design to prevent any unintended biases in our data collection and analysis and to ensure that our outcomes do not inadvertently reinforce social injustices.
Defining implementation variables: Regarding the pilot’s structure, one of the setups under consideration is that we will divide the six-month pilot into three periods of two months each. In the first period, the participants will be randomly assigned to one of three groups: (1) control group – which receives no financial incentive for cycling, (2) low incentive group – which receives a fixed amount of mobility credits for each kilometer traveled by bicycle, and (3) high incentive group – which receives a higher amount of mobility credits for each kilometer. The amounts that each group receives will change at the beginning of every two-month period.
Mobile app development: We developed a mobile application so that participants can register their cycling trips during the pilot. The data gathered with the app will be used to compensate users and provide input for the evaluation phase.
Setting up the evaluation: We set up the evaluation phase, to assess how financial incentives affect citizens’ riding habits, what the social justice implications are, and to weigh the costs and benefits of the Bike SP Program. We will use data from the pilot project to measure changes in cycling frequency, duration, distance, and mode choice among participants in different socioeconomic and demographic categories. We will also employ data from surveys gathered during the program to measure changes in perceptions, attitudes, and preferences regarding cycling before and after the pilot. The results across groups will be compared using appropriate statistical techniques to test for differences and causal effects. Qualitative observations by the researchers will also be recorded. The cycling cities and mobility data justice framework will be used to identify further challenges and opportunities for scaling up the pilot.
This study seeks to enhance our understanding of the connections between financial incentives, cycling behavior, and social justice, thereby supporting the development of inclusive and effective policies for sustainable urban mobility not only in São Paulo but also providing valuable perspectives for cycling research in the Global South. This way, the findings from this research aim to provide practical lessons for urban planners, policymakers, and researchers intending to increase cycling modal share in similar contexts worldwide, as well as serve as a model for addressing the challenges faced by other cities characterized by a car-centric culture.
Higor A. de Souza, Marcelo de S. Lauretto, Fabio Kon, and Marcos L. Chaim. Understanding the use of spectrum-based fault localization. Journal of Software: Evolution and Process, 2023.
Developers spend significant time locating and fixing bugs, which is often performed manually. Although spectrum-based fault localization (SFL) techniques aim at helping developers to locate faults, they are not yet used in practice. Recent studies have investigated how developers use SFL, presenting different conclusions about their effectiveness and usefulness. We carried out a user study to further enhance the understanding of SFL. We assessed whether SFL improves the developers’ performance and to what extent SFL leads developers to inspect faulty code excerpts. We also investigated the intention of the developers to use SFL and how they interact with SFL. Twenty-six participants performed debugging tasks using real programs, with and without using the Jaguar SFL tool. Using SFL, more developers located and fixed the bugs. SFL also led more developers to inspect the faulty code and locate the faulty method. However, they did not spend less time locating the faults. SFL was well-accepted by the participants, who showed intention to use it in their daily activities. Our results indicate that SFL is useful even when the fault is not ranked among the first positions, leading developers to reach faulty code regions and find the bugs.
Reynaldo Villena, and Routo Terada. Recovering the Secret on Binary Ring-LWE problem with Random Known bits. Proceedings of the 23rd Brazilian Symposium on Information and Computational Systems Security, 2023.
There are cryptographic systems that are secure against attacks by both quantum and classical computers. Some of these systems are based on the Binary Ring-LWE problem which is presumed to be difficult to solve even on a quantum computer. This problem is considered secure for IoT (Internet of things) devices with limited resources. In Binary Ring-LWE, a polynomial a is selected randomly and a polynomial b is calculated as b = a.s + e where the secret s and the noise e are polynomials with binary coefficients. The polynomials b and a are public and the secret s is hard to find. However, there are Side Channel Attacks that can be applied to retrieve some coefficients (random known bits) of s and e. In this work, we analyze that the secret s can be retrieved successfully having at least 50 % of random known bits of s and e.
Eder M. Barbosa, Josias Lima, Alessandro Santos, and Patricia Baptista. Using cellular infrastructures data to foster the transition towards smart cities: a systematic mapping. IEEE International Smart Cities Conference (ISC2), 2023.
Smartphones connected to the cellular network generate records about connection information (Call Details Record – CDR), creating considerable amounts of telecommunications data, which creates an opportunity to support city management, namely to foster the smart cities concept. This work performs the systematic mapping of research in this area and identifies the main opportunities with cellular infrastructure data to support smart city control centers. The methodological process encompasses a sequence of intricately executed stages, including formulating a research protocol, utilizing search engines, rigorous application of inclusion and exclusion criteria, meticulous selection of relevant studies, thorough data validation, and exhaustive synthesis of research outcomes. Thus, 72 papers represent use cases divided into smart services groups from ISO 37122. As a result, Mobility and Urban planning groups presented the most studies and uses, recently increasing the research in other axles, such as Economy, Environment and Climate Change, Health, Social Conditions, and Security. However, there are challenges to overcome to increase smart services to cities.
This study, presented at the prestigious Pontifical College of Bucharest, Romania, sparked significant academic and professional debate and highlighted the importance of crucial themes related to smart cities. With a particular focus on the criteria established by the International Organization for Standardization (ISO 37122) for the governance and operation of a smart city, this work substantially contributes to the understanding and application of these global standards. Furthermore, incorporating a systematic mapping of the literature in this study dramatically enriches the academic corpus, providing a solid foundation for future research.
João Francisco Lino Daniel, Eduardo Martins Guerra, Thatiane de Oliveira Rosa, and Alfredo Goldman. Towards the Detection of Microservice Patterns Based on Metrics. 49th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), 2023.
Microservices is a popular architectural approach for complex systems in companies, despite its nature of decentralization. There is a comprehensive set of microservices architectural patterns that guides implementations and helps developers to overcome issues. However, the community still scarcely adopts these patterns and only has a theoretical understanding of them. In this work, in order to increase awareness of such patterns and provide aid to developers to better understand an architecture based on microservices, we propose a detection approach based on metrics for microservices patterns. We focused on structural or architectural patterns, and implemented detection for five of them. We conducted two case studies with real-world applications and evaluated the accuracy and applicability of our approach with the developers of those applications.
Pedro Ivo Siqueira Nepomuceno, and Kelly Rosa Braghetto. Managing Semantic Evolutions in Semi-Structured Data. 34th International Conference on Database and Expert Systems Applications (DEXA), 2023.
This paper introduces a model to store semi-structured data while documenting its semantic changes over time. The paper also presents algorithms for querying semantic evolved data, which conciliate the multiple versions the data may have. An implementation of the model and algorithms, MellowDB, was developed, and its performance was analyzed, showing the proposed algorithms and model are feasible.
Guilherme Thomaz, Matheus Guerra, Matteo Sammarco, Marcin Detyniecki, and Miguel Campista. Tamper-proof Access Control for IoT Clouds Using Enclaves. Ad Hoc Networks, Vol. 147, 2023.
Internet of Things (IoT) devices rely on cloud computing for processing user-sensitive data, like health recordings and geolocalization. In this case, security primitives like cryptography and certificate-based authentication does not prevent the cloud provider from acting against the privacy policy. This paper presents a framework for clouds to execute arbitrarily complex processing tasks over IoT data while maintaining the access control policies over the client’s control. We rely on a memory enclave to enforce that the cloud follows personal and customizable access policies and analyzed the security properties of our scheme. The performance evaluation reveals that these robust security improvements come with a latency overhead of just 0.1 ms, confirming the system’s viability. The system leverages multi-threaded processing inside an enclave to process thousands of client messages per second, achieving high scalability. This work also contributes with a microbenchmark that identifies how much each step of an enclave application influences the performance and evaluates the enclave viability for performing realistic IoT data processing.
Lucas Soares, Fabíola Oliveira, Carlos Kamienski, and Luiz Bittencourt. Drone Edge Management System (DREMS): Sequencing Drone Takeoff and Landing. The 10th International Conference on Future Internet of Things and Cloud (FiCloud 2023), 2023.
Drone delivery services are gaining momentum as businesses aim to combine fast customer service with a low carbon footprint. However, ensuring safety and mitigating collisions between drones and obstacles remains a significant challenge. Existing studies primarily focus on specific collision avoidance issues in limited scenarios, neglecting the management of takeoff and landing in high-density distribution centers. This paper introduces the Drone Edge Management System (DREMS) to address these challenges. DREMS utilizes a network of Drone Management Stations (DMS) and a Drone Edge Manager to orchestrate the sequencing of drones for takeoff and landing. The proposed system leverages edge computing infrastructure and facilitates communication between drones and DMS through IoT or 5G/6G wireless technologies. Simulations demonstrate the effectiveness of DREMS in reducing collisions during takeoff and landing compared to an unmanaged strategy. The results emphasize the significance of considering the entire lifecycle of a delivery service, especially for scenarios involving a high density of smaller drones operating in a 3D space.
Bruna M. O. S. Cordeiro, Roberto Rodrigues Filho, Iwens G. Sene-Júnior, and Fábio M. Costa. STEER: An Architecture to Support Self-adaptive IoT Networks for Indoor Monitoring Applications. Journal of Internet Services and Applications, 2023.
IoT infrastructures are becoming increasingly more difficult to manage. One of the main issues is the high volatility present in the infrastruture, which increasingly demands self-adaptive solutions. As a proposal to handle this challenge, this paper presents STEER (Sdn-based inTEnt drivEn iot netwoRks), a new approach for the dynamic adaptation of IoT networks for indoor monitoring applications, based on the unification of Intent-Driven Networks (IDN) and Software-Defined Networks (SDN). Particularly, we explore the ability of IDNs to dynamically interpret an application’s intent, using an IDN-based mediator attached to an SDN-controller to autonomously adapt the IoT network behavior at runtime, thus realizing the intent according to the current operating context of the network. We demonstrate the approach using a representative application scenario related to IoT indoor environment monitoring in the domain of indoor air quality monitoring. The experiments allowed us to validate the applicability of the approach and show the system-wide effect of dynamic adaptation to the current operating environment on improving performance according to the metric under consideration, in this case, the number of application-level messages exchanged in the network.
Eduardo B. Falbel, Lucas M. de Freitas, Kay W. Axhausen, Fabio Kon, and Raphael Y. de Camargo. Spatial out-of-sample estimation of cycling OD matrices. Swiss Transport Research Conference, 2023.
Cycling is a potential tool to mitigate many of the problems faced by urban populations today. As such, there has been a recent push towards this mode of transportation by city officials worldwide. Encouraging the use of bicycles as a legitimate mobility tool (as opposed to only a means of exercise or recreation), however, involves having adequate knowledge of present mobility patterns, such as sources of trip generation and attraction. Unfortunately, cities usually do not gather enough loop-count data on flows and/or enough cycling OD-demand data to adequately understand cycling demand. We propose models based on spatial econometrics and gradient boosted regression trees which can be trained with data from cities with mature cycling cultures and then applied to cities still in their cycling infancy to supply city officials with a better estimate of these OD Matrices so they can better promote this means of transportation. We perform a first case study and show preliminary results comparing both types of models.
Arthur S. Jacobs, Ronaldo A. Ferreira, and Lisandro Z. Granville. Enabling Self-Driving Networks with Machine Learning. NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium, 2023.
This work aims to enable self-driving networks by tackling the lack of trust that network operators have in Machine Learning (ML) models. We assess and scrutinize the decision-making process of ML-based classifiers used to compose a self-driving network. First, we investigate and evaluate the accuracy and credibility of classifications made by ML models used to process high-level management intents. We propose a novel conversational interface (LUMI) that allows operators to use natural language to describe how the network should behave. Second, we analyze and assess the accuracy and credibility of existing ML models’ for network security and performance. We also uncover the need to reinvent how researchers apply ML to networking problems, so we propose a new ML pipeline that introduces steps to scrutinize models using techniques from the emerging field of eXplainable Artificial Intelligence (XAI). Finally, we investigate whether there is a viable method to improve the trust of operators in the decisions made by ML models that enable self-driving networks. Our investigation led us to propose a new XAI method to extract explanations from any given black-box ML model in the form of decision trees while maintaining a manageable size, which we called TRUSTEE. Our results show that ML models widely applied to solve networking problems have not been put under proper scrutiny and can easily break when put under real-world traffic. Such models, therefore, need to be corrected to fulfill their given tasks properly.
Guilherme Thomaz, Matheus Guerra, Matteo Sammarco, and Miguel Campista. CACIC-DevKit: Construção de Sistemas IoT com Políticas de Acesso Customizáveis e Segurança por Hardware (in Portuguese). Companion Proceedings of the 41st Brazilian Symposium on Computer Networks and Distributed Systems, 2023.
Memory enclaves secure data in clouds in the presence of attackers with privileged access to servers. The diversity of applications in the Internet of Things (IoT) makes it difficult to develop enclave systems. This work proposes CACIC-DevKit: a tool for developing IoT systems using the CACIC architecture, proposed in our previous work. The differential of the tool is the flexibility in choosing the appropriate data sources, processing tasks, and database for your use case. To demonstrate the usability, a system for smart-grids is developed with real devices, graphical user interfaces, and commercial databases.
Lucas Airam, Gustavo Camilo, Gabriel Rebello, Matteo Sammarco, Miguel Campista, and Luís Costa. ATHENA-FL: Avoiding Statistical Heterogeinety with One-versus-All in Federated Learning (in Portuguese). Proceedings of the 7th Urban Computing Workshop, 2023.
O aprendizado federado é um novo paradigma que permite o treinamento de modelos de aprendizado de máquina através da colaboração entre clientes e um servidor de agregação. O treinamento dispensa o compartilhamento de dados privados, garantindo aos clientes privacidade de suas amostras. Entretanto, quando os clientes possuem distribuições de dados distintas, o treinamento apresenta dificuldades de convergência, resultando em erros preditivos no modelo final. Este artigo propõe um sistema de aprendizado federado que considera clientes com distribuições de dados heterogêneas e, mesmo assim, produz modelos acurados em menos épocas de treinamento do que o estado da arte. Os efeitos da heterogeneidade dos dados são mitigados através do agrupamento dos clientes baseado em uma estimativa da distribuição de dados através dos pesos da rede neural treinada localmente. Além disso, o sistema utiliza a técnica um-contra-todos, treina um detector para cada classe no sistema. Assim, grupos diferentes podem combinar os detectores a fim de formar um modelo capaz de detectar classes provenientes de outros grupos. Os resultados mostram que o modelo um-contra-todos possui alta capacidade de identificar corretamente as amostras e com acurácia até 18% maior do que o treinamento tradicional, com um baixo custo de comunicação durante o treinamento, reduzindo a quantidade de bytes transmitidos entre 59,6% até 94% em comparação à arquitetura MobileNet.
Received an Honorable Mention.
Lucas Souza, Gabriel Rebello, Gustavo Camilo, Miguel Elias, and Luís Costa. GITI-CB: Identity Management with Information Exchange between Blockchains (in Portuguese). Proceedings of the 6th Blockchain Workshop: Theory, Technology and Applications, 2023.
Citizen identification is essential to unlock access to basic services such as healthcare and education. However, traditional identity management systems adopt approaches that are poorly scalable or detrimental to user security and privacy. This paper presents a proposal for an identity management system based on blockchain interoperability. In the system, each domain maintains a blockchain to manage the identity of its users. Furthermore, the paper analyzes the technique of exchanging information between blockchains to implement the concept of “take your own identity”. In this way, the system mitigates scalability problems and guarantees users control over their data.
Gustavo Camilo, Gabriel Rebello, Lucas Souza, Miguel Campista, and Luís Costa. Profitable Node Positioning and Low-cost Route Creation in the Lighting Network (in Portuguese). Proceedings of the 41st Brazilian Symposium on Computer Networks and Distributed Systems , 2023.
As redes de canais de pagamento (Payment Channel Networks – PCN) têm atingido sucesso ao substituir os lentos mecanismos de consenso global por acordos criptográficos locais entre nós participantes. Apesar do sucesso, as PCNs sofrem com os modelos atuais de posicionamento de novos nós participantes, que ignoram possíveis ganhos financeiros dos usuários e incentivam a centralização da rede. Este artigo apresenta um modelo de adição de novos nós à rede que cria conexões de alto retorno financeiro ao usuário e baixo custo de emissão de transações. O trabalho formula o problema da adição do nó à rede matematicamente e demonstra que o problema é NP-difícil. O modelo proposto permite ainda que usuários criem canais de longa duração. O artigo desenvolve uma heurística baseada em um algoritmo guloso para resolução do problema. A análise da heurística implementada mostra que a solução oferece recompensa até 3 vezes maior e custo 2 vezes menor que métodos tradicionais que priorizam nós de maior grau, maior centralidade ou PageRank.
Received Honorable Mention.
Leonardo Leite, Nelson Lago, Claudia Melo, Fabio Kon, and Paulo Meirelles. A Theory of Organizational Structures for Development and Infrastructure Professionals. In IEEE Transactions on Software Engineering, vol. 49, no. 4, pp. 1898-1911 (1 April 2023), 2023.
DevOps and continuous delivery have impacted the organizational structures of development and infrastructure groups in software-producing organizations. Our research aims at revealing the different options adopted by the software industry to organize such groups, understanding why different organizations adopt distinct structures, and discovering how organizations handle the drawbacks of each structure. We interviewed 68 carefully-selected IT professionals, 45 working in Brazil, 10 in the USA, 8 in Europe, 1 in Canada, and 4 in globally distributed teams. By analyzing these conversations through a Grounded Theory process, we identified conditions, causes, reasons to avoid, consequences, and contingencies related to each discovered structure (segregated departments, collaborative departments, API-mediated departments, and single department). In this way, we offer a theory to explain organizational structures for development and infrastructure professionals. This theory can support practitioners and researchers in comprehending and discussing the DevOps phenomenon and its related issues, and also provides valuable input to practitioners’ decision-making.
Diogo Gonçalves, Carlo Puliafito, Enzo Mingozzi, Luiz Bittencourt, and Edmundo Madeira. End-to-end network slicing in vehicular clouds using the MobFogSim simulator. Ad Hoc Networks, 2023.
Fog computing and network slicing are drawing attention as promising technologies in modern networks, such as Vehicular Ad-Hoc Networks (VANETs). On the one hand, fog computing lets end-user devices offload part of their computation and data to micro data centres (i.e., fog nodes) that are pervasively deployed in their proximity. On the other hand, network slicing creates different logical networks over a common physical infrastructure, wherein each logical network, called a slice, aims at meeting the requirements and characteristics of a specific class of applications. In this context, simulators allow the evaluation of new solutions in a cost-efficient and repeatable way. MobFogSim is specifically targeted at allowing the evaluation of resource management solutions in modern networks, including the support of device mobility, fog service migration, and network slicing. In this work, we further extend MobFogSim by presenting new functionalities, namely: (i) the support of VANETs; (ii) the modelling of end-to-end (E2E) slices, which include storage and processing resources of fog nodes besides the network resources; and (iii) improvements to the scalability of our simulator. We validate this work by conducting experiments over MobFogSim to assess its improved scalability as well as to test network slicing and fog computing solutions in three different VANET scenarios: (i) fog_only, wherein fog nodes are deployed only at the edge of the fixed infrastructure; (ii) vehicular_only, where fog nodes are provided only by nearby vehicles; and (iii) hybrid, which combines the previous two. Results show that the vehicular_only approach can reduce the latency provided to end-user devices by around 50% with respect to the fog_only approach. Besides, the improved version of MobFogSim reduces the simulation time by around 65% if compared to the previous version.
Fabíola M. C. de Oliveira, Luiz F. Bittencourt, Reinaldo A. C. Bianchi, and Carlos A. Kamienski. Drones in the Big City: Autonomous Collision Avoidance for Aerial Delivery Services. IEEE Transactions on Intelligent Transportation Systems, 2023.
As delivery companies continue to explore the use of drones, the need for efficient and safe operation in urban environments becomes increasingly critical. Market-wide versions of drone delivery services will necessarily spread many drones, especially in big cities. In this scenario, avoiding collisions with other drones or typical obstacles in urban spaces is fundamental. This paper proposes and evaluates, via simulation and analytical modeling, an aerial delivery service scenario and three autonomous geometric approaches for collision avoidance. We compare our approaches with three simple methods – DoNothing (not detouring), Random, and aviation-like Rightward – and two state-of-the-art geometric approaches. Simulation experiments consider different fleet sizes with constant and Poisson drone arrival rates and drones randomly choosing one of different altitudes for the cruise flight. Contrary to our expectations, the Random and Rightward approaches increase the collisions compared with DoNothing, making the latter our baseline. Our approaches significantly reduce collisions in all experiments and deal with more drones within the detection radius, showing that collisions are more complex to avoid. Comparing the collision rate, successful trips, and the number of flying drones reveals that the efficiency in avoiding collisions reduces the number of successful trips by increasing the number of active drones. Regardless of the expected reduction in collisions, more altitudes do not eliminate them. These results indicate the need for more sophisticated approaches to reduce or eliminate collisions. The analytical modeling using Markov Chains corroborates the simulation results by shedding some light on and helping explain the simulation results.
Jessica Díaz, Jorge Pérez, Isaque Alves, Fabio Kon, Leonardo Leite, Paulo Meirelles, and Carla Rocha. Harmonizing DevOps taxonomies — A grounded theory study. Journal of Systems and Software, 2023.
Context:
DevOps responds to the growing need of companies to streamline the software development process and thus has experienced widespread adoption in the past few years. However, the successful adoption of DevOps requires companies to address important cultural and organizational changes. Nevertheless, it is crucial to recognize that various DevOps taxonomies exist, both from academic and practitioner perspectives, which may lead to misleading or failed adoption of DevOps.
Objective:
This paper presents empirical research on the structure of DevOps teams in software-producing organizations. The goal is to better understand the organizational structure and characteristics of teams adopting DevOps by harmonizing the existing knowledge.
Methods:
To achieve this, we employed a grounded theory approach with collaborative coding, involving two research groups. Inter-Coder Agreement (ICA) was utilized to guide the discussion rounds. We conducted a comprehensive analysis of existing studies on DevOps teams and taxonomies to gain a deeper understanding of the subject.
Results:
From the analysis, we built a substantive and analytic theory of DevOps taxonomies. The theory is substantive in that the scope of validity refers to the ten secondary studies processed and analytic in that it analyzes “what is” rather than explaining causality or attempting predictive generalizations. A public repository with all the data related to the products resulting from the analysis and generation of the theory is available.
Conclusions:
We built a theory on DevOps taxonomies and tested whether it harmonizes the existing taxonomies, i.e., whether our theory can instantiate the others. This is the first step to define which taxonomies are best suited to approach DevOps culture and practices according to the companies’ objectives and capabilities.
Fabíola Oliveira, Luiz Bittencourt, Carlos Kamienski, and Edson Borin. PANCODE: Multilevel Partitioning of Neural Networks for Constrained Internet-of-Things Devices. IEEE Access, Vol. 11 , 2023.
The increasing number of Internet-of-Things (IoT) devices will generate unprecedented data in the upcoming years. Fog computing may prevent the saturation of the network infrastructure by processing data at the edge or within these devices. Consequently, the machine intelligence built almost exclusively on the cloud can be scattered to the edge devices. While deep learning techniques can adequately process IoT-massive data volumes, their high resource-demanding nature poses a trade-off for execution on resource-constrained devices. This paper proposes and evaluates the performance of the PArtitioning Networks for COnstrained DEvices (PANCODE), a novel algorithm that employs a multilevel approach to partition large convolutional neural networks for distributed execution on constrained IoT devices. Experimental results with the LeNet and AlexNet models show that our algorithm can produce partitionings that achieve up to 2173.53 times more inferences per second than the Best Fit algorithm and up to 1.37 times less communication than the second-best approach. We also show that the METIS state-of-the-art framework only produces invalid partitionings in more constrained setups. The results indicate that our algorithm achieves higher inference rates and low communication costs in convolutional neural networks distributed among constrained and exceptionally very constrained devices.
Giovanni A. Oliveira, Priscila S. Lima, Fabio Kon, Routo Terada, Daniel M. Batista, Roberto H. Junior, and Mosab Hamdam. A Stacked Ensemble Classifier for an Intrusion Detection System in the Edge of IoT and IIoT Networks. IEEE Latin-American Conference on Communications (LATINCOM), 2022.
Over the last three decades, cyberattacks have become a threat to national security. These attacks can compromise Internet of Things (IoT) and Industrial Internet of Things (IIoT) networks and affect society. In this paper, we explore Artificial Intelligence (AI) techniques with Machine and Deep Learning models to improve the performance of an anomaly-based Intrusion Detection System (IDS). We use the ensemble classifier method to find the best combination between multiple models of prediction algorithms and to stack the output of these individual models to obtain the final prediction of a new and unique model with better precision. Although, there are many ensemble approaches, finding a suitable ensemble configuration for a given dataset is still challenging. We designed an Artificial Neural Network (ANN) with the Adam optimizer to update all model weights based on training data and achieve the best performance. The result shows that it is possible to use a stacked ensemble classifier to achieve good evaluation metrics. For instance, the average accuracy achieved by one of the proposed models was 99.7%. This result was better than the results obtained by any other individual classifier. All the developed code is publicly available to ensure reproducibility.
Arthur S. Jacobs, Roman Beltiukov, Walter Willinger, Ronaldo A. Ferreira, Arpit Gupta, and Lisandro Granville. AI/ML for Network Security: The Emperor has no Clothes. Proceedings of ACM Conference on Computer and Communications Security (ACM CCS'22), 2022.
Several recent research efforts have proposed Machine Learning (ML)-based solutions that can detect complex patterns in network traffic for a wide range of network security problems. However, without understanding how these black-box models are making their decisions, network operators are reluctant to trust and deploy them in their production settings. One key reason for this reluctance is that these models are prone to the problem of underspecification, defined here as the failure to specify a model in adequate detail. Not unique to the network security domain, this problem manifests itself in ML models that exhibit unexpectedly poor behavior when deployed in real-world settings and has prompted growing interest in developing interpretable ML solutions (e.g., decision trees) for “explaining” to humans how a given black-box model makes its decisions. However, synthesizing such explainable models that capture a given black-box model’s decisions with high fidelity while also being practical (i.e., small enough in size for humans to comprehend) is challenging.
In this paper, we focus on synthesizing high-fidelity and low-complexity decision trees to help network operators determine if their ML models suffer from the problem of underspecification. To this end, we present Trustee, a framework that takes an existing ML model and training dataset as input and generates a high-fidelity, easy-to-interpret decision tree and associated trust report as output. Using published ML models that are fully reproducible, we show how practitioners can use Trustee to identify three common instances of model underspecification; i.e., evidence of shortcut learning, presence of spurious correlations, and vulnerability to out-of-distribution samples.
Awarded Best Paper Honorable Mention at ACM CCS 2022. Awarded 2023 IETF/IRTF Applied Networking Research Prize.
Jessica Sato, Jorge Ribeiro, Roberto Araujo, José Pina, and Daniel Batista. Use of Animations for Comparison of Hashes in Electronic Voting via the Internet (in Portuguese). Workshop de Trabalhos de Iniciação Científica e de Graduação do XXII Simpósio Brasileiro de Segurança da Informação e de Sistemas Computacionais, 2022.
Secure electronic voting systems via the Internet require data comparison at various stages of the voting process. Some of this data is hashes, usually represented by strings. Comparing these strings by humans tends to be tedious, which means that it is not always performed correctly. This paper reports preliminary results of a software system that advances state of the art in electronic voting via the Internet by comparing hashes represented by animations. The basis of the system are the free software hashify, responsible for the animations, and the free software Helios, responsible for the votes. Results show that it is possible to compare Helios hashes using hashify animations.
Rodrigo Branco, Ronaldo Ferreira, and Edson Cáceres. Traffic Light Control for Emergency Vehicles (in Portuguese). 54° Simpósio Brasileiro de Pesquisa Operacional - SBPO, 2022.
The excess of vehicles in metropolitan areas creates problems for first responders during an emergency response, delaying emergency vehicles at critical moments. One of the ways to reduce the effects of congestion on an emergency vehicle (EV) is to use preemption, i.e., changing the traffic lights’ phases along its route. This paper proposes an algorithm that uses the shock-wave principle to compute the time to dissipate a queue of vehicles ahead of the EV waiting at a traffic light and determine the appropriate timing to trigger the preemption of the traffic light. Extensive evaluations of the proposed algorithm simulating real scenarios of different cities and with varying levels of congestion show that, for the considered scenarios, it reduces up to 96.98% the loss time of the EV in traffic, resulting in better performances than the existing solutions.
Henrique Carvalho, Jorge Ribeiro, Daniel Batista, and José Pina. HashifyPass – A Tool for Viewing Password Hashes (in Portuguese). Salão de Ferramentas do XXII Simpósio Brasileiro de Segurança da Informação e de Sistemas Computacionais, 2022.
For security reasons, it is recommended to create long, completely unstructured, random and different passwords for each of the personal accounts. Due to these requirements, some people may want to confirm that they have entered the correct password before submitting a login form. To assist in this confirmation in websites, many systems have the option to view the password, which makes authentication more vulnerable to shoulder surfing attacks. This paper introduces the HashifyPass software, which allows website passwords to be confirmed without displaying them. For this, an animation is used to visualize the password hash. The integration of the software into a login form attests to its effectiveness.
Jean Fobe, Michele Nogueira, and Daniel Batista. A New Defensive Technique Against Sleep Deprivation Attacks Driven by Battery Usage. XXII Simpósio Brasileiro de Segurança da Informação e de Sistemas Computacionais, 2022.
A significant amount of IoT devices are essentially powered by batteries and implements mechanisms to save energy, such as the sleep mode. The decision-making process deployed in IoT devices to enter to and exit from sleep mode can be exploited by remote users through sleep deprivation attacks, reducing the battery’s lifetime and causing a denial of service. This paper presents a new defensive technique to mitigate and prevent sleep deprivation attacks. It is based on the local battery consumption data, that is an input to control the sleep mode. Performance evaluation carried out in a system based on an ESP32 showed that the technique could increase the battery’s lifetime by 51.2% in a scenario under a sleep deprivation attack.
Murilo B. Ribeiro, and Kelly R. Braghetto. A Scalable Data Integration Architecture for Smart Cities: Implementation and Evaluation. Journal of Information and Data Management, 2022.
The collection, processing, and analysis of data generated by varied sources can help us better understand the functioning and demands of the cities. However, developing efficient solutions to explore urban data is challenging due to the large volume, heterogeneity, and lack of accessibility and integration of this kind of data.
In this work, we identify the main requirements of a data integration system to support decision-making in cities, focusing on its challenges. We analyze some existing data integration solutions, to uncover their features and limitations. Based on these results, we propose a new microservice architecture to support the development of software platforms for integrating smart cities’ heterogeneous data and a guideline to assess their performance. We also present details of a proof-of-concept implementation of the proposed architecture and its performance evaluation. The results demonstrate that the platform can scale horizontally to handle the highly dynamic demands of a smart city while maintaining low response times.
Michele Pushi, Anderson Silva, and Alessandro Santos. Governance challenges for information systems applied to smart city control centers (in Portuguese). III Workshop Brasileiro de Cidades Inteligentes, 2022.
This systematic mapping shows the main difficulties and opportunities of governance in control centers for Smart Cities. This mapping followed the methodological steps: protocol, execution in search engines, application of inclusion and exclusion criteria, selection of studies, data extraction, and synthesis of results. This resulted in 20 papers divided into Compliance, Operations, Training, Technologies, and Information Security. In general, the challenges are: how to meet Compliance in a dynamic environment; how to increase the Operation’s efficiency; how to keep the knowledge of all participants in the ecosystem up to date; how to keep the state-of-the-art technologies; and how to keep information secure.
Guilherme Pimenta, Fernanda Dallaqua, Alvaro Fazenda, and Fabio Faria. Neuroevolution-based Classifiers for Deforestation Detection in Tropical Forests. 35th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2022.
Tropical forests represent the home of many species on the planet for flora and fauna, retaining billions of tons of carbon footprint, promoting clouds and rain formation, implying a crucial role in the global ecosystem, besides representing the home to countless indigenous peoples. Unfortunately, millions of hectares of tropical forests are lost every year due to deforestation or degradation. To mitigate that fact, monitoring and deforestation detection programs are in use, in addition to public policies for the prevention and punishment of criminals. These monitoring/detection programs generally use remote sensing images, image processing techniques, machine learning methods, and expert photointerpretation to analyze, identify and quantify possible changes in forest cover. Several projects have proposed different computational approaches, tools, and models to efficiently identify recent deforestation areas, improving deforestation monitoring programs in tropical forests. In this sense, this paper proposes the use of pattern classifiers based on neuroevolution technique (NEAT) in tropical forest deforestation detection tasks. Furthermore, a novel framework called e-NEAT has been created and achieved classification results above 90% for balanced accuracy measure in the target application using an extremely reduced and limited training set for learning the classification models. These results represent a relative gain of 6.2% over the best baseline ensemble method compared in this paper.
Arielle Pereira, Álvaro Fazenda, and Alan Calheiros. Evaluating ML models for lightning forecasting in Brazil. Workshop on Data-Driven Extreme Events Analytics (DEXEA 2022) - Companion Proceedings of the 37thBrazilian Symposium on Data Bases, 2022.
Instruments for monitoring severe meteorological phenomena (such as lightning, flooding and landslides) can be used to assist in decision-making by state agencies, in an attempt to mitigate their possible harmful effects. These phenomena usually occur suddenly on a short-term duration, under a limited region, imposing difficulties in being predicted by regular weather forecast models, requiring specific prediction systems. Very short-term weather forecasting systems, on order of a few hours, known as nowcasting, can include numerical models of physical phenomena and machine learning algorithms. This work presents a system for forecasting the incidence of lightning, a common phenomenon in electrically active storms, through the application and evaluation of two machine learning models, an Artificial Neural Network and a Random Forest model, which were able to detect the occurrence of atmospheric electrical discharges from the automatic recognition of patterns obtained from the data generated by the numerical weather forecasts. The Random Forest model presented the best results when trained with the set that includes the ten best correlated variables, reaching 99.77% of accuracy for the case study performed.
Gustavo Camilo, Gabriel Rebello, Lucas Souza, Maria Potop-Butucaru, Marcelo Amorim, Miguel Campista, and Luís Costa. Analysis of the Topological Evolution of the Lightning Payment Channel Network (in Portuguese). Proceedings of the 22nd Brazilian Symposium on Information and Computational Systems Security, 2022.
Payment channel networks (PCN) offer a fast, secure, and distributed alternative for issuing payments while avoiding slow consensus mechanisms of blockchains. In this new technology, the network topology established between payment channels directly influences the performance, cost, and transaction success of participants. This paper analyzes the topology of the Lightning Network, current leading payment channel network, evaluating and discussing the network evolution. The paper reconstructs the network graph from real data using a set of gossip messages from channel and payment announcements collected between January 2020 and August 2021. The results show a strong trend of centralization of funds and connectivity, where 0.38% of nodes concentrate 50% of the network capacity, thus exposing a vulnerability to targeted attacks. As with the Bitcoin cryptocurrency, the centralization found in practice directly conflicts with the initial proposal of a peer-to-peer, i.e. decentralized, network. Moreover, the low transitivity of the network compromises the use of channel rebalancing techniques, which contribute to the stability of the system. This identifies the need for new attachment policies that prioritize greater decentralization and robustness of the network, in addition to prioritizing the creation of cycles for effective channel rebalancing.
Lucas Souza, Gustavo Camilo, Gabriel Rebello, Miguel Campista, and Luís Costa. Secure and Scalable Identity Management through Multiple Blockchains (in Portuguese). Anais Estendidos do XXII Simpósio Brasileiro em Segurança da Informação e de Sistemas Computacionais, 2022.
Citizen identification is essential to allow access to basic services such as healthcare and education. Nevertheless, traditional identity management systems embrace approaches that are poorly scalable or detrimental to user security and privacy. We present a proposal for an identity management system based on blockchain interoperability. In our system, each domain maintains a blockchain to manage the identity of its users. Furthermore, the paper analyzes the technique of exchanging information between blockchains to implement the concept of bring your own identity(BYOI). Thus, the system mitigates scalability problems and guarantees users control over their data. The work developed is part of the project promoted by the National Network for Education and Research, “Identity Management with Information Exchange between Blockchains”.
Lucas Souza, Gustavo Camilo, Miguel Campista, Luís Costa, and Otto Duarte. Enhancing Automatic Attack Detection through Spectral Decomposition of Network Flows. 2022 IEEE Global Communications Conference, 2022.
Flow classification employs machine learning techniques to identify attacks on computer networks. This classification relies on quantitative features that synthesize the information of packets from the same flow. Conventional features, however, such as packet size and the number of bytes, generate redundancies and do not capture the temporal correlations between the packets in a flow. Automated network attacks generate periodic patterns observable through spectral decomposition, which facilitates classification. This paper proposes FENED (Feature Extraction by Network spEctrum Decomposition), a method to extract features from network data. We consider the packet-arrived order within the same flow using the fast Fourier transform for binary classification. The proposed feature vector contains the module of the spectral components of the flow. Experimental results show that FENED outperforms conventional proposals because it extracts features that consider intra-flow packet-arrival order.
Michele Pushi, Alessandro S. Santos, and Anderson Silva. Governance challenges for information systems applied in smart cities control center (in Portuguese). III Workshop de Cidades Inteligentes, 2022.
This systematic mapping shows the main difficulties and opportunities of governance in control centers for Smart Cities. This mapping followed the methodological steps: protocol, execution in search engines, application of inclusion and exclusion criteria, selection of studies, data extraction, and synthesis of results. This resulted in 20 papers divided into Compliance, Operations, Training, Technologies, and Information Security. In general, the challenges are: how to meet Compliance in a dynamic environment; how to increase the Operation’s efficiency; how to keep the knowledge of all participants in the ecosystem up to date; how to keep the state-of-the-art technologies; and how to keep information secure.
Rodrigo Tinini, Matias Santos, Gustavo Figueiredo, Daniel Batista, and Carlos Kamienski. B5GSim – A Simulator for Beyond 5G Networks (in Portuguese). Tools Session of the 40th Brazilian Symposium on Computer Networks and Distributed Systems, 2022.
The use of Cloud and Fog Computing, Network Functions Virtualization and transport networks based on the enhanced Common Public Radio Interface protocol (eCPRI), are the pillars of future Beyond 5G (B5G) networks. By these technologies, such networks can operate energy-efficiently while providing wide coverage and high transmission rates to mobile users in large-scale network scenarios. However, as it is not trivial to build experimental scenarios for such networks, simulation tools are used to evaluate them. So, in this paper we present the B5GSim simulator, a specialist tool for the simulation of 5G and B5G networks.
Fabio Kon, Éderson Cássio Ferreira, Higor Amario de Souza, Fábio Duarte, Paolo Santi, and Carlo Ratti. Abstracting mobility flows from bike-sharing systems. Public Transport, 2022.
Bicycling has grown significantly in the past ten years. In some regions, the implementation of large-scale bike-sharing systems and improved cycling infrastructure are two of the factors enabling this growth. An increase in non-motorized modes of transportation makes our cities more human, decreases pollution, traffic, and improves quality of life. In many cities around the world, urban planners and policymakers are looking at cycling as a sustainable way of improving urban mobility. Although bike-sharing systems generate abundant data about their users’ travel habits, most cities still rely on traditional tools and methods for planning and policy-making. Recent technological advances enable the collection and analysis of large amounts of data about urban mobility, which can serve as a solid basis for evidence-based policy-making. In this paper, we introduce a novel analytical method that can be used to process millions of bike-sharing trips and analyze bike-sharing mobility, abstracting relevant mobility flows across specific urban areas. Backed by a visualization platform, this method provides a comprehensive set of analytical tools to support public authorities in making data-driven policy and planning decisions. This paper illustrates the use of the method with a case study of the Greater Boston bike-sharing system and, as a result, presents new findings about that particular system. Finally, an assessment with expert users showed that this method and tool were considered very useful, relatively easy to use and that they intend to adopt the tool in the near future.
All the software described in this paper is available as open source at https://gitlab.com/interscity/bike-science
Bruna M.O.S. Cordeiro, Roberto Rodrigues-Filho, Iwens G. Sene-Júnior, and Fábio M. Costa. STEER: Redes IoT Dirigidas por Intenções e Baseadas em SDN. XVI Simpósio Brasileiro de Computação Ubíqua e Pervasiva (SBCUP 2022), 2022.
IoT infrastructures are becoming increasingly more difficult to manage. One of the main issues is the high volatility present in the infrastructure, which increasingly demands self-adaptive solutions. As a response, this work presents STEER (Sdn-based inTEnt drivEn iot netwoRks), a new approach for the dynamic adaptation of IoT networks, based on the unification of Intent-Driven Networks (IDN) and Software-Defined Networks (SDN). particularly, we explore the ability of IDNs to interpret an application’s intent, using an IDN-based mediator attached to SDN-controllers to autonomously change the IoT network behavior at runtime, thus realizing the intent according to the current operating context of the network.
Fillipe Santos, Roger Immich, and Edmundo R. M. Madeira. Multimedia services placement algorithm for cloud-fog hierarchical environments. Computer Communication, Issue 191, 2022.
With the rapid development of mobile communication, multimedia services have experienced explosive growth in the last few years. The high quantity of mobile users, both consuming and producing these services to and from the Cloud Computing (CC), can outpace the available bandwidth capacity. Fog Computing (FG) presents itself as a solution to improve on this and other issues. With a reduction in network latency, real-time applications benefit from improved response time and greater overall user experience. Taking this into account, the main goal of this work is threefold. Firstly, it is proposed a method to build an environment based on Cloud–Fog Computing (CFC). Secondly, it is designed two models based on Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM). The goal is to predict demand and reserve the nodes’ storage capacity to improve the positioning of multimedia services. Later, an algorithm for the multimedia service placement problem which is aware of data traffic prediction is proposed. The goal is to select the minimum number of nodes, considering their hardware capacities for providing multimedia services in such a way that the latency for servicing all the demands is minimized. An evaluation with actual data showed that the proposed algorithm selects the nodes closer to the user to meet their demands. This improves the services delivered to end-users and enhances the deployed network to mitigate provider costs. Moreover, reduce the demand to Cloud allowing turning off servers in the data center not to waste energy.
Miguel Vasconcelos, Daniel Cordeiro, and Fanny Dufossé. Indirect Network Impact on the Energy Consumption in Multi-clouds for Follow-the-renewables Approaches. Proceedings of the 11th International Conference on Smart Cities and Green ICT Systems - SMARTGREENS, 2022.
Cloud computing has become an essential component of our digital society. Efforts for reducing its environmental impact are being made by academics and industry alike, with commitments from major cloud providers to be fully operated by renewable energy in the future. One strategy to reduce nonrenewable energy usage is the “follow-the-renewables”, in which the workload is migrated to be executed in the data centers with the most availability of renewable energy. In this paper, we study the indirect impacts on the energy consumption caused by the additional load in the network generated from the live migrations of the “follow-the-renewables” approaches. We then provide an algorithm that thoroughly considers the network to schedule the live migrations and, combined with an accurate estimation model for the duration of the migrations, is able to perform the live migrations without network congestion with the same or even reducing the brown energy consumption in comparison to other state-of-the-art algorithms.
João Francisco Lino Daniel, Alfredo Goldman, and Eduardo Martins Guerra. Are knowledge and usage of microservices patterns aligned? An exploratory study with professionals. IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC), 2022.
Microservices Architecture is a trending solution for large systems, which counts with an extensive pattern language that defines its base practices and documents solutions to recurrent problems. However, there is a lack of studies investigating how these patterns are known and applied by professionals. Understanding how the patterns are used enables to comprehend the design process for this architectural style and identify opportunities for improvement. So, this work aims to collect and analyze information about how professionals know and use microservice patterns. To achieve that, we conducted a questionnaire study focused on eleven patterns that directly influence the architecture and components structure. The questionnaire was answered by 63 participants and revealed that, in general, they know the patterns, but with a significant amount declaring that it was known only as a practice. Additionally, among other results, our study also identified that the patterns are more commonly adopted at the project beginning rather than by refactoring and that they frequently are adopted more than once in the same system.
Fabíola M. C. de Oliveira, Luiz F. Bittencourt, Reinaldo A. C. Bianchi, and Carlos A. Kamienski. Drones in the Big City: Reducing Air Delivery Collisions (in Portuguese). VI Workshop de Computação Urbana (CoUrb), 2022.
Empresas de entregas já estão realizando testes em pequena escala com drones. Em geral, para atender a grandes cidades, é necessário considerar um grande número de drones. Neste cenário, é fundamental evitar colisões com outros drones ou obstáculos típicos de ambientes urbanos. Este artigo propõe uma estratégia de prevenção de colisões chamada GeoDrone, que tem sua eficácia comparada com duas abordagens: manter a rota original e um algoritmo geométrico da literatura. GeoDrone reduziu as colisões em até 14,5 vezes em relação ao algoritmo da literatura, portanto, concluímos que estratégias geométricas reduzem substancialmente as colisões neste cenário, mas não as eliminam, indicando a necessidade de especificar abordagens mais sofisticadas.
Received the Best Paper Award.
Gustavo Camilo, Gabriel Rebello, Lucas Souza, Guilherme Thomaz, Maria Potop-Butucaru, Marcelo Amorim, Miguel Campista, and Luís Costa. Payment Channel Networks: Providing Scalability for Payments in Cryptocurrencies (in Portuguese). XL Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), 2022.
A corrente de blocos revolucionou a transferência de ativos no século XXI e permitiu a criação e a ampla adoção de criptomoedas. Apesar do grande sucesso das criptomoedas, o baixo desempenho dos protocolos de consenso utilizados ainda dificulta sua adoção como método de pagamento no dia-a-dia. Outros fatores que impedem o avanço das criptomoedas como método de pagamento alternativo são a alta latência de confirmação e o alto valor das taxas. Assim, a tecnologia de rede de canais de pagamento (Payment Channel Network – PCN) apresenta uma solução rápida e segura para o problema da escalabilidade da corrente de blocos. As redes de canais de pagamento introduzem uma nova maneira de transacionar, exibindo alta vazão de transações ao minimizar o número de transações que vão para a corrente de blocos. Este capítulo aborda de forma prática a tecnologia de redes de canais de pagamentos para prover a troca eficiente e ágil de criptomoedas. A atividade prática utiliza o PCNsim, um simulador modular de redes de canais de pagamento desenvolvido pelo GTA (Grupo de Teleinformática e Automação). O objetivo deste capítulo é demonstrar os fundamentos-chave das redes de canais de pagamento e relacionar esses conceitos aos desafios de pesquisa em redes de computadores e segurança da informação. Espera-se que, ao final do capítulo, seus participantes dominem os fundamentos de redes de canais de pagamentos, desenvolvendo as habilidades de identificar de forma crítica as suas vantagens e desvantagens. Mais ainda, espera-se que os participantes entendam os desafios relacionados à privacidade e roteamento e estejam na vanguarda da tecnologia para promover pesquisas de alto nível na área.
Lucas Souza, Gustavo Camilo, Matteo Sammarco, Miguel Campista, and Luís Costa. Federated Learning with Hierarchical Grouping of Clients to Increase Accuracy (in Portuguese). XL Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), 2022.
Federated learning performance depends on the data distribution, deteriorating in scenarios in which clients hold heterogeneous data. We propose a hierarchical client clustering system to mitigate the performance problems of federated learning in non-Independent and Identically Distributed (IID) scenarios. Our proposal efficiently groups clients with approximately IID data distribution, achieving fast and accurate model convergence. We initialize the system, executing a clustering unsupervised learning algorithm on the bias vector of the last layer of the clients’ neural network in the server. The DBSCAN algorithm demonstrated better clustering results, correctly identifying clusters even when all clients have datasets with IID distributions. Finally, the results show an increase of model accuracy by up to 16% compared to the traditional federated learning non-IID scenarios.
Gustavo Camilo, Lucas Souza, Miguel Campista, Luis Costa, and Otto Duarte. A Blockchain-based System for Secure and Distributed Virtual Network Functions Orchestration. IEEE International Conference on Communications - ICC, 2022.
Service provisioning in next-generation networks, such as 5G and 6G, relies on virtualization to carry out multi-domain and multi-tenant connections. In these scenarios, virtual network functions (VNF) orchestration becomes susceptible to security threats once trust between peers cannot be assumed. This paper proposes a blockchain-based system for an agile, secure, and distributed provisioning of virtual network functions in scenarios with multiple administrative domains. Our proposal employs smart contracts to deliver all stages of a service-level-agreement management life cycle automatically. We develop, implement, and evaluate a prototype of the proposed system using smart contracts running on Hyperledger Fabric. The performance evaluation results show that the system guarantees high-rate VNF provisioning, reaching hundreds of slice requests per second in a trustful way.
Gabriel A. F. Rebello, Gustavo F. Camilo, Maria Potop-Butucaru, Miguel E. M. Campista, Marcelo D. Amorim, and Luís H. M. K. Costa. PCNsim: A Flexible and Modular Simulator for Payment Channel Networks. IEEE International Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2022.
Payment channel networks (PCN) enable the use of cryptocurrencies in everyday life by solving the performance issues of blockchains. Nevertheless, the main implementations of payment channel networks lack the flexibility to test new proposals that can address fundamental challenges, such as efficient payment routing and maximization of the payment success rate. In this demo paper, we propose PCNsim, an open-source simulator based on OMNeT++, which fully reproduces the default behavior of a payment channel network. We build the simulator in a modular architecture that allows easy topology/workload customization and automates result visualization. The core mechanism of PCNsim implements the specifications of the Lightning Network. We evaluate our proposal with a dataset of credit card transactions in a scale-free topology and show that it successfully demonstrates the difference between two routing methods in different setups.
Gabriel A. F. Rebello, Maria Potop-Butucaru, Marcelo Dias de Amorim, and Otto C. M. B. Duarte. Securing Wireless Payment-Channel Networks With Minimum Lock Time Windows. IEEE International Conference on Communications (ICC), 2022.
Payment-channel networks (PCN) enhance the impact of cryptocurrencies by providing a fast and consensus-free solution to the scalability problems of traditional blockchain protocols. However, PCNs often rely on powerful nodes with high availability, large storage capacity, and strong computational power, which hinders their adoption in mobile environments. In this paper, we consider a PCN architecture that extends the functionalities of traditional PCNs to wireless resource-constrained devices. We address the token theft problem, a vulnerability that is critical on wireless PCNs, and propose a countermeasure based on minimum time windows that lock tokens whenever a user disconnects. We evaluate our proposal with real data from Bitcoin’s Lightning Network and 3G/4G mobile broadband networks. The results show that the countermeasure is most effective when devices present high availability and that there is a security-efficiency trade-off when connectivity is low.
Guilherme Thomaz, Matheus Guerra, Matteo Sammarco, and Miguel Campista. CACIC – Trusted Access Control Using Enclaves to Data in Internet of Things Clouds (in Portuguese). XL Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), 2022.
Os sensores da Internet das Coisas geram um enorme volume de informações sensíveis processadas em nuvem, como geolocalização, consumo de energia e sinais biomédicos. Os sistemas de controle de acesso convencionais falham em garantir que esses dados sejam acessados e modificados apenas por usuários autorizados em um cenário em que a nuvem é maliciosa. Este artigo propõe uma arquitetura para transmissão, armazenamento, processamento e disponibilização de dados sensíveis de Internet das Coisas em nuvens computacionais, utilizando ambientes de execução confiáveis. Diferente das arquiteturas convencionais, o cliente personaliza para quem os seus dados são disponibilizados, pois as publicações e consultas aos dados são processadas em regiões isoladas na memória chamadas de enclaves. A implementação do servidor seguro processa cerca de quinhentas requisições por segundo e o atraso inserido pelo processamento em enclaves de memoria é igual a dezessete milissegundos. Os resultados revelam que a proposta é ágil e escalável, ao mesmo tempo que garante segurança, ate mesmo quando o sistema operacional ou o administrador da nuvem são comprometidos.
Roberto Rodrigues Filho and Barry Porter. Hatch: Self-distributing Systems for Data Centers. Future Generation Computer Systems (FGCS) v. 132, 2022.
Designing and maintaining distributed systems remains highly challenging: there is a high-dimensional design space of potential ways to distribute a system’s sub-components over a large-scale infrastructure; and the deployment environment for a system tends to change in unforeseen ways over time. For engineers, this is a complex prediction problem to gauge which distributed design may best suit a given environment. We present the concept of self-distributing systems, in which any local system built using our framework can learn, at runtime, the most appropriate distributed design given its perceived operating conditions. Our concept abstracts distribution of a system’s sub-components to a list of simple actions in a reward matrix of distributed design alternatives to be used by reinforcement learning algorithms. By doing this, we enable software to experiment, in a live production environment, with different ways in which to distribute its software modules by placing them in different hosts throughout the system’s infrastructure. We implement this concept in a framework we call Hatch, which has three major elements: (i) a transparent and generalized RPC layer that supports seamless relocation of any local component to a remote host during execution; (ii) a set of primitives, including relocation, replication and sharding, from which to create an action/reward matrix of possible distributed designs of a system; and (iii) a decentralized reinforcement learning approach to converge towards more optimal designs in real time. Using an example of a self-distributing web-serving infrastructure, Hatch is able to autonomously select the most suitable distributed design from among ≈700,000 alternatives in about 5 min.
Fabrício B. Carvalho, Ronaldo A. Ferreira, Ítalo Cunha, Marcos A. M. Vieira, and Murali K. Ramanathan. Dyssect: Dynamic Scaling of Stateful Network Functions. Proceedings of the IEEE International Conference on Computer Communications (IEEE INFOCOM'22), 2022.
Network Function Virtualization promises better utilization of computational resources by dynamically scaling resources on demand. However, most network functions (NFs) are stateful and require state updates on a per-packet basis. During a scaling operation, cores need to synchronize access to a shared state to avoid race conditions and to guarantee that NFs process packets in arrival order. Unfortunately, the classic approach to control concurrent access to a shared state with locks does not scale to today’s throughput and latency requirements. Moreover, network traffic is highly skewed, leading to load imbalances in systems that use only sharding to partition the NF states. To address these challenges, we present Dyssect, a system that enables dynamic scaling of stateful NFs by disaggregating the states of network functions. By carefully coordinating actions between cores and a central controller, Dyssect migrates shards and flows between cores for load balancing or traffic prioritization without resorting to locks or reordering packets. Our experimental evaluation shows that Dyssect reduces tail latency up to 32% and increases throughput up to 19.36% when compared to state-of-the-art competing solutions.
Brivaldo A. Silva Junior, Paulo Mol, Osvaldo Fonseca, Ítalo Cunha, Ronaldo A. Ferreira, and Ethan Katz-Bassett. Automatic Inference of BGP Location Communities. Proceedings of the ACM on Measurement and Analysis of Computing Systems, v. 6, 2022.
The Border Gateway Protocol (BGP) orchestrates Internet communications between and inside Autonomous Systems. BGP’s flexibility allows operators to express complex policies and deploy advanced traffic engineering systems. A key mechanism to provide this flexibility is tagging route announcements with BGP communities, which have arbitrary, operator-defined semantics, to pass information or requests from router to router. Typical uses of BGP communities include attaching metadata to route announcements, such as where a route was learned or whether it was received from a customer, and controlling route propagation, for example to steer traffic to preferred paths or blackhole DDoS traffic. However, there is no standard for specifying the semantics nor a centralized repository that catalogs the meaning of BGP communities. The lack of standards and central repositories complicates the use of communities by the operator and research communities. In this paper, we present a set of techniques to infer the semantics of BGP communities from public BGP data. Our techniques infer communities related to the entities or locations traversed by a route by correlating communities with AS paths. We also propose a set of heuristics to filter incorrect inferences introduced by misbehaving networks, sharing of BGP communities among sibling autonomous systems, and inconsistent BGP dumps. We apply our techniques to billions of routing records from public BGP collectors and make available a public database with more than 15 thousand location communities. Our comparison with manually-built databases shows our techniques provide high precision (up to 93%), better coverage (up to 81% recall), and dynamic updates, complementing operators’ and researchers’ abilities to reason about BGP community semantics.
This paper was accepted and presented at the main track of the conference ACM SIGMETRICS, the flagship conference of the ACM special interest group for the computer systems performance evaluation community.
Diogo Gonçalves, Luiz Bittencourt, and Edmundo Madeira. End-to-end Network Slice Allocation for User Mobility Support in MobFogSim Simulator (in Portuguese). Proceedings of the 40th Brazilian Symposium on Computer Networks and Distributed Systems, 2022.
Network slicing has been presented as one promising technology for resource management in modern networks, e.g., 5G. Based on virtualisation technologies, network slicing creates different virtual networks over one common physical infrastructure. Simulators have been presented as one solution to evaluate new solutions in that context based on scalability, flexibility, and monetary aspects. MobFogSim was proposed to support the evaluation of solutions for resource management in fog computing environments, including service migration, network slicing, and support to users’ mobility. This work introduces the new features of MobFogSim in terms of the simulator’s scalability and support to end-to-end slices, which includes the management of Fog Nodes’ processing and storage resources. Simulations based on realistic parameters show the impact of different slice allocation strategies in the slices’ resource allocation as well as the improvements in the simulator’s scalability.
Robson Aleixo, Fabio Kon, Rudi Rocha, Marcela Camargo, and Raphael de Camargo. Predicting Dengue Outbreaks with Explainable Machine Learning. International Workshop on Artificial Intelligence for Health – AI4Health, 2022.
Seasonal infectious diseases, such as dengue, have been causing great losses in many countries around the world in terms of deaths, quality of life, and economic burden. In Brazil, this is relevant not only in large cities such as Rio de Janeiro and São Paulo but, according to the Ministry of Health, in another 500 cities throughout the country. Predicting the occurrence of diseases, such as dengue bursts, can be a valuable instrument for public health management as health officials can better prepare and redirect resources to the affected areas. In this paper, we present an explainable machine learning model to forecast the number of dengue occurrences in a large metropolis, Rio de Janeiro. We focus on explainable models, which provide health authorities with the reasons for outbreak predictions, allowing them to plan their actions accordingly. We trained a gradient boosting decision tree algorithm (CatBoost) with data from the National System of Information on Notifiable Diseases (SINAN), weather data, and socio-demographic data from The Brazilian Institute of Geography and Statistics (IBGE).
Received the Best Paper Award.
Artur André Oliveira, Marcos S. Buckeridge, and Roberto Hirata Jr.. Detecting tree and wire entanglements with deep learning. Trees, 2022.
Power and communication line corridors are usually mixed with urban trees, and this mixing can be the source of multiple issues like fires and communication failures. Nevertheless, urban trees are a valuable resource to the city as they dissipate heat island effects, reduce air pollution and increase general health perception. This work proposes a deep learning approach to detect trees entangled to power and communication lines using street-level imagery and perform quick quantitative and qualitative analyses based on the Grad-CAM++ method. Testing the method was performed using 1001 images from urban trees from the cities of São Paulo and Porto Alegre (both in Brazil). We found an overall accuracy of 74.6% (73.6% for São Paulo and 75.6% for Porto Alegre), suggesting that the methodology could be suitable in the future for city management to avoid risks of accidents due to contact between trees and electrical wiring. This text describes the method, a new data set of urban images, the experimental setup design and tests, and some possible future improvements.
Antonio G. P. Lobato, Martin A. Lopez, Alvaro A. Cardenas, Otto C. M. B. Duarte, and Guy Pujolle. A fast and accurate threat detection and prevention architecture using stream processing. Concurrency and Computation: Practice and Experience, 2022.
Late detection of security breaches increases the risk of irreparable damages and limits any mitigation attempts. We propose a fast and accurate threat detection and prevention architecture that combines the advantages of real-time streaming with batch processing over a historical database. We create a dataset by capturing both legitimate and malicious traffic and propose two ways of combining packets into flows, one considering a time window and the other analyzing the first few packets of each flow per period. We also investigate the effectiveness of our proposal on real-world network traces obtained from a significant Brazilian network operator providing broadband Internet to their customers. We implement and evaluate three classification algorithms and two anomaly detection methods. The results show an accuracy higher than 95% and an excellent trade-off between attack detection and false-positive rates. We further propose an improved scheme based on software defined networks that automatically prevents threats by analyzing only the first few packets of a flow. The proposal promptly and efficiently blocks threats, is robust, and can scale up, even when the attacker employs spoofed IP.
Antonio Iyda Paganelli, Abel González Mondéjar, Abner Cardoso da Silva, Greis Silva-Calpa, Mateus F. Teixeira, Felipe Carvalho, Alberto Raposo, and Markus Endler. Real-time data analysis in health monitoring systems: A comprehensive systematic literature review. Journal of Biomedical Informatics v. 127, 2022.
Health monitoring systems (HMSs) capture physiological measurements through biosensors (sensing), obtain significant properties and measures from the output signal (perceiving), use algorithms for data analysis (reasoning), and trigger warnings or alarms (acting) when an emergency occurs. These systems have the potential to enhance health care delivery in different application domains, showing promising benefits for health diagnosis, early symptom detection, disease prediction, among others. However, the implementation of HMS presents challenges for sensing, perceiving, reasoning, and acting based on monitored data, mainly when data processing should be performed in real time. Thus, the quality of these diagnoses relies heavily on the data and data analysis methods applied. Data mining techniques have been broadly investigated in health systems; however, it is not clear what real-time data analysis techniques are best suited for each context. This work carries out a search in five scientific electronic databases to identify recent studies that investigated HMS using real-time data analysis techniques. Thirty-six research studies were selected after screening 2,822 works. Applied data analysis methods, application domains, utilized sensors, physiological parameters, extracted features, claimed benefits, limitations, datasets used, and published results were described, compared and analyzed. The findings indicate that machine learning methods are trending in such studies. There is no universal solution for all health domains; however, support vector machines are a predominant method. Among the application domains, cardiovascular disease is the most investigated. Most reviewed studies reported improvements in performing data mining tasks or operational modes of solutions. Although studies tested algorithms and presented promising results, those are particular for each experiment. This review gives a comprehensive overview of HMS real-time data analysis and points to directions for future research.
Roberto Rodrigues Filho, Elvin Alberts, Ilias Gerostathopoulos, Barry Porter, and Fábio M. Costa. Emergent Web Server: An Exemplar to Explore Online Learning in Compositional Self-Adaptive Systems. International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS), 2022.
Contemporary deployment environments are volatile, with conditions that are often hard to predict in advance, demanding solutions that are able to learn how best to design a system at runtime from a set of available alternatives. While the self-adaptive systems community has devoted significant attention to online learning, there is less research specifically directed towards learning for open-ended architectural adaptation – where individual components represent alternatives that can be added and removed dynamically. In this paper we present the Emergent Web Server (EWS), an architecture-based adaptive web server with 42 unique compositions of alter-native components that present different utility when subjected to different workload patterns. This artefact allows the exploration of online learning techniques that are specifically able to consider the composition of logic that comprises a given system, and how each piece of logic contributes to overall utility. It also allows the user to add new components at runtime (and so produce new composition options), and to remove existing components; both are likely to occur in systems where developers (or automated code generators) deploy new code on a continuous basis and identify code which has never performed well. Our exemplar bundles together a fully-functional web server, a number of pre-packaged online learning approaches, and utilities to integrate, evaluate, and compare new online learning approaches.
Leonardo Leite, Gustavo Pinto, Fabio Kon, and Paulo Meirelles. The organization of software teams in the quest for continuous delivery: A grounded theory approach. Information and Software Technology v. 139, 2021.
Context:
To accelerate time-to-market and improve customer satisfaction, software-producing organizations have adopted continuous delivery practices, impacting the relations between development and infrastructure professionals. Yet, no substantial literature has substantially tackled how the software industry structures the organization of development and infrastructure teams.
Objective:
In this study, we investigate how software-producing organizations structure their development and infrastructure teams, specifically how is the division of labor among these groups and how they interact.
Method:
After brainstorming with 7 DevOps experts to better formulate our research and procedures, we collected and analyzed data from 37 semi-structured interviews with IT professionals, following Grounded Theory guidelines.
Results:
After a careful analysis, we identified four common organizational structures: (1) siloed departments, (2) classical DevOps, (3) cross-functional teams, and (4) platform teams. We also observed that some companies are transitioning between these structures.
Conclusion:
The main contribution of this study is a theory in the form of a taxonomy that organizes the found structures along with their properties. This theory could guide researchers and practitioners to think about how to better structure development and infrastructure professionals in software-producing organizations.
Gustavo Arbex, Kétly Machado, Michele Nogueira, Daniel Batista, and Roberto Hirata Jr.. IoT DDoS Detection Based on Stream Learning. 12th International Conference on Network of the Future (NoF), 2021.
The Internet of Things (IoT) represents a new reality, as smart devices spread quickly and a higher number of applications arises. This attracts the attention of not only legitimate users but also attackers aiming to jeopardize the entire IoT infrastructure. Intrusion detection mechanisms are paramount in this networking environment as its first line of defense. Hence, this work proposes a Network Intrusion Detection System (NIDS) that deals with the Distributed Denial of Service (DDoS) attack, one of the most critical attacks that occur through IoT. The proposed NIDS uses stream learning to detect DDoS attacks in the IoT network and is designed to be deployed in a fog infrastructure. The detection model, built on Hoeffding Anytime Tree (HATT) algorithm, achieved a 99% accuracy and a 99% recall.
Alan Barzilay, Caio Martinelli, Michele Nogueira, Daniel Batista, and Roberto Hirata Jr.. AnubisFlow: A Feature Extractor for Distributed Denial of Service Attack Classification. 12th International Conference on Network of the Future (NoF), 2021.
The detection and mitigation of DDoS attacks require a system to analyze and process the incoming network flow in a live capture manner. In this scenario, an efficient analysis depends on a good set of features to classify the traffic. With this goal in mind, we propose a technique based on a new set of features that are computationally inexpensive and descriptive of the data stream. Moreover, the technique considers the flows in many moments, not only when they are finished. We analyze its predicting performance by creating a decision tree model and a logistic regression, which achieved 99.98% and 95.99% Cohen’s Kappa coefficient, respectively. In spirit with the recent trend toward reproducibility of research results, we integrate the proposal in an open-source tool called AnubisFlow. Also, our analysis for the models is available as open data to the scientific community.
Caio Lente, Roberto Hirata Jr., and Daniel Batista. An Improved Tool for Detection of XSS Attacks by Combining CNN with LSTM. Salão de Ferramentas do Simpósio Brasileiro em Segurança da Informação e de Sistemas Computacionais (SBSeg), 2021.
Cross-Site Scripting (XSS) is still a significant threat to web applica- tions. By combining Convolutional Neural Networks (CNN) with Long Short- Term Memory (LSTM) techniques, researchers have developed a deep learning system called 3C-LSTM that achieves upwards of 99.4% accuracy when predict- ing whether a new URL corresponds to a benign locator or an XSS attack. This paper improves on 3C-LSTM by proposing different network architectures and validation strategies and identifying the optimal structure for a more efficient, yet similarly accurate, version of 3C-LSTM. The authors identify larger batch sizes, smaller inputs, and cross-validation removal as modifications to achieve a speedup of around 3.9 times in the training step.
Murilo Borges Ribeiro and Kelly Rosa Braghetto. A Data Integration Architecture for Smart Cities. XXXVI Simpósio Brasileiro de Bancos de Dados (SBBD), 2021.
The data generated by smart cities have low integration, as the systems that produce them are usually closed and developed for specific needs. Moreover, the large volume of data, and the semantic and structural changes in datasets over time make the use of data to support decision-making even more difficult. In this work, we identify the main requirements of a data integration system to support decision-making in cities, focusing on its challenges. We analyze some existing data integration solutions, to uncover their features and limitations. Based on these results, we propose a new microservice architecture to support the development of software platforms for integrating smart cities’ heterogeneous data and a guideline to assess their performance.
Gabriel Antonio Rebello, Maria Potop-Butucaru, Marcelo de Amorim, and Otto Carlos Duarte. Protecting Wireless Payment Channel Networks with Minimal Time Blocking Windows (in Portuguese). Anais do XXI Simpósio Brasileiro em Segurança da Informação e de Sistemas Computacionais, 2021.
Redes de canais de pagamento (Payment Channel Networks – PCN) aumentam o impacto das criptomoedas, fornecendo uma solução rápida e independente de consenso para mitigar os problemas de escalabilidade dos protocolos tradicionais de correntes de blocos (blockchain). No entanto, as PCNs atuais são baseadas em nós robustos com alta disponibilidade e capacidade computacional, dificultando sua adoção em ambientes móveis e sem fio. Este artigo propõe uma arquitetura PCN híbrida que estende as funcionalidades das PCNs tradicionais para cenários de dispositivos sem fio com recursos limitados. O artigo analisa a vulnerabilidade de roubo de tokens e propõe uma contramedida com base em janelas de tempo de bloqueio. O artigo avalia a proposta com dados reais da Lightning Network e de redes de banda larga móvel. Os resultados mostram que a janela de tempo mínimo de bloqueio depende do tempo de inatividade dos dispositivos e que selecionar uma janela padrão é mais eficaz quando os dispositivos apresentam alta disponibilidade.
Franklin Barbosa and Renato Ishii. A Neural Network Approach to High Cost Patients Detection. Computational Science and Its Applications – ICCSA. Lecture Notes in Computer Science, vol 12951, 2021.
The growing aging of the world’s population along with several environmental, social and economic factors, end up posing major challenges for public health. One challenge is the detection and treatment of high cost patients, i.e., a small percentage of patients associated with majority of expenditures in healthcare. The early detection of patients who may become high cost in the future can be used to better target interventions focusing on preventing their transition or, in the case of those who are already in such condition, to allow appropriate approaches, rather than generic ones. In both cases, the detection of such patients can be beneficial, reducing avoidable costs and improving patients’ condition. In order to make such detection, this work has focused on using deep learning techniques, specifically, Neural Networks, along with a dataset composed of survey answers applied by the United States government, called Medical Expenditure Panel Survey (MEPS) and attributes gathered from the literature. For the purposes of this work, 11 years of the MEPS dataset were considered, including the years from 2006 to 2016. The models created have shown results ranging between 83% to 90% on metrics such as accuracy, precision, recall, specificity and f1-score. This work also aimed to make the creation and testing of such networks easier, by providing the tools developed during its evolution on GitHub.
Alessandro S. Santos, Alessandra C. Corsi, Rynaldo Z. H. Almeida, Mauro K. Noda, Ícaro Gonçales, Rodrigo N. Ribeiro, Cezar O. Machado, Matheus Polkorny, Malena D'Elia Otero, Ana Elisa S. Abreu, Caio Azevedo, and Mauro Spinola. Feasibility study for detecting shallow landslides using IoT devices in smart cities. IEEE International Smart Cities Conference, 2021.
Inertial sensors are considered a new strategy to assess the slope movement prior to landslides in risk areas. It is a challenge to understand limitations, advantages, and disadvantages of the signals analysis from inertial sensors embedded in IoT devices for monitoring this phenomenon. Landslides can take a long time to collapse completely, and collecting data in real situations can imply a long-term collection, with no guarantees of recording the phenomenon. Promoting accelerated experiments can be an alternative for evaluating algorithms to detect soil movement. Therefore, this paper presents the results of two experiments performed for data collection by inertial sensors deployed in sandy soil in a dump truck. The signals were collected during sand unloading to evaluate the performance of the IoT devices in events similar to a landslide phenomenon.
Marcos Amaris, Mayuri Morais, and Raphael Camargo. Efficient Prediction of Region-wide Traffic States in Public Bus Networks using LSTMs. 24th IEEE International Conference on Intelligent Transportation (ITSC), 2021.
Public bus systems are impacted by many factors, such as varying traffic conditions, passenger demand, and weather changes. One can combine all those factors that affect bus travel times into a single factor called link state, where a link represents part of a bus route. Several works exist that predict single link states using different statistical and machine learning approaches. More recently, deep learning techniques, such as LSTMs, started to be used to predict the state of entire bus routes. The main problem with this approach is that it uses extensive computational resources. In this work, we evaluate the use of LSTMs to predict the state of entire city regions instead of single routes. It has two advantages: (i) the state of each link is evaluated only once for all the bus routes that cross it, and (ii) information from buses from all routes can be used to determine future link states. Using a shallow bidirectional LSTM architecture produced accurate state predictions with an average MAPE of 12.5. Moreover, we show that it can be trained daily and used to predict link states in real-time for a large metropolis, like São Paulo.
Luis Rodriguez and Daniel Batista. Towards Improving Fuzzer Efficiency for the MQTT Protocol. 26th IEEE Symposium on Computers and Communications (IEEE ISCC), 2021.
MQTT’s security has been a major concern because of its weak protocol implementations. Over the last few years, several fuzzing frameworks have been proposed to mitigate this issue. However, these frameworks lack sufficient knowledge of MQTT’s specifications, requiring a considerable amount of network packets to cover all of its features and functionality. In this paper, we explain how to improve the efficiency of fuzzing frameworks for MQTT by using a grammar based on its specifications. Although defining a grammar is time-consuming and complex, these drawbacks are overshadowed by its benefits, such as deep state exploration and efficiency. Our improvements are implemented in MQTTGRAM, a new grammar-based fuzzer for MQTT. Due to these improvements, MQTTGRAM offers higher code coverage with significantly fewer packets than existing MQTT fuzzers. For instance, MQTTGRAM exchanges up to 9x fewer packets than its counterparts without reducing the line coverage.
Tallys G. Martins, Nelson Lago, Eduardo F. Z. Santana, Alexandru Telea, Fabio Kon, and Higor A. de Souza. Using bundling to visualize multivariate urban mobility structure patterns in the São Paulo Metropolitan Area. Journal of Internet Services and Applications, vol 12, 2021.
Internet-based technologies such as IoT, GPS-based systems, and cellular networks enable the collection of geolocated mobility data of millions of people in large metropolitan areas. In addition, large, public datasets are made available on the Internet by open government programs, providing ways for citizens, NGOs, scientists, and public managers to perform a multitude of data analysis with the goal of better understanding the city dynamics to provide means for evidence-based public policymaking. However, it is challenging to visualize huge amounts of data from mobility datasets. Plotting raw trajectories on a map often causes data occlusion, impairing the visual analysis. Displaying the multiple attributes that these trajectories come with is an even larger challenge. One approach to solve this problem is trail bundling, which groups motion trails that are spatially close in a simplified representation. In this paper, we augment a recent bundling technique to support multi-attribute trail datasets for the visual analysis of urban mobility. Our case study is based on the travel survey from the São Paulo Metropolitan Area, which is one of the most intense traffic areas in the world. The results show that bundling helps the identification and analysis of various mobility patterns for different data attributes, such as peak hours, social strata, and transportation modes.
Matheus Tavares Bernardino, Giuliano Belinassi, Paulo Meirelles, Eduardo Martins Guerra, and Alfredo Goldman. Improving Parallelism in Git and GCC: Strategies, Difficulties, and Lessons Learned. IEEE Software ( Volume: 38, Issue: 5, Sept.-Oct.), 2021.
Manufacturers are creating powerful CPUs by exponentially increasing the number of cores over time, as producing faster sequential chips has become more expensive. Developers must now employ parallel strategies and design parallel algorithms if they want to use every resource available in the machine. Still, many successful open-source projects are mostly sequential, failing to harness the full computational power available. This article presents approaches for performance improvements into two large and well-known open-source projects, Git and GCC, using parallel programming. We share the difficulties faced and the strategies used, concluding with a set of lessons learned useful to similar parallelization processes.
Guilherme Oliveira, Jonathan Porto, Nelson Prates Jr., Aldri Santos, Michele Nogueira, and Daniel Batista. Network Function Virtualization in the IoT: An Overview of Performance Management vs. Security (in Portuguese). Livro de Minicursos do XXXIX Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, 2021.
This chapter presents open issues and the state-of-the-art related to the use of Network Function Virtualization (NFV) in the detection and mitigation of security threats in the Internet of Things (IoT). The main characteristics of NFV, the project, architectures, and protocols of networks to connect IoT devices are also discussed as basis to understand the main concepts. It focuses also on the NFV management specifications and how they affect performance and security in IoT. Next, the chapter presents the issues related to the performance of NFV applied to security in IoT. Then, it highlights a case study on the MCTIC/FAPESP MENTORED Testbed, an experimental environment being deployed for the community that provides realistic scenarios for simulating specific vulnerabilities and for evaluating network security mechanisms in a controlled manner. Finally, the chapter discusses the main open challenges in order to increase the interest of readers to conduct research on topics that bring together virtualization, IoT and network security.
Roberto Rodrigues Filho, Barry Porter, Fábio M. Costa, and Iwens Sene Júnior. Emergent Software Systems: Theory and Practice. XXXIX Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), 2021.
Autonomic Computing and related research communities have drawn attention from researchers and industry practitioners who seek techniques and tools to build large scale, reliable self-adaptive systems. However, building autonomic solutions remains a challenge: i) the upfront effort to develop such systems is very high, making them costly to implement; ii) only specialised parts of the system are made adaptive, limiting its flexibility in handling unknown operating conditions; and iii) state-of-the-art approaches still heavily rely on design-time predictions of operating conditions, making systems execution uncertain when predictions are wrong. To address these challenges, the concept of Emergent Software Systems has been proposed. The Emergent Software approach aims to reduce the upfront effort to create autonomic solutions, and it supports fully adaptive systems able to autonomously learn about the system’s structure and operating environment with no predefined knowledge or predictions. This chapter aims to disseminate Emergent Software Systems, presenting the central concept and tools to realise the approach.
Franklin Magalhães Ribeiro Junior and Carlos Kamienski. Data resilience system for fog computing. Data resilience system for fog computing. Computer Networks, vol. 195, 2021.
Fog computing improves IoT systems by analyzing and storing data locally at the network edge. However, it is challenging to design a fog-based IoT system data flow as data transmissions must be agile and resistant to network failures and disconnections. Data collected by sensors must persist in the fog, even during a long disconnection period. When the connection is available again, the fog needs to send the data immediately to the cloud. This paper proposes and evaluates the Fog-DaRe system for supporting data flow resilience between fog and cloud during network availability and unavailability situations. Fog-DaRe allows data persistence in the fog and uses different compression techniques to reduce the data volume. We evaluate 10 data flow configurations in experiments with 5,000 simulated sensors, computing hardware, and network metrics. The Fog-DaRe strategy yields different tradeoffs for scenarios with network unavailability, lossy compression techniques, and data encryption. For example, our results reveal a reduction of at least 77.7% for fog-to-cloud batch transfer time and 81.5% for fog storage usage when the network is unavailable. When the network between fog and cloud is available, delay increases by 10% due to data buffering in the fog, but storage requirement drops 73.6%. Lossy data filtering yields a reduction of 83.3% in batch transfer time and 50% in storage. Also, the compression of encrypted data increases storage usage and batch transfer time by 125%, compared to plain data.
Eduardo S. Gama, Lucas Otávio N. De Araújo, Roger Immich, and Luiz F. Bittencourt. Video Streaming Analysis in Multi-tier Edge-Cloud Networks. 8th International Conference on Future Internet of Things and Cloud (FiCloud), 2021.
Video streaming services represent most internet traffic, and according to Cisco forecasts, in 2022, 82% of all internet traffic will be dominated by video streaming. This includes current video services as well as innovative services such as Real-Time video Streaming and future cloud gaming, whereas, for mobile devices, this estimate represents 78% of all mobile data traffic. A good cloud architecture partially solves some issues related to the live stream and Video on Demand (VoD) services to accommodate video traffic. However, a centralized cloud service introduces some issues such as higher latency and core network congestion. Therefore, to improve video services, it is paramount to distribute video streams according to their requirements properly: a real-time video streaming infrastructure is an interactive service that needs reduced delays (a few milliseconds). At the same time, a non-interactive VoD delivery can tolerate higher delays without impairing the quality of experience. This work discusses and gives evidence for the need for proper management and orchestration of video delivery over the Internet as it is core to the smooth coexistence of video services in multi-tier edge/cloud environments. The results assessment corroborate that well-defined video management can considerably increase the end-user QoE.
Diogo Gonçalves, Luiz Bittencourt, and Edmundo Madeira. Dynamic Network Slicing in Fog Computing for Mobile Users (in Portuguese). XXXIX Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, 2021.
A Computação em Névoa é responsável por prover recursos computacionais na borda da rede a usuários com diferentes características e demandas. Por meio da virtualização de seus recursos, é possível criar múltiplas Redes Virtuais, ou Fatias de Rede, sobre uma mesma arquitetura física, cada uma atendendo um grupo de usuários. Nesse contexto, avaliar o desempenho de tais redes em diferentes cenários se torna primordial para identificar pontos fortes e fracos a serem considerados no desenvolvimento de mecanismos para gerenciar a rede. Este artigo apresenta uma análise de desempenho de diferentes abordagens de alocação de Fatias de Rede com o objetivo de otimizar o processo de migração de serviços na névoa. Resultados obtidos no simulador MobFogSim apontam que, devido a variações de demanda, o desempenho da alocação estática dessas redes pode se degradar ao longo do tempo. A alocação dinâmica de fatias de rede se apresentou como uma solução para esse cenário, a depender do custo computacional necessário para a reconfiguração dessas redes.
Lucas Souza, Gustavo Camilo, and Otto Duarte. Enhancing Automatic Attacks Detection by Spectral Decomposition of Network Packets. XXXIX Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, 2021.
A classificação de fluxos para a identificação de ataques em redes de computadores por aprendizado de máquina utiliza características quantitativas que sintetizam as informações de pacotes pertencentes a um fluxo. Entretanto, as características convencionais, como tamanho de pacote e número de bytes, geram redundâncias e não representam as correlações temporais entre os pacotes de um fluxo. Ataques de rede automatizados geram padrões periódicos observáveis através da decomposição espectral, o que facilita a classificação. Este artigo propõe o FENED1, um método para extrair características de dados de rede considerando a ordem de chegada dos pacotes dentro de um mesmo fluxo através da transformada rápida de Fourier para a classificação binária. O vetor de características proposto contém o módulo das componentes espectrais do fluxo. Os resultados mostram que a proposta é melhor ou igual às propostas convencionais de extração de características que desconsideram a ordem de chegada dos pacotes em um fluxo.
Gustavo Camilo, Lucas Souza, and Otto Duarte. A secure distributed system for the provisioning of Network Virtual Functions as Services through blockchains. XXXIX Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, 2021.
A virtualização nas redes de próxima geração, como 5G e 6G, se servem de modelos de provisionamento de serviços em cenários multi-domínios e multi-inquilinos. Nestes cenários, a orquestração de funções virtuais de rede (Virtual Network Function NFV) e o cumprimento de acordo de níveis de serviço (Service Level Agreement SLA) tornam-se susceptíveis a ameaças de segurança, uma vez que não há confiança entre os pares. Este artigo propõe um sistema baseado em corrente de blocos para o provisionamento ágil, seguro e distribuído de funções virtuais de rede em cenários de múltiplos domínios administrativos. A proposta utiliza contratos inteligentes para atender de maneira automática todas as etapas do ciclo de vida do gerenciamento de um acordo de nível de serviço. Os resultados da análise de desempenho de um protótipo desenvolvido mostram que o sistema garante o provisionamento seguro e ágil de VNFs, atendendo a centenas de requisições de criação de fatias por segundo.
Henrique Carvalho, Jorge Ribeiro, Daniel Batista, and José Pina. Performance Analysis of a Tool for Visualization of Hashes on Mobile Devices (in Portuguese). Workshop de Trabalhos de Iniciação Científica e de Graduação (WTICG) do SBSeg, 2021.
Um aplicativo de segurança que aumente a privacidade de comunicações deve ter desempenho que garanta a sua usabilidade sem comprometer a reserva de recursos escassos, principalmente em dispositivos móveis. Dentre esses aplicativos, destacam-se aqueles, como o hashify, que manipulam ou geram animações a partir de hashes criptográficos. Este artigo apresenta a análise de desempenho do hashify, avaliando o tempo de geração de animações e consumo de memória e rede. Resultados preliminares obtidos com um dispositivo Android mostraram que a geração de imagens pelo software ocorre, em média, em 22,6ms, um tempo relativamente baixo e que mostra que ele pode vir a ser integrado em aplicativos móveis.
Renê Cardozo and Daniel Batista. Parameter extraction for network simulation in widely-used mobile apps (in Portuguese). IV Workshop de Trabalhos de Graduação e Iniciação Científica (WTG) do SBRC, 2021.
Este artigo apresenta uma investigação a respeito da aderência do novo protocolo da camada de transporte, QUIC, por aplicações de grande utilização em dispositivos móveis e suas principais características de tráfego de rede. Para isso, foram escolhidos nove aplicativos com mais de 1 bilhão de downloads cada na Play Store, e eles tiveram seu tráfego de rede capturado durante cinco minutos de utilização por meio do software Wireshark. Baseado nas características encontradas (latência, bytes transferidos, quantidade de pacotes transferidos, taxa de transferência, tamanho dos pacotes e endereços IP envolvidos na comunicação), foram extraídos parâmetros que podem ajudar na simulação destas aplicações em simuladores de rede como o ns-3.
Bruno Cunha and Daniel Batista. Evaluation of the MQTT Protocol Integration in a Smart Cities Platform (in Portuguese). IV Workshop de Trabalhos de Graduação e Iniciação Científica (WTG) do SBRC, 2021.
O número de aplicativos baseados no protocolo Message Queuing Telemetry Transport (MQTT) tem aumentado bastante, fazendo com que esse seja o protocolo pub/sub mais popular do mundo. Este artigo apresenta o desenvolvimento e a avaliação de um adaptador MQTT para a plataforma de cidades inteligentes InterSCity, uma plataforma de código aberto para aplicações robustas de cidades inteligentes e Internet das Coisas. O adaptador permite que sensores e atuadores interajam com a plataforma usando o protocolo MQTT. A avaliação de desempenho do adaptador sugere que o uso do MQTT pode ser mais eficiente que o uso da API HTTP. Por exemplo, com o uso do MQTT, foi observada uma vazão até 84,27 vezes maior do que com o uso do HTTP.
Rodrigo Tinini, Matias Santos, Carlos Kamienski, Gustavo Figueiredo, and Daniel Batista. Efficient Allocation of vBBUs and VPONs in a Virtualized Cloud-Fog RAN Architecture over TWDM-PON (in Portuguese). XXXIX Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), 2021.
Para diminuir a latência e o consumo de energia em redes 5G, operadores têm adotado a arquitetura Cloud Radio Access Networks (CRAN) com um fronthaul TWDM-PON. Apesar de reduzir o consumo de energia, a carga de dados no fronthaul da CRAN é alta, podendo aumentar as latências e diminuir a cobertura da rede. Assim, neste artigo, consideramos a arquitetura Cloud-Fog RAN (CF-RAN), que usa fog nodes para diminuir a carga do fronthaul. Para esta arquitetura, nós propomos uma heurística baseada em grafos que dinamicamente ativa fog nodes e dimensiona a banda do fronthaul. A proposta provê soluções ótimas de um ILP, é capaz de mitigar a probabilidade de bloqueio e reduz o consumo de energia em até 58% em comparação com heurísticas base.
Fabíola Oliveira, Luiz Bittencourt, and Carlos Kamienski. Collision Prevention in Drone Delivery Services for Smart Cities (in Portuguese). V Workshop of Urban Computing (CoUrb), 2021.
The recent advances in unmanned aerial vehicles (UAV), commonly called drones, and the new communication and artificial intelligence technologies make it possible to develop aerial delivery services for the near future. However, such advances in smart city services require strict security and safety standards. Particularly, collision avoidance strategies are needed to guarantee that drones do not collide with each other, with other aerial objects or beings, and numerous obstacles in typical urban settings. This paper proposes a delivery service scenario for smart cities and assesses the number of drones that collide under three different methods for the situation when a drone approaches another one: keeping the original route, taking a random detour and, taking a detour to the right, like in aviation. The results show that the detours can maintain or eliminate the number of collisions for fleets with few drones but increase the number of collisions when more drones are present. We investigate the travel time of the drones to show how each method behaves and the position of the collisions to identify the collision situation. The main conclusion is that naive and straightforward detour approaches do not guarantee collision avoidance, making a case for more sophisticated ones.
José Daniel Ribeiro Filho, Ariel Soares Teles, Francisco Silva, and Luciano Reis Coutinho. Towards Clustering Human Behavioral Patterns based on Digital Phenotyping. IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS), 2021.
Mental health professionals use clinical evidence and information self-reported by patients for diagnosing mental disorders. However, self-reports and questionnaires are approaches affected by cognitive biases due to imprecision in the report. Machine learning has been used along with sensor data embedded in mobile devices (e.g., smartphones) to identify patterns correlated to mental disorders. This study proposes a solution that uses a clustering algorithm to analyze group behaviors over time. We believe that our solution can help mental health professionals to continuously monitor patients, identify similar behaviors, and changes in behaviors. We present an analysis of different clustering algorithms and show group dynamics. We conclude that the Birch algorithm has the best performance for grouping behaviors in our experiments.
Artur Oliveira and Roberto Hirata. INACITY – INvestigate and Analyze a CITY. SoftwareX, vol 15, 2021.
INACITY is a platform that integrates Geo-located Imagery Databases (GIDs), Geographical Information Systems (GIS), digital maps, and Computer Vision (CV) to collect and analyze urban street-level images. The platform’s software architecture is a client–server model, where the client-side is a simple Web page that allows the user to select regions of a map and select filters to analyze and visualize urban features. The server side is a Django-powered Web service with PostgreSQL and Neo4j databases. Users can select a region of a map, an image filter, and geographical features to analyze relevant urban characteristics as trees, for instance, using the platform. An open-source implementation of the platform is available. The architecture is extensible, and it is easy to add new modules or replace the existing ones with new digital maps, GIS databases, other CV filters, or other GIDs.
Arthur S. Jacobs, Ricardo Pfitscher, Rafael Ribeiro, Ronaldo A. Ferreira, Lisandro Granville, Walter Willinger, and Sanjay Rao. Hey, Lumi! Using Natural Language for Intent-Based Network Management. Proceedings of the USENIX Annual Technical Conference 2021 (USENIX ATC'21). July 14-16, 2021.
In this work, we ask: what would it take for, say, a campus net-work operator to tell the network, using natural language, to“Inspect traffic for the dorm”? How could the network instantly and correctly translate the request into low-level configuration commands and deploy them in the network to accomplish the job it was “asked” to do? We answer these questions by presenting the design and implementation of LUMI, a new system that (i) allows operators to express intents in natural language, (ii) uses machine learning and operator feedback to ensure that the translated intents conform with the operator’s goals, and (iii) compiles and deploys them correctly in the network. As part of LUMI, we rely on an abstraction layer between natural language intents and network configuration commands referred to as Nile (Network Intent LanguagE). We evaluate LUMI using synthetic and real campus network policies and show that LUMI extracts entities with high precision and compiles intents in a few milliseconds. We also report on a user study where 88.5% of participants state they would rather use LUMI exclusively or in conjunction with configuration commands.
Fernanda Dallaqua, Álvaro Fazenda, and Fabio Faria. ForestEyes Project: Conception, enhancements, and challenges. Future Generation Computer Systems, v. 124, 2021.
Rainforests play an important role in the global ecosystem. However, significant regions of them are facing deforestation and degradation due to several reasons. Diverse government and private initiatives were created to monitor and alert for deforestation increases from remote sensing images, using different ways to deal with the notable amount of generated data. Citizen Science projects can also be used to reach the same goal. Citizen Science consists of scientific research involving nonprofessional volunteers for analyzing, collecting data, and using their computational resources to outcome advancements in science and to increase the public’s understanding of problems in specific knowledge areas such as astronomy, chemistry, mathematics, and physics. In this sense, this work presents a Citizen Science project called ForestEyes, which uses volunteer’s answers through the analysis and classification of remote sensing images to monitor deforestation regions in rainforests. To evaluate the quality of those answers, different campaigns/workflows were launched using remote sensing images from Brazilian Legal Amazon and their results were compared to an official groundtruth from the Amazon Deforestation Monitoring Project PRODES. In this work, the first two workflows that enclose the State of Rondônia in the years 2013 and 2016 received more than 35,000 answers from 383 volunteers in the 2,050 created tasks in only two and a half weeks after their launch. For the other four workflows, even enclosing the same area (Rondônia) and different setups (e.g., image segmentation method, image spatial resolution, and detection target), they received 51,035 volunteers’ answers gathered from 281 volunteers in 3,358 tasks. In the performed experiments, it was possible to observe that the volunteers achieved satisfactory overall accuracy, higher than 75%, in the classification of forestation and non-forestation areas using the ForestEyes project. Furthermore, considering an efficient segmentation and a better image spatial resolution, they achieved almost 66% accuracy in the classification of recent deforestation, which is a great challenge to overcome. Therefore, these results show that Citizen Science might be a powerful tool in monitoring deforestation regions in rainforests as well as in obtaining high-quality labeled data.
Leissi M.C. Leon, Krzysztof C. Ciesielski, Paulo A.V. Miranda. Efficient Hierarchical Multi-Object Segmentation in Layered Graphs. Mathematical Morphology - Theory and Applications, 5:21-43, 2021.
We propose a novel efficient seed-based method for the multi-object segmentation of images based on graphs, named Hierarchical Layered Oriented Image Foresting Transform (HLOIFT). It uses a tree of the relations between the image objects, with each node in the tree representing an object. Each tree node may contain different individual high-level priors of its corresponding object and defines a weighted digraph, named as layer. The layer graphs are then integrated into a hierarchical graph, considering the hierarchical relations of inclusion and exclusion. A single energy optimization is performed in the hierarchical layered weighted digraph leading to globally optimal results satisfying all the high-level priors. The experimental evaluations of HLOIFT, on medical, natural, and synthetic images, indicate promising results comparable to the related baseline methods that include structural information, but with lower computational complexity. Compared to the hierarchical segmentation by the min-cut/max-flow algorithm, our approach is less restrictive, leading to globally optimal results in more general scenarios, and has a better running time.
Fillipe Santos, Roger Immich, and Edmundo Madeira. Multimedia Microservice Placement in Hierarchical Multi-tier Cloud-to-Fog Networks. FlexNGIA - IFIP/IEEE International Workshop on Fully-Flexible Internet Architectures and Protocols for the Next-Generation Tactile Internet, 2021.
The demand for multimedia services in mobile networks has increased in the last years. The high quantity of users mobile, both consuming and producing multimedia content to and from the Cloud can outpace the available bandwidth capacity. Notwithstanding the many benefits of Cloud Computing (CC), it has been noticed that it does not provide adequate latency in areas with high demands for multimedia content. Furthermore, using Fog Computing (FG) it is possible to improve on the above-mentioned issues, being especially useful in latency-sensitive applications such nodes are physically much closer to devices if compared to centralized data centers. The main goal of this work is twofold, first, it proposed a method to design/create a hierarchical multi-tier Cloud-to-Fog network. Second, it introduced a novel multimedia microservices placement algorithm for multi-tier Fog nodes. The performance assessment was composed of two months of real-world mobile network traffic data from Milan, Italy. The obtained results showed that our algorithm selects the nodes closer to the user to meet their demands. This decision improves the services delivered to end-users, for example, a local Fog node can instead be responsible for the video stream and is far quicker than offloading the processing to a centralized cloud platform.
Guilherme A. Thomaz, Gustavo F. Camilo, Lucas A. C. de Souza, and Otto O. C. M. B. Duarte. A Comparative Analysis of the Architecture and Performance of Permissioned Block Chain Platforms for Smart Contracts (in Portuguese). IV Workshop em Blockchain: Teoria, Tecnologias e Aplicações (WBlockchain SBRC), 2021.
A corrente de blocos e os contratos inteligentes garantem segurança e automatização em cenários sem confiança, gerando soluções inovadoras em diversos setores produtivos. O projeto de codigo aberto Hyperledger impulsiona o emprego dessas tecnologias no meio corporativo provendo diferentes plataformas para o desenvolvimento de aplicações distribuídas. Este artigo analisa e compara duas plataformas amplamente utilizadas para o desenvolvimento de aplicações baseadas em correntes de blocos permissionadas: o Hyperledger Sawtooth e o Hyperledger Fabric. Dois prototipos desenvolvidos implementam contratos inteligentes para uma mesma aplicação de modo a avaliar o desempenho de cada ferramenta. Os resultados obtidos revelam que: i) o processamento paralelo de transações do Sawtooth apresenta um desempenho até 30% superior apenas se o numero de transações conflitantes permanecer baixo; ii) o desempenho do modelo XO do Fabric e 4 vezes maior que o OX do Sawtooth, mas apresenta uma piora consideravel com transações conflitantes; iii) o consenso do Sawtooth apresenta maior seguranc¸a e menor desempenho que o do Fabric; iv) as aplicações no Sawtooth consomem menos armazenamento em disco.
Gabriel Antonio Rebello, Gustavo Camilo, Lucas Chagas Guimarães, Lucas Airam de Souza, Guilherme Thomaz, and Otto Carlos Duarte. A security and performance analysis of proof-based consensus protocols. Annals of Telecommunications, 2021.
Blockchain is a disruptive technology that will revolutionize the Internet and our way of living, working, and trading. However, the consensus protocols of most blockchain-based public systems show vulnerabilities and performance limitations that hinder the mass adoption of blockchain. This paper presents and compares the main proof-based consensus protocols, focusing on the security and performance of each consensus protocol. Proof-based protocols use the probabilistic consensus model and are more suitable for public environments with many participants, such as the Internet of Things (IoT). We highlight the centralization tendency and the main vulnerabilities of Proof of Work (PoW), Proof of Stake (PoS), and their countermeasures. We also analyze and compare alternative proof-based protocols, such as Proof of Elapsed Time (PoET), Proof of Burn (PoB), Proof of Authority (PoA), and Delegated Proof of Stake (DPoS). Finally, we analyze the security of the IOTA consensus protocol, a DAG-based platform suited for the IoT environment.
Guilherme Thomaz, Gustavo Camilo, Lucas Airam de Souza, and Otto Carlos Duarte. Architecture and Performance Comparison of Permissioned Blockchains Platforms for Smart Contracts. IEEE Global Communications Conference (GLOBECOM), 2021.
Blockchain and Smart Contracts ensure security and automation in trustless scenarios, leading to innovative solutions in various industry branches. The Hyperledger open-source project adopts these technologies in the corporate business, providing platforms for developing distributed applications. This paper analyses and compares two widely used platforms to develop applications based on permissioned blockchains: Hyperledger Sawtooth and Hyperledger Fabric. We implement two prototypes based on the same smart contract to evaluate the performance of each tool. The results show that: i) Sawtooth parallel transaction execution performs up to 30% better than serial execution only if the number of conflicting transactions remains low, and ii) Fabric has a much faster consensus protocol, but presents a low performance if the transactions are conflicting.
Igor Alvarenga, Gustavo Camilo, Lucas Airam de Souza, and Otto Carlos Duarte. DAGSec: A hybrid distributed ledger architecture for the secure management of the Internet of Things. IEEE International Conference on Blockchain, 2021.
The rise of 5G mobile broadband networks creates new possibilities for the Internet of Things. Billions of devices will provide comprehensive services, including e-health applications, smart grids, and industry 4.0. Distributed ledger technologies solve most security and privacy threats of current IoT systems connected to a cloud or multi-access edge communication (MEC). Unfortunately, the volume of transactions imposed by 5G networks prevents blockchain-based solutions due to scalability issues. Nonetheless, emerging solutions based on directed acyclic graphs (DAG), still require some form of centralization or global view. This article proposes DAGSec, a hybrid distributed ledger architecture that provides a secure Internet of Things environment with high throughput and low latency. Our proposal uses directed acyclic graphs and local transaction validation instead of global transaction validation to attain a high transaction rate. Furthermore, we propose a blockchain-based witness system to approximate chronological order of independent transactions.
Lucas Chagas Guimarães, Gabriel Antonio Rebello, Gustavo Camilo, Lucas Airam de Souza, and Otto Carlos Duarte. A threat monitoring system for intelligent data analytics of network traffic. Annals of Telecommunications, 2021.
Security attacks have been increasingly common and cause great harm to people and organizations. Late detection of such attacks increases the possibility of irreparable damage, with high financial losses being a common occurrence. This article proposes TeMIA-NT (ThrEat Monitoring and Intelligent data Analytics of Network Traffic), a real-time flow analysis system that uses parallel flow processing. The main contributions of the TeMIA-NT are (i) the proposal of an architecture for real-time detection of network intrusions that supports high traffic rates, (ii) the use of the structured streaming library, and (iii) two modes of operation: offline and online. The offline operation mode allows evaluating the performance of multiple machine learning algorithms over a given dataset, including metrics such as accuracy and F1-score. The proposed system uses dataframes and the structured streaming engine in online mode, which allows detection of threats in real-time and a quick reaction to attacks. To prevent or minimize the damage caused by security attacks, TeMIA-NT achieves flow-processing rates that reach 50 GB/s.
Guilherme Oliveira, Rodrigo Ney, Juan Herrera, Daniel Batista, Roberto Hirata, Jaime Galán-Jiménez, Javier Berrocal, Juan Murillo, Aldri Santos, and Michele Nogueira. Predicting Response Time in SDN-Fog Environments for IIoT Applications. IEEE Latin-American Conference on Communications (LATINCOM), 2021.
In IoT application scenarios, the response time is one of the attributes that most require attention and, for this reason, the paradigm of decentralized (or fog) computation has gained ground. Moreover, to help reduce the response time of decentralized IoT networks, routing optimization approaches can be employed using software-defined networking (SDN). When both contexts are combined, a new one called SDN-Fog Environments appears. This work presents a solution to predict the response time of Industrial Internet of Things (IIoT) applications using supervised and unsupervised learning for SDN-Fog Environments. Results show that the prediction of the response time of IIoT scenarios was close to the times obtained by solving the problem in the literature. Furthermore, according to the best-performing models, the prediction framework had less than 50 milliseconds of variation, executed in less than one second.
Thales Paiva, Yaissa Siqueira, Daniel Batista, Roberto Hirata, and Routo Terada. BGP Anomalies Classification using Features based on AS Relationship Graphs. IEEE Latin-American Conference on Communications (LATINCOM), 2021.
Ensuring the correct behavior of the Border Gateway Protocol (BGP) is essential for keeping a good quality of service on the internet. When an anomalous behavior is detected, operators of border gateways need to classify it correctly into a direct (intended or unintended) anomaly, an indirect anomaly, or a link failure. This classification helps to understand its cause and act upon it. Recently, some techniques for the classification of BGP anomalies using machine learning models were proposed. However, we notice some limitations of these classification models that make it unclear if they can be used in the real world to classify new anomalies. This paper presents a new model with good performance when classifying BGP events not seen in its training. Our model is based on Long Short-Term Memory (LSTM) networks and uses new features based on inferred relationships between Autonomous Systems (ASes) to classify sets of BGP update messages. The model classifies samples from new events achieving 91% of accuracy and F1 scores of 1.00, 0.93, and 0.80 for direct anomalies, indirect anomalies, and link failure, respectively.
Fatemeh Mosaiyebzadeh, Luis Rodriguez, Daniel Batista, and Roberto Hirata. A Network Intrusion Detection System using Deep Learning against MQTT Attacks in IoT. IEEE Latin-American Conference on Communications (LATINCOM), 2021.
Cyber-attacks and threats are growing fast in the Internet of Things (IoT) infrastructure as applications in smart cities gain momentum. Usually, IoT devices communicate via machine-to-machine protocols such as Message Queuing Telemetry Transport (MQTT). Due to the heterogeneous structure in IoT and the absence of security by design methodologies, security mechanisms in environments with MQTT traffic are needed, and they can be deployed as Intrusion Detection Systems (IDS). This paper proposes a Deep Learning (DL) based Network IDS trained using a public dataset containing MQTT attacks. We assess the proposal using standard performance metrics such as accuracy, precision, recall, F1-score, and weighted average. When evaluating the performance of our DL-based Network IDS, it obtained, in average, 97.09% of accuracy and an F1-score equal to 98.33% in the detection of MQTT attacks. Another important contribution of our work is the sharing of the experiments on GitHub, which guarantees the reproducibility of the research.
Antonio Paganelli, Adriano Branco, Markus Endler, Pedro Elkind Velmovitsky, Pedro Miranda, Plinio Pelegrini Morita, Paulo Alencar, and Donald Cowan. IoT-Based COVID-19 Health Monitoring System: Context, Early Warning and Self-Adaptation. IEEE International Conference on Big Data, 2021.
The Internet of Things (IoT) has enabled novel solutions for monitoring patients’ health through wearable sensors in conditions of both non-communicable and infectious diseases. In this paper, we report work in progress involving the development of an IoT-based COVID-19 health monitoring system that can effectively monitor the essential physiological functions of a patient through wireless sensors, thus supporting the early detection of severe cases and the continuous assessment of the patient status. The work provides several main contributions, as it includes: (i) a brief description of the current IoT-based system for remote monitoring of COVID-19 patients; (ii) a description of embedded characteristics of our device, including its contextual functions, early warning score mechanisms and self-adaptive features; and (iii) a description of our preliminary experimental results. Our proposed solution reduced drastically the amount of redundancy in data and still maintains monitoring accuracy. Given the COVID-19 scenarios, in which human resources are extended to the limit and the number of patients in severe conditions is often high, a system that can support IoT-based continuous monitoring are essential to identify changes in clinical status promptly and accurately and can potentially transform the way patients are monitored.
Renan Fialho, Rayele Moreira, Thalyta C. P. Santos, Samila S. Vasconcelos, Silmar Teixeira, Francisco Silva, Joel Rodrigues, and Ariel Soares Teles. Can computer vision be used for anthropometry? A feasibility study of a smart mobile application. IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS), 2021.
Anthropometry is a method for measuring physical characteristics of the human body, particularly dealing with measures of size and shape of the body. These measurements can be performed using a tape measure, but new devices and software solutions already been employed in digital anthropometry. However, such tools do not enable the anthropometric evaluation to be performed automatically. In this paper, we present the NLMeasurer application for anthropometry, a mobile tool based on computer vision for identifying anatomical reference points (ARPs) and assessing the size of body segments. To evaluate the performance of the NLMeasurer, four participants were photographed and their images processed. The anthropometric measures calculated by the application, using different settings, were compared with those obtained using a tape measure. Results indicate no statistically significant difference (p > 0.05) between the methods, except in one configuration. This initial experiment was promising to reveal the feasibility of using NLMeasurer for anthropometry.
Osvaldo Fonseca, Ítalo Cunha, Elverton Fazzion, Wagner Meira Jr, Brivaldo Junior, Ronaldo A. Ferreira, and Ethan Katz-Basset. Identifying Networks Vulnerable to IP Spoofing. IEEE Transactions on Network and Service Management, volume 18, issue 3, 2021.
The lack of authentication in the Internet’s data plane allows hosts to falsify (spoof) the source IP address in packet headers. IP source spoofing is the basis for amplification denial-of-service (DoS) attacks. Current approaches to locate sources of spoofed traffic lack coverage or are not deployable today. We propose a mechanism that a network with multiple peering links can use to coarsely locate the sources of spoofed traffic in the Internet. The idea behind our approach is that a network can monitor and map spoofed traffic arriving on a peering link to the set of sources routed toward that link. We propose mechanisms the network can use to systematically vary BGP announcement configurations to induce changes to Internet routes and to the set of sources routed to each peering link. A network using our technique can correlate observations over multiple configurations to more precisely delineate regions sending spoofed traffic. Evaluation of our techniques on the Internet shows that they can partition the Internet into small regions, allowing targeted intervention.
Pamela Zave, Fabrício B. Carvalho, Ronaldo A. Ferreira, Jennifer Rexford, Masaharu Morimoto, and X. Kelvin Zou. A Verified Session Protocol for Dynamic Service Chaining. IEEE/ACM Transactions on Networking, Volume 28, Number 1, pages 423-437, February, 2021.
Middleboxes are crucial for improving network security and performance, but only if the right traffic goes through the right middleboxes at the right time. Existing traffic-steering techniques rely on a central controller to install fine-grained forwarding rules in network elements-at the expense of a large number of rules, a central point of failure, challenges in ensuring all packets of a session traverse the same middleboxes, and difficulties with middleboxes that modify the “five tuple.” We argue that a session-level protocol is a fundamentally better approach to traffic steering, while naturally supporting host mobility and multihoming in an integrated fashion. In addition, a session-level protocol can enable new capabilities like dynamic service chaining, where the sequence of middleboxes can change during the life of a session, e.g., to remove a load-balancer that is no longer needed, replace a middlebox undergoing maintenance, or add a packet scrubber when traffic looks suspicious. Our Dysco protocol steers the packets of a TCP session through a service chain, and can dynamically reconfigure the chain for an ongoing session. Dysco requires no changes to end-host and middlebox applications, host TCP stacks, or IP routing. Dysco’s distributed reconfiguration protocol handles the removal of proxies that terminate TCP connections, middleboxes that change the size of a byte stream, and concurrent requests to reconfigure different parts of a chain. Through formal verification using Spin and experiments with our prototype, we show that Dysco is provably correct, highly scalable, and able to reconfigure service chains across a range of middleboxes.
Alessandro Santos, Igor Teixeira, Leandro Avanço, Rodrigo Neves, Icaro Gonçales, and Angelina Inacio. Intelligent Monitoring System of COVID-19 in São Paulo (in Portuguese). Workshop on Tools and Applications - Brazilian Symposium on Multimedia and the Web, 2021.
São Paulo was one of the first states affected by COVID-19 in Brazil. The Intelligent Monitoring System (SIMI) was an important milestone to face the pandemic, whose mission was to consolidate and integrate data on vehicular and people mobility, epidemiological situation, and economic status to support the state government in its strategic decisions. Overcoming the challenges of integration, anonymity, privacy, and multidisciplinarity were essential to provide results for analyzing scenarios and better information for decision-making. SIMI indicators impacted the entire São Paulo society, which defined criteria for flexibilization or restriction of economic sectors or supporting strategic changes to face the pandemic.
Ivan Rodrigues de Moura, Ariel Soares Teles, Markus Endler, Luciano Reis Coutinho, and Francisco José da Silva e Silva. Recognizing Context-Aware Human Sociability Patterns Using Pervasive Monitoring for Supporting Mental Health Professionals. Sensors, vol. 21, 2021.
Traditionally, mental health specialists monitor their patients’ social behavior by applying subjective self-report questionnaires in face-to-face meetings. Usually, the application of the self-report questionnaire is limited by cognitive biases (e.g., memory bias and social desirability). As an alternative, we present a solution to detect context-aware sociability patterns and behavioral changes based on social situations inferred from ubiquitous device data. This solution does not focus on the diagnosis of mental states, but works on identifying situations of interest to specialized professionals. The proposed solution consists of an algorithm based on frequent pattern mining and complex event processing to detect periods of the day in which the individual usually socializes. Social routine recognition is performed under different context conditions to differentiate abnormal social behaviors from the variation of usual social habits. The proposed solution also can detect abnormal behavior and routine changes. This solution uses fuzzy logic to model the knowledge of the mental health specialist necessary to identify the occurrence of behavioral change. Evaluation results show that the prediction performance of the identified context-aware sociability patterns has strong positive relation (Pearson’s correlation coefficient >70%) with individuals’ social routine. Finally, the evaluation conducted recognized that the proposed solution leading to the identification of abnormal social behaviors and social routine changes consistently.
Higor Amario de Souza, Edison de Oliveira Vianna, Edlene Carneiro de Souza, Fabio Kon. Implantação e uso da ferramenta de análise de mobilidade de bicicletas BikeScience na CET: Identificando caminhos cicláveis em São Paulo. Revista UniCET, vol. 1, no. 3, 2021.
Este artigo apresenta o processo de implantação e uso, na Companhia de Engenharia de Tráfego de São Paulo (CET), da ferramenta de análise de dados BikeScience desenvolvida no contexto do projeto InterSCity do Instituto de Matemática e Estatística da Universidade de São Paulo (IME-USP). Esse trabalho é fruto de uma parceria entre a CET e pesquisadores do InterSCity. Aqui descrevemos como tem sido o processo de uso da ferramenta para fazer análises com o objetivo de colaborar para o entendimento e o processo de tomada de decisão sobre as questões relacionadas com a mobilidade urbana ativa em São Paulo. Descrevemos como a ferramenta pode ser usada para trazer informações sobre o perfil de ciclistas com base em dados de mobilidade. Descrevemos também os resultados de uma análise comparativa entre as viagens da Pesquisa Origem Destino 2017 e as contagens de fluxos de bicicletas realizadas pela CET. Os resultados mostram quais as vias e locais da cidade de São Paulo possuem maior concentração de viagens de bicicletas. Por fim, apresentamos trabalhos futuros que serão realizados com o apoio da ferramenta BikeScience.
All the software described in this paper is available as open source at https://gitlab.com/interscity/bike-science
Francisco Wallison Rocha, Emilio Francesquini, and Daniel Cordeiro. An Approach Inspired by Simulation Points to Accelerate Smart Cities Simulations. XII Escola Regional de Alto Desempenho de São Paulo, 2021.
Approaches using simulations are of great value for smart cities research. However, city-scale simulators can be both processing and memory-intensive, and hard to scale. To speed up these simulations and to allow executing larger scenarios, this work presents an approach based on an technique named Simpoint to estimate the result of new simulations using previous simulations. This technique aims to identify and cluster recurring patterns during a simulation. Then, unique representatives of each cluster are selected and their simulation is used to estimate the simulation results of the remaining cluster elements. The experimental results for our estimates are promising. On a dataset with 16,993 time series, our technique was able to estimate the original series with an average error of 1.60979e-11 and standard deviation of 9.18228e-11.
João C. Fukuda, Emilio Francesquini, and Daniel Cordeiro. Profiling an Erlang Program Inside A Linux Environment: A Discussion of Possible Approaches (in Portuguese). XII Escola Regional de Alto Desempenho de São Paulo, 2021.
Erlang is a concurrent language built to run on the BEAM virtual machine. This paper discusses the different approaches one can take to profile programs built on Erlang from both inside and outside BEAM and their inherent tradeoffs. It divides profiling and tracing tools into system and VM-level, compares both categories’ advantages and disadvantages in terms of performance and how trying to keep performance might minimize other aspects of the profiling, and describes how to take advantage of them both alone and together by combining their outputs to produce the best possible result.
Edson Dias, Paulo Meirelles, Fernando Castor, Igor Steinmacher, Igor Wiese, and Gustavo Pinto. What Makes a Great Maintainer of Open Source Projects?. 43rd International Conference on Software Engineering, 2021.
Although Open Source Software (OSS) maintainers devote a significant proportion of their work to coding tasks, great maintainers must excel in many other activities beyond coding. Maintainers should care about fostering a community, helping new members to find their place, while also saying “no” to patches that although are well-coded and well-tested, do not contribute to the goal of the project. To perform all these activities masterfully, maintainers should exercise attributes that software engineers (working on closed source projects) do not always need to master. This paper aims to uncover, relate, and prioritize the unique attributes that great OSS maintainers might have. To achieve this goal, we conducted 33 semi-structured interviews with well-experienced maintainers that are the gatekeepers of notable projects such as the Linux Kernel, the Debian operating system, and the GitLab coding platform. After we analyzed the interviews and curated a list of attributes, we created a conceptual framework to explain how these attributes are connected. We then conducted a rating survey with 90 OSS contributors. We noted that “technical excellence” and “communication” are the most recurring attributes. When grouped, these attributes fit into four broad categories: management, social, technical, and personality. While we noted that “sustain a long term vision of the project” and being “extremely careful” seem to form the basis of our framework, we noted through our survey that the communication attribute was perceived as the most essential one.
Received the Distinguished Paper Award
Antonio Iyda Paganelli, Pedro Elkind Velmovitsky, Pedro Miranda, Adriano Branco, Paulo Alencar, Donald Cowan, Markus Endler, and Plinio Pelegrini Morita. A conceptual IoT-based early-warning architecture for remote monitoring of COVID-19 patients in wards and at home. Internet of Things Journal, 2021.
Due to the COVID-19 pandemic, health services around the globe are struggling. An effective system for monitoring patients can improve healthcare delivery by avoiding in-person contacts, enabling early-detection of severe cases, and remotely assessing patients’ status. Internet of Things (IoT) technologies have been used for monitoring patients’ health with wireless wearable sensors in different scenarios and medical conditions, such as noncommunicable and infectious diseases. Combining IoT-related technologies with early-warning scores (EWS) commonly utilized in infirmaries has the potential to enhance health services delivery significantly. Specifically, the NEWS-2 has been showing remarkable results in detecting the health deterioration of COVID-19 patients. Although the literature presents several approaches for remote monitoring, none of these studies proposes a customized, complete, and integrated architecture that uses an effective early-detection mechanism for COVID-19 and that is flexible enough to be used in hospital wards and at home. Therefore, this article’s objective is to present a comprehensive IoT-based conceptual architecture that addresses the key requirements of scalability, interoperability, network dynamics, context discovery, reliability, and privacy in the context of remote health monitoring of COVID-19 patients in hospitals and at home. Since remote monitoring of patients at home (essential during a pandemic) can engender trust issues regarding secure and ethical data collection, a consent management module was incorporated into our architecture to provide transparency and ensure data privacy. Further, the article details mechanisms for supporting a configurable and adaptable scoring system embedded in wearable devices to increase usefulness and flexibility for health care professions working with EWS.
Alessandro S. Santos, Igor C. Teixeira, Rodrigo Neves, Icaro Gonçales, Angelina Inacio, Eduardo T. Ueda, Eduardo F. Z. Santana, Higor A. de Souza, Fabio Kon. Challenges and Strategies for Information Systems in the Decision-Making Process to Face the COVID-19 Pandemic: The São Paulo Case. Trends and Applications in Information Systems and Technologies. WorldCIST 2021. Advances in Intelligent Systems and Computing, vol 1367., 2021.
The State of São Paulo was the epicenter of COVID-19 in Brazil, with a high impact on society, causing many deaths and significant losses to the economy. A milestone in confronting the pandemic was creating an Intelligent Monitoring System, whose mission was to consolidate and integrate data to support the state government in its strategic decisions. Overcoming the challenges of integration, anonymity, and privacy was essential to validate and make governmental actions legal and ethical. We present the technical aspects, the information integration and good practices in disseminating strategic data on mobility, health, and economy to support strategic decision making.
Franklin Magalhães Ribeiro Junior and Carlos Kamienski. A Survey on Trustworthiness for the Internet of Things. 9th IEEE Access, 2021.
IoT systems use sensors to collect data from smart environments and manage resources through data analysis. An IoT system deals with many connected devices with different network and hardware constraints in a real-world scenario. An IoT system needs to handle low-latency data analysis, security threats, internal vulnerabilities, and network disconnections, which cause data loss and incorrect decisions. Trustworthiness (also known as dependability) provides various features for an IoT end-to-end data flow, such as resilience, security, availability, reliability, scalability, maintainability, heterogeneity, hardware resources management, fault management policies, and data quality. This paper presents a survey on trustworthiness and dependability in IoT systems and proposes the Trustworthiness for IoT Framework (TW-IoT) to provide trustworthiness at the data level for mist and fog-based IoT systems. The TW-IoT framework provides data trustworthiness to ensure a continuous and uninterrupted operation of IoT data flow. We also discuss challenges and trade-offs related to data trustworthiness in IoT.
Eduardo Felipe Zambom Santana, Gustavo Covas, Fábio Duarte, Paolo Santi, Carlo Ratti, and Fabio Kon. Transitioning to a driverless city: Evaluating a hybrid system for autonomous and non-autonomous vehicles. Simulation Modelling Practice and Theory 107, 2021.
Autonomous vehicles will transform urban mobility. However, before being fully implemented, autonomous vehicles will navigate cities in mixed-traffic roads, negotiating traffic with human-driven vehicles. In this work, we simulate a system of autonomous vehicles co-existing with human-driven vehicles, analyzing the consequences of system design choices. The system consists of a network of arterial roads with exclusive lanes for autonomous vehicles where they can travel in platoons. This paper presents the evaluation of this system in realistic scenarios evaluating the impacts of the system on travel time using mesoscopic traffic simulation. We used real data from the metropolis of São Paulo to create the simulation scenarios. The results show that the proposed system would bring reductions to the average travel time of the city commuters and other benefits such as the reduction of the space required to handle all the traffic.
Matheus Leal, Flávia Pisani, and Markus Endler. A blockchain-based service for inviolable presence registration of mobile entities. Journal of the Brazilian Computer Society, 2021.
Several applications can benefit from recording information about the places a mobile entity visits and the length of time it spends there (e.g., shoppers, employees, buses, portable equipment, autonomous robots). This paper presents our approach to recording spatio-temporal presence information in a secure and inviolable way using a Distributed Ledger Technology. We implemented this solution as a middleware service that uses Complex Event Processing on smartphones to record beacon-smartphone proximity data in a blockchain efficiently. We have built upon the previous version of our service to include access control to the stored information. We analyzed the impact of this addition on the service’s performance and observed that it introduced very little overhead while significantly increasing user privacy. Furthermore, we compared the effect of using different blockchain technologies on overall service performance and characterized scenarios where using either IoTeX or Ethereum can be suitable for this type of application.
Veruska Ayora, Flávio Horita, and Carlos Kamienski. Profiling Online Social Network Platforms: Twitter vs. Instagram. Proceedings of the 54th Hawaii International Conference on System Sciences (HICSS), 2021.
Online Social Networks (OSN) have been increasingly used as sources of information for different applications, ranging from business, politics, and public services. However, there is a lack of information on OSN platforms’ behavior that may impact big data processing and real-time services. In this paper, two of the most widely used social networks, Instagram and Twitter, are investigated to broaden the understanding of how each platform’s message characteristics influence data completeness and latency. We performed a series of experiments to emulate data posting and collection automatically. Our results increase the level of transparency of the platforms’ internal behavior, showing that both can deliver data with reasonably low latencies and high completeness, but Twitter can be up to eight times faster when it comes to multimedia messages.
Diogo Gonçalves, Carlo Puliafito, Enzo Mingozzi, Omer Rana, Luiz Bittencourt, and Edmundo Madeira. Dynamic Network Slicing in Fog Computing for Mobile Users in MobFogSim. IEEE/ACM 13th International Conference on Utility and Cloud Computing (UCC), 2020.
Fog computing provides resources and services in proximity to users. To achieve latency and throughput requirements of mobile users, it may be useful to migrate fog services in accordance with user movement – a scenario referred to as follow me cloud. The frequency of migration can be adapted based on the mobility pattern of a user. In such a scenario, the fog computing infrastructure should simultaneously accommodate users with different characteristics, both in terms of mobility (e.g., route and speed) and Quality of Service requirements (e.g., latency, throughput, and reliability). Migration performance may be improved by leveraging “network slicing”, a capability available in Software Defined Networks with Network Function Virtualisation. In this work, we describe how we extended our simulator, called MobFogSim, to support dynamic network slicing and describe how MobFogSim can be used for capacity planning and service management for such mobile fog services. Moreover, we report an experimental evaluation of how dynamic network slicing impacts on container migration to support mobile users in a fog environment. Results show that dynamic network slicing can improve resource utilisation and migration performance in the fog.
Gustavo F. Camilo, Gabriel Antonio F. Rebello, Lucas Airam C. de Souza, and Otto Carlos M. B. Duarte. AutAvailChain: Automatic and Secure Data Availability through Blockchain. GLOBECOM 2020 - IEEE Global Communications Conference, 2020.
The trust centralization in current data sharing systems restricts the owner’s control over their data. Furthermore, the owner’s intervention to authorize his/hers data access for each request makes frequent access to popular data tiresome. In this paper, we propose AutAvailChain, an architecture based on software defined networking (SDN) and blockchain to provide secure, automatic, and distributed sharing of IoT data. We develop a prototype using the Hyperledger Fabric platform to implement the blockchain and a smart contract. The results show a quick, secure, and excellent performance of dozens of transactions per second.
Bruno Gabriel Araújo Lebtag, Paulo Gabriel Teixeira, Rodrigo Pereira dos Santos, Davi Viana, and Valdemar V. Graciano Neto. Evaluating the Understandability and Expressiveness of Simulation Executable Models with Professionals: Obtaining perceptions from researchers and practitioners for improving quality of models. 19th Brazilian Symposium on Software Quality (SBQS), 2020.
Large-scale and complex systems exhibit (i) dynamic structures and behaviors, (ii) several components/systems involved and (iii) multiple interoperability links. Such technologies have exposed limitations and fragilities on traditional software specification languages (such as UML and SySML), since those languages were designed to document single (not multiple interoperating) systems, which can further compromise the quality of the final product. In this context, Executable Models (ExM) technology, such as simulation models, models@runtime and executable UML, match these requirements by supporting engineers with visualization of the systems structures (still at design-time) and the ability to model their behaviors and interactions. However, we currently observe a decrease in the use of models and consequently ExM by software engineering professionals in the academy and industry and we claim that those professionals have not exhibited abilities to use ExM even in simpler scenarios. In this paper, we present the results of an exploratory study on the perceptions of those professionals regarding the use of ExM to solve problems in their current practice. 58 professionals were exposed to situations to solve problems using a specific type of ExM (DEVS simulation models), based on a survey research. Responses were quantitatively and qualitatively analyzed. Results reveal that executable languages still require advances to bring them even closer to the current software engineering practice and towards a larger adoption in the future.
Giovanne Santos and Daniel Batista. On-Demand Placement and Scheduling of Virtual Network Functions with Software Requirements. LATINCOM - IEEE Latin-American Conference on Communications, 2020.
Virtual Network Functions (VNFs) can be combined together to meet several network services with reduced capital and operational expenditures. Given that the VNFs are virtualized, a network operator needs to solve two problems to efficiently deploy them: VNF placement and VNF scheduling. In this paper, we propose an algorithm to solve the two problems at the same time, placing and scheduling the VNFs on demand, and taking the software requirements into consideration, in a way that traditional distributed computing schedulers can be used. The proposed algorithm was evaluated via simulation against three other schedulers. Results showed that the algorithm is able to increase, by 19.7%, the number of completed VNFs in a scenario with 16540 VNFs being instantiated.
Alexandre Meslin, Noemi Rodriguez, Markus Endler. Supporting Multiple Smart-City Applications based on MUSANet, a Common IoMT Middleware. WORKSHOP EM CLOUDS E APLICAÇÕES (WCGA), 2020, Rio de Janeiro, Brazil , 2020.
The MUSANet system is a three-tier middleware for smart cities implemented using InterSCity, ContextNet, and Mobile-Hub. In order to decentralize processing from the cloud, the system includes stationary layer processing in the fog and collection of mobile data in the edge. In this article, we explore the flexibility and decoupling offered by MUSANet. We present two different applications for smart cities and discuss how they can be implemented in MUSANet, showing that, using the basic infrastructure, we can build new applications without interfering in existing ones due to the low coupling between the entities that make up the tiers of MUSANet. A third application illustrates how the distribution of data processing among MUSANet layers can help reduce the network load, preserving energy.
Alessandro Santos, Leandro de Freitas, Igor Teixeira, Vagner Gava, Gustavo Taira, Rosa Encinas Quille, Kelly Braghetto. Desafios e oportunidades da aplicação de Sistemas Ciberfísicos no monitoramento da poluição urbana. 2020: ANAIS DO IV WORKSHOP DE COMPUTAÇÃO URBANA, SBC, Rio de Janeiro, Brasil, 2020.
A ação do homem tem provocado mudanças no meio ambiente, sendo a poluição urbana uma das consequências negativas aplicadas nesse ecossistema. Com o desenvolvimento tecnológico, novas perspectivas computacionais afloram para o monitoramento ambiental. Este artigo apresenta pontos chaves da fenomenologia ambiental que podem se beneficiar da evolução promovida pela computação aplicada nos estudos da poluição, assim como realiza um levantamento de pesquisas e tecnologias utilizadas nesse contexto.
Matteus Vargas Simão da Silva, Luiz Fernando Bittencourt, Adín Ramirez Rivera. Towards Federated Learning in Edge Computing for Real-Time Traffic Estimation in Smart Cities. 2020: ANAIS DO IV WORKSHOP DE COMPUTAÇÃO URBANA, SBC, Brasil, 2020.
The wide proliferation of sensors and devices of Internet of Things(IoT), together with Artificial Intelligence (AI), has created the so-called Smart Environments. From a network perspective, these solutions suffer from high latency and increased data transmission. This paper proposes a Federated Learning (FL) architecture for Real-Time Traffic Estimation, supported by Roadside Units (RSU’s) for model aggregation. The solution envisages that learning will be done on clients with their local data, and fully distributed on the Edge, with high learning rates, low latency, and less bandwidth usage. To achieve that,this paper discusses tools and requirements for FL implementation towards a model for real-time traffic estimation, as well as how such solution could be evaluated using VANET and network simulators. As a first practical step, we show a preliminary evaluation of a learning model using a data set of cars that demonstrate a distributed learning strategy. In the future, we will use a similar distributed strategy within our proposed architecture.
Ademar Takeo Akabane, Edmundo Roberto Mauro Madeira, Leandro Aparecido Villas. Collaborative and Infrastructure-less Vehicular Traffic Rerouting for Intelligent Transportation Systems. 2020: ANAIS ESTENDIDOS DO XXXVIII SIMPÓSIO BRASILEIRO DE REDES DE COMPUTADORES E SISTEMAS DISTRIBUÍDOS, 2020.
This extended abstract provides an at-a-glance view of the main contributions of my Ph.D. work. The work aims to investigate and develop cutting-edge an infrastructure-less vehicular traffic management system in order to minimize vehicular traffic congestion and advance the state-of-the-art in intelligent transportation systems. The proposed solutions were widely compared with other literature solutions on different performance evaluation metrics. The evaluation results show that the proposed vehicle traffic management system is efficient, scalable, and cost-effective, which may be a good alternative to mitigate urban mobility problems.
Gustavo Franco Camilo, Gabriel Antonio Fontes Rebello, Lucas Airam Castro de Souza, Otto Carlos Muniz Bandeira Duarte. AutAvailChain: Disponibilização Segura, Controlada e Automática de Dados IoT usando Corrente de Blocos. 2020: ANAIS DO III WORKSHOP EM BLOCKCHAIN: TEORIA, TECNOLOGIA E APLICAÇÕES, 2020.
A centralização da confiança utilizada nos sistemas de compartilhamento de dados atuais limita o controle do usuário proprietário sobre os próprios dados. A intervenção individual do proprietário para autorizar o acesso a seus dados a cada demanda dificulta a acessibilidade a dados muito populares. Este artigo propõe AutAvailChain, uma arquitetura baseada em corrente de blocos e redes definidas por software para prover o compartilhamento seguro, automático e distribuído de dados IoT. O protótipo desenvolvido utiliza a plataforma Hyperledger Fabric para implementar a corrente de blocos e um contrato inteligente. Os resultados mostram um desempenho satisfatório para atender, de maneira rápida e segura, dezenas de transações por segundo.
Marcelo Vieira, Sérgio Carvalho, Fábio Costa and David Bromberg. A Model-Driven Approach for Real-time Role-Based Communication. 2020, Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, SBC, 2020.
Recent years have seen the inception of many domain-specific modelling languages, enabling to overcome some of the main difficulties found in software development. The use of models has a particular impact on the implementation phase, as models tend to be closer to the problems to be solved than code. This paves the way to enable application construction by non-experts in software development, such as domain specialists. In this paper, we exploit the use of models in the domain of real-time communication, which poses significant challenges for application construction due to the multitude and intricacy of the technologies involved. We propose RBCML, a communication modelling language for the high-level specification of real-time communication sessions based on the roles that users play in the sessions. The language is processed using a combination of partial code generation and dynamic model interpretation, resulting in the construction of fully functional communication applications. The paper describes RBCML and its implementation on top of W3C’s Web Real-Time Communication protocols (WebRTC). An evaluation is presented to compare the use of RBCML with code-based development and to characterize the performance of communication session establishment using the language.
Patrick Abrahao, Roger Immich, Alfredo Goldman. Análise da Performance de Streaming de Vídeos Adaptativos em Redes Veiculares V2I. 2020, WORKSHOP DE TRABALHOS DE INICIAÇÃO CIENTÍFICA E DE GRADUAÇÃO, SBC, 2020.
O emprego de carros com equipamentos de vídeo, assim como veículos conectados e autônomos, tem experienciado um aumentando considerável. Os números de serviços e aplicações a disposição em Vehicular Ad-hoc Networks (VANETs) seguem a mesma tendência. Esse tipo de rede é contemplado com um componente central de sistemas de transporte inteligentes, que provê um suporte para uma grande variedade de aplicações, incluindo serviço de vídeo. Esses serviços permeiam a rede com conteúdo de vídeo diariamente. Com o objetivo de entender melhor o comportamento destes serviços, este trabalho realiza uma análise da performance de streaming de vídeos adaptativos em VANETs. Resultado das simulações comprovam, através de métricas de QoS e QoE, que o MPEG-DASH apresenta mais vantagens em cenários menos densos, ainda que estes apresentem características de movimentação acentuada.
Fernanda B. J. R. Dallaqua, Alvaro L. Fazenda, and Fabio A. Faria. ForestEyes Project: A proposal to ally Citizen Science and Machine Learning applied to deforestation detection (in Portuguese). XXI Brazilian Symposium on Geoinformatics - GEOINFO, 2020.
This paper presents the ForestEyes project methodology, a Citizen Science project in which volunteers analyze and classify segments of remote sensing images. These classifications are used as training set of classifiers, which will then label new remote sensing images to monitor deforestation. The goal is that, with improvement, the project will be able to generate reliable data, being used in areas where there is a deficit of monitoring programs.
Leonardo Leite, Fabio Kon, and Paulo Meirelles. Understanding context and forces for choosing organizational structures for continuous delivery. X Workshop de Teses e Dissertações (WTDSoft, 2020.
In this research, we aim to understand the organizational structures adopted by software-producing organizations for managing IT technical teams in a continuous delivery context. Following Grounded Theory guidelines, we interviewed 46 IT professionals to investigate how organizations pursuing continuous delivery organize their development and operations teams. Among our results, we discovered four organizational structures: (1) siloed departments, (2) classical DevOps, (3) cross-functional teams, and (4) platform teams. After having discovered such structures and their properties, we describe, in this paper, our plans to better understand which contextual properties and forces lead an organization to adopt an organizational structure to the detriment of the other ones.
Rafael Lopes Gomes, Luiz Fernando Bittencourt, Edmundo Roberto Mauro Madeira. Reliability-Aware Network Slicing in Elastic Demand Scenarios. IEEE Communications Magazine, vol. 58, no. 10, pp. 29-34, October 2020, 2020.
The Internet is an essential tool for society as a whole, being the basis for several services. This importance has increased the requirements for Internet service providers (ISPs). The current Internet infrastructure is limited, which often compromises the quality of service and quality of experience of users. Therefore, ISPs need to evolve their technologies and management capacity. One key approach is network slicing, which allows the management of reliability and elastic resource demand. This article discusses the reliability requirements of the network slicing process as well as the features and challenges of elastic demand scenarios. Additionally, it presents a reliability strategy for network slicing. The results from the experiments performed, using a dataset with real network demands, suggest that the reliability strategy mitigates the impact of physical failures over the Internet access service.
Gabriely Pereira, Lucas Stankus, Gustavo Carlos, Eduardo Pinheiro, Rafael Manzo, Kelly Braghetto, Fabio Kon, Paulo Meirelles. HealthDashboard: A Urban Public Health Geospatial Visualization Platform. VAHC 2020 (11th workshop on Visual Analytics in Healthcare), 2020.
Public healthcare systems generate large amounts of heterogeneous data that can provide valuable insights to inform public policy design. However, extracting relevant information from extensive heterogeneous datasets might be challenging. To address this problem, in a government-academia collaboration, we are developing an interactive visual dashboard for large-scale data analysis based on the Brazilian National Health System (SUS) hospitalization data. Its software architecture enables integration with the Hospital Information System (SIH-SUS) datasets from any region of Brazil so that health professionals can use it in hundreds of different cities. We defined an architecture that tames code complexity and brings modularity to the system. The platform processes SIH-SUS data and stores it into a geolocated relational database. Expert users can then perform advanced queries on the data with composite filters. Results are then displayed via multiple map visualizations, graphs, and tables. We expect that this open-source platform will become a useful tool for science-based public health policy making, influencing Brazilian public managers in the future to adopt an evidence-based, data-driven approach to healthcare management.
Denis Contini, Lucas Fernando Souza de Castro, Edmundo Madeira, Sandro Rigo, and Luiz Fernando Bittencourt. Simulating Smart Campus Applications in Edge and Fog Computing. IEEE International Conference on Smart Computing (SMARTCOMP), 2020.
Due to the rapid increase of IoT applications and their use in many different areas, large amounts of data have been generated to be processed and stored. In this scenario, some applications are sensitive to high latency and response times. In order to fulfil these requirements, Edge and Fog Computing appear with the objective of bringing processing and storage devices closer to applications and management mechanisms. In this context, due to limitations related to high cost, scalability and planning, several mechanisms and algorithms need to be simulated before being implemented in the real world. This paper presents a comparison between two simulation tools and their main characteristics (EdgeCloudSim and iFogSim) using a smart campus scenario deployed at the University of Campinas, where the sensors collect data from water meters and smart energy marker watches, in addition to smart public transportation and battery disposal bins. Our evaluation shows that the information processing in edge and fog can efficiently serve the applications, however, each simulation tool has its specificities, and should be used according to the researcher’s objectives and needs.
Débora Lina Ciriaco, Alexandre Pessoa, Laís Salvador, and Renata Wassermann. Semantic Integration of Unified Health System Databases: A Case Study with the Municipality of São Paulo (in Portuguese). XIII ONTOBRAS - Seminar on Ontology Research in Brazil, 2020.
Integrating databases is crucial for the understanding of the health domain. In this work, a semantic integration methodology was adapted for the birth and death bases of the Unified Health System (SUS). We developed a case study targeting the development of a health indicator in the context of mother and child health at the São Paulo municipality. We developet the ontology layers for this solution, comprising specifications and mappings. The ontologies were populated and evaluated for their capacity to answer the relevant questions selected by domain experts. The solution proved useful in the integration process, providing a global view of the data and its relationships.
Rodrigo Tinini, Daniel Batista, Gustavo Figueiredo, Massimo Tornatore, and Biswanath Mukherjee. Energy-Efficient vBBU Migration and Wavelength Reassignment in Cloud-Fog RAN. IEEE Transactions on Green Communications and Networking ( Volume: 5, Issue: 1, March), 2020.
Cloud-Fog Radio Access Network (CF-RAN) is a new architecture that increases network capacity in Cloud RAN (CRAN) by moving some BaseBand Units (BBU) from cloud to fog nodes closer to Remote Radio Heads (RRH). However, fog nodes increases CapEx and OpEx. Moreover, tidal traffic fluctuations may lead to an energy-inefficient operation if resources becomes lightly loaded. To address this problem, BBUs of fog nodes could be dynamically activated, and following traffic fluctuations, migrated to cloud. By leveraging Network Functions Virtualization (NFV), virtualized BBUs (vBBUs) can be dynamically allocated, deallocated, and migrated from fog nodes to cloud. Moreover, considering a Time-and-Wavelength Division Multiplexed Passive Optical Network (TWDM-PON) fronthaul, traffic can be migrated among virtual Passive Optical Network (VPON) channels to optimize bandwidth usage. In this article, we propose an Integer Linear Programing (ILP) formulation and an algorithm based on its linear relaxation to solve this migration problem. Compared to an algorithm without migration capabilities, our proposals reduces blocking of RRHs demanding processing of 89% and achieves power savings of 38% by reducing activated processing resources and VPONs after migrations, while experiencing small rates of service interruption. Our relaxation-based solution approximates ILP optimality and reduces execution time of ILP up to 50x.
Fernanda Beatriz Jordan Rojas Dallaqua, Fabio Augusto Faria, and Alvaro Luiz Fazenda. Building Data Sets for Rainforest Deforestation Detection Through a Citizen Science Project. IEEE Geoscience and Remote Sensing Letters, 2020.
Originally, the ForestEyes project aims to detect deforestation in tropical forests based on citizen science (CS) and machine learning (ML) approaches, in which the volunteers analyze and label segments of remote sensing images to build new training sets for creating different classification models. In previous work, only three modules related to CS have been proposed. In this letter, two new modules are created: 1) organization and selection and 2) ML. Therefore, these modules turn the ForestEyes project a more robust system in the deforestation detection task, building high-confidence labeled collections, increasing the monitoring coverage, and decreasing volunteer dependence. Performed experiments show that volunteers create better data sets than those based on automatic PRODES-based approaches, selecting the most relevant samples and discarding noisy segments that might disrupt ML techniques. Finally, the results showed the feasibility of allying CS with ML for rainforest deforestation detection task.
Alessandro Santiago dos Santos, Alessandra C. Corsi, Igor C. Teixeira, Vagner L. Gava, Filipe A. M. Falcetta, Eduardo S. de Macedo, Caio da S. Azevedo, Karlson T. B. de Lima, and Kelly R. Braghetto. Brazilian natural disasters integrated into cyber-physical systems: computational challenges for landslides and floods in urban ecosystems. 2020 IEEE International Smart Cities Conference (ISC2), USA, 2020.
Natural disasters cause a high impact in society, resulting in human and economic losses, so much so that increasing the efficiency in monitoring these phenomena becomes a necessity. The integration of cyber-physical systems and their IoT devices, connectivity, machine learning, and Big Data can help to achieve this efficiency. This paper presents key points of the phenomenology of these processes, with challenges and opportunities for applied computing in urban environmental studies in Brazil, as well as investigates studies and techniques that have been used to monitor landslides and floods.
Eduardo F. Z. Santana, Fabio Kon. Using the InterSCSimulator to Evaluate Systems and Urban Scenarios. Tools Session of the 38th Brazilian Symposium on Computer Networks, 2020.
The InterSCSimulator is a scalable, open-source Smart City simulator. The primary use of this tool is to evaluate complex Smart City scenarios and to test Smart City systems such as software platforms and applications. This simulator was already used in different contexts, such as to generate workload to Smart City platforms experiments, to evaluate the impacts of autonomous vehicles systems, and to assess the impact of a new subway line in São Paulo. This paper presents the main features and use cases of the InterSCSimulator, providing an information source to possible new users and contributors to this project.
Fabio Kon, Kelly Braghetto, Eduardo F. Z. Santana, Roberto Speicys, Jorge Guerra Guerra . Toward Smart and Sustainable Cities. Communications of the ACM, November 2020, Vol. 63 No. 11, Pages 51-52, 2020.
Autonomous vehicles will transform urban mobility. However, before being fully implemented, autonomous vehicles will navigate cities in mixed-traffic roads, negotiating traffic with human-driven vehicles. In this work, we simulate a system of autonomous vehicles co-existing with human-driven vehicles, analyzing the consequences of system design choices. The system consists of a network of arterial roads with exclusive lanes for autonomous vehicles where they can travel in platoons. This paper presents the evaluation of this system in realistic scenarios evaluating the impacts of the system on travel time using mesoscopic traffic simulation. We used real data from the metropolis of São Paulo to create the simulation scenarios. The results show that the proposed system would bring reductions to the average travel time of the city commuters and other benefits such as the reduction of the space required to handle all the traffic.
Tallys G. Martins, Nelson Lago, Higor A. de Souza, Eduardo F. Z. Santana, Alexandru Telea, Fabio Kon. Visualizing the structure of urban mobility with bundling: A case study of the city of São Paulo. IV Workshop of Urban Computing, 2020.
Visualization of urban mobility data can facilitate the analysis and the decision-making process by public managers. However, mobility datasets tend to be very large and pose several challenges to the use of visualization, such as algorithm scalability and data occlusion. One approach to solve this problem is trail bundling, which groups motion trails that are spatially close in a simplified representation. This paper presents the results of adapting and using a recent bundling technique on a big dataset of urban mobility in São Paulo. The results show that bundling allows the visualization of various mobility patterns in the city.
Jorge Ribeiro, Daniel Batista, José Pina. hashify: A Software for Visualizing Hashes with Animations (in Portuguese). 2020 Brazilian Symposium on Information Security and Computer Systems (SBSeg), Tool Session, 2020.
Comparing hashes is an essential operation in digital security, but tedious and error-prone when the hashes are in the form of hexadecimal strings.
This paper introduces a new hash visualization software with animations. The software, called hashify, uses 4 characters and 4 SVG icons to generate 2-second animations that transmit around 48 bits of a sequence derived from the original hash. It was implemented as a JavaScript library and embedded in a Firefox extension prototype, which uses the library to display a stamp of the HTTPS certificate used on a web page. The probability of collision and the results of a user survey attest to the effectiveness of hashify.
Thatiane de Oliveira Rosa, Alfredo Goldman, and Eduardo Martins Guerra. Characterization and Evolution Model of Service-based Architecture Systems (in Portuguese). Workshop on Theses and Dissertations (WTDSOFT) - Brazilian Conference on Software: Theory and Practice (CBSOFT), 2020.
Building a good architecture is critical to success in the software development process. However, this is not a trivial activity, as it involves a series of business, technical, and structural decisions. Thus, to support the construction of architecture more appropriate to a context, new approaches such as microservices and modular monoliths constantly appear, which propose to decompose complex software into small loosely coupled parts. However, analyzing the state-of-the-art and practice, there is a blurred limit in the classification of these different approaches, especially those based on services. Furthermore, there is little support for characterizing and targeting service-based architectures. Therefore, based on bibliographic research and case studies, it is intended to develop a model for characterization and evolution of service-based systems architecture, adopting microservices guidelines. This model presents dimensions that measure structural characteristics of the architecture related to the size of modules, sharing of databases, and coupling between services. As a contribution, this model will facilitate the mapping and measurement of different impacts generated in the software architecture, based on the increments and refactorings carried out. It will also support architectural decisions that consider different quality attributes to achieve a balance between independence and collaboration of services for a given system.
Sheriton R. Valim and Felipe Nogueira and Flávia Pisani and Markus Endler. Middleware Support for Generic and Flexible Actuation in the Internet of Mobile Things. 2020 IEEE 6th World Forum on Internet of Things (WF-IoT), 2020.
The ability to control actuators of smart objects is a central requirement of many IoT applications such as Smart Buildings, Smart Cities, and Precision Agriculture. Still, in most current IoT systems, actuation control is hard-wired and device-specific, making it impossible to deal with a dynamic and variable set of smart (and mobile) devices that have also intermittent wireless connectivity with the Internet. These are typical problems of Internet of Mobile Things (IoMT) settings, where smart objects (e.g., medical equipment, robots, UAVs, and vehicles) are not stationary. Thus, this paper describes the design, implementation and performance tests of a middleware-level service that enables generic actuation control for a heterogeneous and dynamic set of actionable smart and movable devices.
Marcelino Silva, Ariel Teles, Rafael Lopes, Francisco Silva, Davi Viana, Luciano Coutinho, Nishu Gupta, and Markus Endler. Neighborhood-aware Mobile Hub: An Edge Gateway with Leader Election Mechanism for Internet of Mobile Things. Mobile Networks and Applications (2020), 2020.
Internet of Things (IoT) is the interconnection of thousands of heterogeneous addressable smart objects (i.e., devices embedded with sensors and actuators) with Internet connectivity. Internet of Mobile Things (IoMT) is characterized by considering the mobility of smart objects. For managing smart objects, it is necessary to provide a middleware. Mobile Hub (M-Hub) is an IoT middleware that collects, processes and distributes data from a large number of smart objects on the edge of the network. M-Hub runs on mobile devices, enabling them to be gateways. It represents an autonomous entity, able to detect a set of objects available in the neighborhood and to monitor them independently of other M-Hubs. Hence, in some situations it may happen that a same object is eligible to be monitored by several M-Hubs. In this context, this paper proposes Neighborhood-aware M-Hub (NAM-Hub), a leader election mechanism integrated to the M-Hub to determine a suitable gateway for each smart object discovered opportunistically. It considers context data gathered from the mobile device to dynamically elect leaders (i.e., a leader and a sub-leader). The proposed solution contributes to take advantage from the resources provided for the mobile gateway and avoids their wastage. The proposed leader election mechanism was tested and evaluated considering its performance and the results were promising, with short detection time and recovery time in the system.
Ivan Rodrigues de Moura, Francisco José da Silva e Silva, Luciano Reis Coutinho and Ariel Soares Teles. Mental Health Ubiquitous Monitoring: Detecting Context-Enriched Sociability Patterns Through Complex Event Processing. 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), 2020.
Traditionally, the process of monitoring and evaluating social behavior related to mental health has based on self-reported information, which is limited by the subjective character of responses and by various cognitive biases. Today, however, computational methods can use ubiquitous devices to monitor social behaviors related to mental health rather than relying on self-reports. Therefore, these technologies can be used to identify the routine of social activities, which enables the recognition of abnormal behaviors that may be indicative of mental disorders. In this paper, we present a solution for detecting context-enriched sociability patterns. Specifically, we introduced an algorithm capable of recognizing the social routine of monitored people. To implement the proposed algorithm, it was used a set of Complex Event Processing (CEP) rules, which allow the continuous processing of the social data stream derived from ubiquitous devices. The experiments performed indicated that the proposed solution is capable of detecting sociability patterns similar to a batch algorithm and demonstrated that context-based recognition provides a better understanding of social routine.
Fernando Freire Scattone and Kelly Rosa Braghetto. Distributed Complex Event Processing Applied to the Real-Time Detection of Traffic Events (in Portuguese). Anais da 11ª Escola Regional de Alto Desempenho de São Paulo (ERAD-SP), 2020.
Uma técnica comumente usada para processar dados em tempo real é o Processamento de Eventos Complexos (CEP – Complex Event Processing).
CEP permite a detecção de eventos de interesse a partir da identificação de padrões nos dados processados. Este trabalho apresenta uma implementação de arquitetura de microsserviços auto-escalável para CEP, apropriada para lidar com grandes fluxos de dados, como os gerados por sensores em cidades inteligentes. Um sistema que detecta problemas no tráfego das linhas de transporte público de ônibus de São Paulo foi projetado para testar a arquitetura.
Francisco Wallison Rocha, Emilio Francesquini, and Daniel Cordeiro. The Use of Data Partitioning to Accelerate Smart City Simulations (in Portuguese). XI Escola Regional de Alto Desempenho de São Paulo, 2020.
Simulations are a high-value technique for Smart Cities research. However, simulators capable of simulating events on a whole city may demand a lot of memory and processing time. This work presents a load-balancing algorithm to a traffic simulator developed to study Smart Cities.
Mayuri Morais and Raphael Camargo. Scalable Data Analysis for Public Bus Systems. 11ª Escola Regional de Alto Desempenho de São Paulo, 2020, 2020.
Urban mobility through quality public transportation is one of the major challenges for the consolidation of smart cities. Researchers developed different approaches for improving bus system reliability and information quality, including travel time prediction algorithms, network state evaluations, and bus bunching prevention strategies. The information provided by these approaches are complementary and could be aggregated for better predictions. In this work, we propose the architecture and a present a prototype implementation of a framework that enables the integration of several approaches, which we call models, into scalable and efficient composite models.
Ivan Moura, Ariel Teles, Francisco Silva, Davi Viana, Luciano Coutinho, Flávio Barros, and Markus Endler. Mental Health Ubiquitous Monitoring Supported by Social Situation Awareness: A Systematic Review. Journal of Biomedical Informatics, vol. 107, July, 2020.
Traditionally, the process of monitoring and evaluating social behavior related to mental health has based on self-reported information, which is limited by the subjective character of responses and various cognitive biases. Today, however, there is a growing amount of studies that have provided methods to objectively monitor social behavior through ubiquitous devices and have used this information to support mental health services. In this paper, we present a Systematic Literature Review (SLR) to identify, analyze and characterize the state of the art about the use of ubiquitous devices to monitor users’ social behavior focused on mental health. For this purpose, we performed an exhaustive literature search on the six main digital libraries. A screening process was conducted on 160 peer-reviewed publications by applying suitable selection criteria to define the appropriate studies to the scope of this SLR. Next, 20 selected studies were forwarded to the data extraction phase. From an analysis of the selected studies, we recognized the types of social situations identified, the process of transforming contextual data into social situations, the use of social situation awareness to support mental health monitoring, and the methods used to evaluate proposed solutions. Additionally, we identified the main trends presented by this research area, as well as open questions and perspectives for future research. Results of this SLR showed that social situation-aware ubiquitous systems represent promising assistance tools for patients and mental health professionals. However, studies still present limitations in methodological rigor and restrictions in experiments, and solutions proposed by them have limitations to be overcome.
Rayele Moreira, Ariel Teles, Renan Fialho, Rodrigo Baluz, Thalyta Cibele Santos, Rômulo Goulart-Filho, Laiane Rocha, Francisco José Silva, Nishu Gupta, Victor Hugo Bastos, and Silmar Teixeira. Mobile Applications for Assessing Human Posture: A Systematic Literature Review. Electronics, vol. 9, 2020.
Smartphones are increasingly incorporated with features such as sensors and high resolution cameras that empower their capabilities, enabling their use for varied activities including human posture assessments. Previous reviews have discussed methods used in postural assessment but none of them focused exclusively on mobile applications. This paper systematically reviews mobile applications proposed for analyzing human posture based on alignment of the body in the sagittal and coronal plane. The main digital libraries were searched, 26 articles published between 2010 and 2020 were selected, and 13 mobile applications were identified, classified and discussed. Results showed that the use of mobile applications to assist with posture assessment have been demonstrated to be reliable, and this can contribute to clinical practice of health professionals, especially the assessment and reassessment phases of treatments, despite some variations when compared to traditional methods. Moreover, in the case of image-based applications, we highlight the advantage that measurements can be taken with the assessor at a certain distance with respect to the patient’s position, which is an important function for assessments performed in pandemic times such as the outbreak of COVID-19.
Luis Gustavo Araujo Rodriguez and Daniel Macêdo Batista. Program-aware fuzzing for MQTT applications. ISSTA 2020: Proceedings of the 29th ACM SIGSOFT International Symposium on Software Testing and Analysis, 2020.
Over the last few years, MQTT applications have been widely exposed to vulnerabilities because of their weak protocol implementations. For our preliminary research, we conducted background studies to: (1) determine the main cause of vulnerabilities in MQTT applications; and (2) analyze existing MQTT-based testing frameworks. Our preliminary results confirm that MQTT is most susceptible to malformed packets, and its existing testing frameworks are based on blackbox fuzzing, meaning vulnerabilities are difficult and time-consuming to find. Thus, the aim of my research is to study and develop effective fuzzing strategies for the MQTT protocol, thereby contributing to the development of more robust MQTT applications in IoT and Smart Cities.
Anderson Almeida, Marcos Amaris, Bruno Merlin and Allan Veras. Modeling and Temporal Prediction of Quality Water Parameters Using Deep Neural Networks (in Potuguese)). Workshop of Applied Computing on the Management of the Environment and Natural Resources, 2020.
The quality of the water is directly related to its level of pollution, and for that, monitoring is necessary to identify the physical, chemical, and biological characteristics, considering the current legislation.
This article presents a comparison of the Long-Short Term Memory (LSTM) and Perceptron Multilayer (MLP) neural network models to predict the pH, OD, BOD, Phosphorus, and Turbidity parameters of water quality. The error metrics RMSE and MSE were used, when the neural networks are configured with 10, 25, and 50 neurons. The LSTM network presented RMSE errors of 0.137, 0.132 and 0.134, and MSE of 0.036, 0.034 and 0.035. The MLP network presented RMSE errors of 0.095, 0.084 and 0.076, and MSE of 0.013, 0.010 and 0.008.
The results of the experiments aim to contribute to the process of monitoring water quality and to assist water management planning through the appropriate machine learning model for predicting parameters.
Osvaldo Fonseca, Ítalo Cunha, Elverton Fazzion, Wagner Meira Jr, Bivaldor Junior, Ronaldo A. Ferreira and Ethan Katz-Bassett. Tracking Down Sources of Spoofed IP Packets. IFIP Networking Conference, 2020.
The lack of authentication in the Internet’s data plane allows hosts to falsify (spoof) the source IP address in packet headers, which forms the basis for amplification denial-of-service (DoS) attacks. Current approaches to locate sources of spoofed traffic lack coverage or are not deployable today. We propose a mechanism that a network with multiple peering links can use to coarsely locate the sources of spoofed traffic in the Internet. More precisely, the network can monitor and map spoofed traffic arriving on a peering link to the set of sources routed toward that link. We propose mechanisms the network can use to systematically vary BGP announcement configurations to induce changes to Internet routes and to the set of sources routed to each peering link. A network using our technique can correlate observations over multiple configurations to more precisely delineate regions sending spoofed traffic. Evaluation of our techniques on the Internet shows that they can partition the Internet into small regions, allowing targeted intervention.
Received the 2nd Best Paper Award.
Leonardo Leite, Fabio Kon, Gustavo Pinto and Paulo Meirelles. Building a Theory of Software Teams Organization in a Continuous Delivery Context. 42nd International Conference on Software Engineering Companion (ICSE ’20 Companion), 2020.
Based on Grounded Theory guidelines, we interviewed 27 IT professionals to investigate how organizations pursuing continuous delivery should organize their development and operations teams. In this paper, we present the discovered organizational structures: (1) siloed departments, (2) classical DevOps, (3) cross-functional teams, and (4) platform teams.
ICSE Poster Track
Leonardo Leite, Fabio Kon, Gustavo Pinto and Paulo Meirelles. Platform Teams: An Organizational Structure for Continuous Delivery. IEEE/ACM 42nd International Conference on Software Engineering Workshops (ICSEW’20), 2020.
Context: Continuous delivery practices accelerate time to market and improve customer satisfaction. Although recent related work suggests that organizations employing continuous delivery should promote a collaborative culture among different IT teams, there is no substantial literature tackling how organizations should organize their teams to excel in the context of continuous delivery.
Objective: In this study, we investigate how organizations pursuing continuous delivery organize their development and operations teams.
Method: We collected and analyzed data from interviews with 46 IT professionals, following Grounded Theory guidelines.
Results: After a careful analysis, we found four patterns of organizational structures: (1) the siloed departments, (2) the classical DevOps, (3) the cross-functional teams, and (4) the platform teams. This empirical study organizes and presents these structures, alongside their properties, as a taxonomy, which is our theory for organizing software teams in the context of continuous delivery.
André Luis Cristiani, Roger Immich, Ademar T. Akabane, Edmundo Roberto Mauro Madeira, Leandro Aparecido Villas and Rodolfo I. Meneguette. ATRIP: Architecture for Traffic Classification Based on Image Processing. MDPI Vehicles, number 2, June, 2020.
With the increase of vehicles in large urban centers, there is also an increase in the number of traffic jams and accidents on public roads. The development of a proper Intelligent Transport System (ITS) could help to alleviate these problems by assisting the drivers on route selections to avoid the most congested road sections. Therefore, to improve on this issue, this work proposes an architecture to aid an ITS to detect, analyze, and classify the traffic flow conditions in real time. This architecture also provides a control room dashboard to visualize the information and notify the users about the live traffic conditions. To this end, the proposed solution takes advantage of computer vision concepts to extract the maximum information about the roads to better assess and keep the drivers posted about the traffic conditions on selected highways. The main contribution of the proposed architecture is to perform the detection and classification of the flow of vehicles regardless of the luminosity conditions. In order to evaluate the efficiency of the proposed solution, a testbed was designed. The obtained results show that the accuracy of the traffic classification rate is up to 90% in daylight environments and up to 70% in low light environments when compared with the related literature.
Thatiane de Oliveira Rosa, Alfredo Goldman, and Eduardo Martins Guerra. How ‘micro’ are your services?. IEEE International Conference on Software Architecture Companion (ICSA-C), 2020.
Microservice is an architectural style that proposes that a complex system should be developed from small and independent services that work together. There is not a welldefined boundary about when a software architecture can be considered based on microservices or not. Because of that, defining microservices context and infrastructure is challenging, especially to characterize aspects related to microservice size, data consistency, and microservices coupling. Thus, it is crucial to understand the microservices-based software characteristics, to comprehend the impact of some evolutions on architecture, and evaluate how much a particular architecture fits the microservices architectural style. Therefore, based on bibliographic research and case studies conducted in academical and industrial environments, we aim to propose a model to characterize the architecture structure based on the main guidelines of the microservice architectural style. This model introduces dimensions that measure characteristics based on modules size, coupling to data sources, and service collaboration. This study should facilitate the mapping, measurement, and monitoring of different impacts generated in the software architecture from increments and refactoring performed. This work is on the initial development stage and as a result, we expected that the model supports architectural decisions that consider different quality attributes to achieve the right balance between service independence and collaboration for a given system.
Eddas Bertrand‐Martinez, Phelipe Dias Feio, Vagner de Brito Nascimento, Fabio Kon and Antônio Abelém. Classification and evaluation of IoT brokers: A methodology. International Journal of Network Management, e2115, 2020.
Since the term Internet of Things (IoT) was coined by Kevin Ashton in 1999, a number of middleware platforms have been developed to cope with important challenges such as the integration of different technologies. In this context of heterogeneous technologies, IoT message brokers become critical elements for the proper function of smart systems and wireless sensor networks (WSN) infrastructures. There are several evaluations made on IoT messaging middleware performance. Nevertheless, most of them ignore crucial aspects of the IoT context that also need to be included, such as reliability and other qualitative aspects. Thus, in this article, we propose a methodology for classification and evaluation of IoT brokers to help the scientific community and technology industry on evaluating them according to their interests, without leaving out important aspects for the context of smart environments. Our methodology bases its qualitative evaluations on the ISO/IEC 25000 (SQuaRE) set of standards and its quantitative evaluations on Jain’s process for performance evaluation. We developed a case study to illustrate our proposal with 12 different open‐source brokers, validating the feasibility of our methodological approach.
Alexandre Aragão, Lucas Machado, Nathyane Moreno, Davi Viana, Francisco Silva, Tércio Sousa, Luis Rivero, Ariel Teles, Arlindo F. da Conceição, and Inaldo Costa. Improving a smart city application through evaluation of Quality Metrics and Usability (in Portuguese). iSys - Brazilian Journal of Information Systems, v. 13, n. 3, p. 55-81, June., 2020.
Several software applications have been changing people’s lifestyles in technological and social aspects. Applications in the context of Smart Cities (SCs) may contain characteristics that are not normally evaluated in traditional applications, since they may involve aspects related to sensor networks, management of large amounts of data and applications that have specific behaviors according to the context of use. This paper presents a study on the evaluation of three software quality characteristics considered relevant for SCs: context, calmness and Mobility. Within the context of the study, two tests were performed to evaluate an application for SCs. Additionally, an heuristic evaluation was carried out, aiming to verify the usability of the application and the impacts of this type of evaluation in applications for SCs. We identified that both the evaluated characteristics and the heuristics are adequate for the evaluation of applications for ICs, but that their results may be influenced by aspects of development and characteristics of the context of use.
Sheriton R. Valim, Felipe Nogueira, Flávia Pisani and Markus Endler. Middleware Support for Generic and Flexible Actuation in the Internet of Mobile Things. IEEE 6th World Forum on Internet of Things (WF-IoT 2020), 2020.
The ability to control actuators of smart objects is a central requirement of many IoT applications such as Smart Buildings, Smart Cities, and Precision Agriculture. Still, in most current IoT systems, actuation control is hard-wired and device-specific, making it impossible to deal with a dynamic and variable set of smart (and mobile) devices that have also intermittent wireless connectivity with the Internet. These are typical problems of Internet of Mobile Things (IoMT) settings, where smart objects (e.g., medical equipment, robots, UAVs, and vehicles) are not stationary. Thus, this paper describes the design, implementation and performance tests of a middleware-level service that enables generic actuation control for a heterogeneous and dynamic set of actionable smart and movable devices.
Received an Outstanding Student Paper Award
Davor Ljubenkov, Fabio Kon, and Carlo Ratti. Optimizing Bike Sharing System Flows Using Graph Mining, Convolutional and Recurrent Neural Networks. 2020 IEEE European Technology and Engineering Management Summit (E-TEMS), 2020.
A Bicycle-sharing system (BSS) is a popular service scheme deployed in cities of different sizes around the world. Efficiently keeping bicycle-sharing system as balanced as possible is the main problem and thus, predicting or minimizing the manual transportation of bikes across the city is the prime objective in order to save logistic costs for operating companies. The purpose of this paper is two-fold: Identification of spatial structures and their structural change using Convolutional neural network (CNN) that takes adjacency matrix snapshots of unbalanced sub-graphs, and the Long short-term memory artificial recurrent neural network (RNN LSTM) in order to find and predict its dynamic patterns. As a result, we are predicting bike flows for each node in the possible future subgraph configuration, which in turn informs bicycle-sharing system owners to plan accordingly. Benefits are identified both for urban city planning and for bike-sharing companies by saving time and minimizing their cost.
Gabriel da Silva, Dyego Oliveira, Rafael L. Gomes, Luiz F. Bittencourt, and Edmundo R. M. Madeira. Reliable Network Slices based on Elastic Network Resource Demand. NOMS 2020 - 2020 IEEE/IFIP Network Operations and Management Symposium, 2020.
Internet access is crucial to the human society as a platform for several services to the users. Despite this importance, the Internet suffers limitations that compromise Quality of Service (QoS) guarantees. Thus, Internet Service Providers (ISPs) need to evolve, adding new technologies and management strategies to their infrastructure. A promising approach is the slicing of network resources among clients and delivered services, where reliability and elastic resource demand through the day are key issues. Within this context, this paper presents an algorithm called Reliable Reuse Encourage (R-REENC), which defines network slices based on bandwidth requirements and the desired reliability for the clients. The results suggest that the proposed algorithm allocates more suitable slices than other existing approaches.
Melissa Wen, Leonardo Alexandre Ferreira Leite, Fabio Kon, and Paulo Meirelles. Understanding FLOSS Through Community Publications: Strategies for Grey Literature Review. ICSE-NIER '20: Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering: New Ideas and Emerging Results, 2020.
Over the last decades, the Free/Libre/Open Source Software (FLOSS) phenomenon has been a topic of study and a source of real-life artifacts for software engineering research. A FLOSS project usually has a community around its project, organically producing informative resources to describe how, when, and why a particular change occurred in the source code or the development flow. Therefore, when studying this kind of project, collecting and analyzing texts and artifacts can promote a more comprehensive understanding of the phenomenon and the variety of organizational settings. However, despite the importance of examining Grey Literature (GL), such as technical reports, white papers, magazines, and blog posts for studying FLOSS projects, the GL Review is still an emerging technique in software engineering studies, lacking a well-established investigative methodology. To mitigate this gap, we present and discuss challenges and adaptations for the planning and execution of GL reviews in the FLOSS scenario. We provide a set of guidelines and lessons learned for further research, using, as an example, a review we are conducting on the Linux kernel development model.
Thiago Wallass Nascimento Mendes, André Luiz Almeida Cardoso, Alysson Cirilo Silva, Daniel S. Carvalho, Marcos R. Júnior, Markus Endler, Ariel Soares Teles, and Francisco José da Silva e Silva. Internet of Things Applied to Presence Management and People Meetings in Smart Buildings (in Portuguese). Revista de Sistemas e Computação, v. 10, n. 3 , 2020.
With technological advances and the popularization of the Internet of Things (IoT), more concepts of Smart Cities have been adopted in large urban centers, in particular, in smart buildings, that use sensors to better control their facilities. One of the areas of smart buildings is the presence and meeting management that manages the displacement and location of occupants in the building. The detection of people in indoor environments is becoming increasingly useful, especially in times of pandemic, when it is important to identify which people were close to each other in the same place and for how long. Considering this scenario, this study presents a distributed software architecture that uses four components that provide services for storing and consulting data, meeting notifications, and identifying the devices involved. In a flexible way, beacons and Android devices can be used to represent both people and physical spaces. In addition, the proposed architecture enables to determine attendances in real time, calculate the total time of stay, and check meetings of people. The effectiveness of the proposed solution was demonstrated through an experimental evaluation simulating its use.
André Luiz Almeida Cardoso, Thiago Wallass Nascimento Mendes, Ariel Soares Teles, and Francisco José da Silva e Silva. An Architecture for the Secure Distribution of Context Data in Mobile Things Internet Applications (in Portuguese). Revista de Sistemas e Computação, v. 10, n. 3, 2020.
The Internet of Things (IoT) is increasingly present in people’s daily lives. In this paradigm, everyday objects can connect to the Internet, interact with each other and exchange information with people. IoT operates in domains such as health and well being, logistics, industry, and smart cities. Data gathered in these domains comes from different devices. A frequent solution for the heterogeneity of devices is the use of middleware, which aims to serve as a basis for the development of IoT applications. IoT applications have security requirements. Among the various existing IoT middleware solutions, only a few show efforts to provide security mechanisms. The objective of this study is to facilitate the secure distribution of context data in Internet of Mobile Things (IoMT) applications, through the development of a security service. The security service provides mechanisms for establishing a secure communication channel, authentication and access control. Experiments were conducted in a mobile application to compare the cost of memory and processing with and without the use of security features. Results confirm that the security features can be used without requiring excessive computational cost.
Camila A. Wanous, Flávia Pisani, and Markus Endler. NOOP: An IoMT System for Notifying Public Security Issues and Increasing Police Patrol Coverage. 4th Conference on Cloud and Internet of Things (CIoT), 2020.
Although public security is still one of the major problems in most large cities, uninterrupted overt patrolling and rapid police intervention have been identified as effective mechanisms to combat street theft and crime. However, several police departments do not have access to technologies for reliable data communication and workforce management to be notified about occurrences and effectively respond to them. This paper presents the design and evaluation of NeighborhOOd Patrolling (NOOP), an open-source Internet of Mobile Things system for notifying public security issues and increasing police patrol coverage. This tool is being used as an initial version for the “Segurança Presente 5.0” overt patrolling initiative in the city of Rio de Janeiro, Brazil.
Lucas A. M. Silva, Marcos A. M. Vieira, Dorgival Guedes and Ronaldo A. Ferreira. Software-Defined Networking with Services Oriented by Domain Names. Telecommunication Systems, Vol. 74, pages 67-82, 2020.
Software-defined networking (SDN) has provided a new paradigm for network management by allowing a central controller to program the underlying switches directly. However, OpenFlow, the de facto standard API for communicating with the switches, has limited visibility into the network headers, hindering innovations in the data plane and overloading the controller when a more sophisticated network application is needed. In this work, we leverage existing capabilities of modern switches to increase the abstraction power of OpenFlow and enrich the functionalities performed on the data plane of a network. We present an architecture that extends OpenFlow to support matching rules with domain names and provides data-plane operations that are only supported by the controller in existing approaches. Our architecture provides a better abstraction for programming the network and enables more concise policy specifications by requiring fewer rules in the switch flow table. To realize our architecture, we developed a prototype of a switch and a controller to handle the domain name extensions. We presented an application use case for blocking unwanted traffic required for Telecom companies. Our experimental results show that our solution reduces latency, number of rules in the switch, and number of packets sent to the controller. We also show that the new abstraction we provide can significantly reduce the code size of a network application.
Carlo Puliafito, Diogo Gonçalves, Márcio Lopes, Leonardo Martins, Edmundo Madeira, Enzo Mingozzi, Omer Rana and Luiz Bittencourt. MobFogSim: Simulation of mobility and migration for fog computing. Simulation Modelling Practice and Theory, Volume 101 - May, 102062, 2020.
Fog computing is an extension of the cloud towards the network edge that brings resources and services of computing in closer proximity to end users. This proximity provides several benefits such as reduced latency that improves user experience. However, user mobility may limit such benefits in practice, as the distance to a fog service may vary as a user moves from one location to another. Migration of a fog service may be one possible mitigation strategy, enabling the service to always be close enough to a user. Although many simulators exist for evaluating application behaviour and performance within a fog computing environment, none allows evaluation of service migration solutions to support mobility. MobFogSim is presented in this work to overcome this limitation. It extends iFogSim to enable modelling of device mobility and service migration in fog computing. MobFogSim is validated by comparing simulation results with those obtained from a real testbed where fog services are implemented as containers. Additional experiments are carried out in MobFogSim taking account of various mobility patterns of a user, derived from Luxembourg SUMO Traffic (LuST). We use an experiment-based approach to study the impact of user mobility on container migration in fog computing.
Alexandre Meslin, Noemi Rodriguez, and Markus Endler. Scalable Mobile Sensing for Smart Cities: The MUSANet Experience. IEEE Internet of Things Journal, 2020.
In this paper, we present and analyze MUSANet, a hierarchical, distributed, context-aware architecture for collecting, processing, and distributing data in smart cities. We discuss some use case examples related to monitoring and predicting bus arrivals in public transportation and weather conditions. We also present performance results in different scenarios that point to the feasibility of our goal: a scalable architecture with a fast response time to traffic events. MUSANet is based on a three-tier architecture distributed over cloud, fog, and edge, and supporting complex event processing (CEP) in all of them. Although the system is under development using the InterSCity platform in the cloud, the ContextNet middleware at the fog, and the Mobile-Hub platform at the edge, the MUSANet architecture can be deployed using other platforms, maintaining the concept of tiering responsibilities to minimize network bandwidth and delay, group communication, and broad mobile support.
Rodrigo Tinini, Matias Santos, Gustavo Figueiredo, and Daniel Batista. 5GPy: A SimPy-based Simulator for Performance Evaluations in 5G Hybrid Cloud-Fog RAN Architectures. Simulation Modelling Practice and Theory, Volume 101, 2020.
The joint cooperation of cloud and fog computing emerges as a new architectural pattern for future 5G networks in order to cope with the increasingly number of mobile elements presented in such networks. Through the use of the cloud, power efficiency can be achieved through centralization of processing. On the other hand, the use of fog processing nodes increases power consumption but helps to decrease the latency of delay-sensitive applications and to increase the coverage of the network. As the use of cloud and fog presents conflicting characteristics, it is important to accurately study their behaviour in order to define the best way to use such a hybrid architecture. In this work we present a three-fold contribution to the study of joint cloud and fog computing architectures. First, we present a hybrid architecture called Cloud-Fog RAN (CF-RAN) that focus on dynamic activation and deactivation of both network and processing resources in order to maintain a balanced operation between the cloud and the fog. Second, we present a performance evaluation model used to analyse the performance of different metrics of CF-RAN. Third, as it is very difficult and costly to build cloud and fog real scenarios, we introduce 5GPy, a SimPy event-driven simulator, publicly available, used to perform small and large scale simulations on architectures such as CF-RAN. We present the architectural details of 5GPy and, by using Integer Linear Program (ILP) and graph-based heuristics to allocate resources in 5G networks, we performed simulations of CF-RAN operation in a small network and in a large network based on a Brazilian city. The results show interesting aspects and trade-offs between cloud and fog computing that were possible to be found with the proposed performance evaluation model and with the 5GPy simulator.
Ivan Zyrianoff, Alexandre Heideker, Dener Silva, João Kleinschmidt, Juha-Pekka Soininen, Tullio Salmon Cinotti and Carlos Kamienski. Architecting and Deploying IoT Smart Applications: A Performance–Oriented Approach. Sensors 20(1), 84, 2020.
Layered internet of things (IoT) architectures have been proposed over the last years as they facilitate understanding the roles of different networking, hardware, and software components of smart applications. These are inherently distributed, spanning from devices installed in the field up to a cloud datacenter and further to a user smartphone, passing by intermediary stages at different levels of fog computing infrastructure. However, IoT architectures provide almost no hints on where components should be deployed. IoT Software Platforms derived from the layered architectures are expected to adapt to scenarios with different characteristics, requirements, and constraints from stakeholders and applications. In such a complex environment, a one-size-fits-all approach does not adapt well to varying demands and may hinder the adoption of IoT Smart Applications. In this paper, we propose a 5-layer IoT Architecture and a 5-stage IoT Computing Continuum, as well as provide insights on the mapping of software components of the former into physical locations of the latter. Also, we conduct a performance analysis study with six configurations where components are deployed into different stages. Our results show that different deployment configurations of layered components into staged locations generate bottlenecks that affect system performance and scalability. Based on that, policies for static deployment and dynamic migration of layered components into staged locations can be identified.
Melissa Wen, Rodrigo Siqueira, Nelson Lago, Diego Camarinha, Antonio Terceiro, Fabio Kon and Paulo Meirelles. Leading successful government-academia collaborations using FLOSS and agile values. Journal of Systems and Software, 164, 2020.
Government and academia share concerns for efficiently and effectively servicing societal demands, which includes the development of e-government software. Government-academia partnerships can be a valuable approach for improving productivity in achieving these goals. However, governmental and academic institutions tend to have very different agendas and organizational and managerial structures, which can hinder the success of such collaborative projects. In order to identify effective approaches to overcome collaboration barriers, we systematically studied the case of the Brazilian Public Software portal project, a 30-month government-academia collaboration that, using Free/Libre/Open Source Software practices and agile methods for project management, developed an unprecedented platform in the context of the Brazilian government. We gathered information from experience reports and data collection from repositories and interviews to derive a collection of practices that contributed to the success of the collaboration. In this paper, we describe how the data analysis led to the identification of a set of three high-level decisions supported by the adoption of nine best practices that improved the project performance and enabled professional training of the whole team.
Extended version of an OSS Conference paper that received the Best Paper award
Ademar Akabane, Roger Immich, Luiz Bittencourt, Edmundo Madeira, and Leandro Villas. Towards a Distributed and Infrastructure-less Vehicular Traffic Management System. Computer Communications, Volume 151, 2020.
In the past few years, several systems have been proposed to deal with issues related to the vehicular traffic management. Usually, their solutions include the integration of computational technologies such as vehicular networks, central servers, and roadside units. Most systems use a hybrid approach, which means they still need a central entity (central server or roadside unit) and Internet connection to find out an en-route event as well as alternative routes for vehicles. It is easy to understand the need for a central entity because selecting the most appropriate vehicle to perform aforementioned procedures is a difficult task. This is especially true in a highly dynamic network. In addition to that, as far as we know, there are very few systems that apply the altruistic approach (not selfish behavior) to routing decisions. Because of that, the issue addressed in this work is how to perform the vehicular traffic management, when an en-route event is detected, in a distributed, scalable, and cost-effective fashion. To deal with these issues, we proposed a distributed vehicle traffic management system, named as dEASY (distributed vEhicle trAffic management SYstem). The dEASY system was designed and implemented on a three-layer architecture, namely environment sensing and vehicle ranking, knowledge generation and distribution, and knowledge consumption. Each layer of the dEASY architecture is responsible for dealing with the main issues that were not addressed in related works or could be improved. The three-layer architecture is arranged as follows: the first layer deals with the task of selecting the most appropriate vehicle to perform data forwarding and/or knowledge generation, the second one addresses the knowledge generation and distribution, and the third layer applies an altruistic approach to choose an alternative route. Simulation results have shown that, compared with other systems from the literature, our proposed system has lower network overhead due to applied vehicle selection and broadcast suppression mechanisms. On average, dEASY also outperformed all other competitors in what regards to the travel time and time lost metrics. Through the analysis of results, it is possible to conclude that our infrastructure-less system is scalable and cost-effective.
João Vitor Torres, Igor Drummond Alvarenga, Raouf Boutaba and Otto Carlos Muniz Bandeira Duarte. Evaluating CRoS-NDN: a comparative performance analysis of a controller-based routing scheme for named-data networking. Journal of Internet Services and Applications, november, 2019.
The huge amount of content names available in Named-Data Networking (NDN) challenges both the required routing table size and the techniques for locating and forwarding information. Content copies and content mobility exacerbate the scalability challenge to reach content in the new locations. We present and analyze the performance of a proposed Controller-based Routing Scheme, named CRoS-NDN, which preserves NDN features using the same interest and data packets. CRoS-NDN supports content mobility and provides fast content recovery from copies that do not belong to the consumer-producer path because it splits identity from location without incurring FIB size explosion or supposing prefix aggregation. It provides features similar to Content Distribution Networks (CDN) in NDN, and improves the routing efficiency. We compare our proposal with similar routing protocols and derive analytical expressions for lower-bound efficiency and upper-bound latency. We also conduct extensive simulations to evaluate results in data delivery efficiency and delay. The results show the robust behavior of the proposed scheme achieving the best efficiency and delay performance for a wide range of scenarios. Furthermore, CRoS-NDN results in low use of processing time and memory for a growing number of prefixes.
Leonardo Leite, Carla Rocha, Fabio Kon, Dejan Milojicic and Paulo Meirelles. A Survey of DevOps Concepts and Challenges. ACM Computing Surveys (CSUR), Volume 52 Issue 6, 2019.
DevOps is a collaborative and multidisciplinary organizational effort to automate continuous delivery of new software updates while guaranteeing their correctness and reliability. The present survey investigates and discusses DevOps challenges from the perspective of engineers, managers, and researchers. We review the literature and develop a DevOps conceptual map, correlating the DevOps automation tools with these concepts. We then discuss their practical implications for engineers, managers, and researchers. Finally, we critically explore some of the most relevant DevOps challenges reported by the literature.
Anderson Mendrot Filho and Denise Stringhini. Wireless sensor networks for monitoring and detection of land slides: a systematic review (in Portuguese). Atas das conferências ibero-americanas www/internet e computação aplicada, 2019.
Deslizamentos de terra são um dos principais tipos de desastres naturais e causam danos ambientais e sociais à população em torno de áreas de risco. Uma maneira de evitar esses danos é pelo monitoramento desses eventos. Atualmente, existe uma tendência no estudo do uso de redes de sensores sem fio de baixo custo para detectar mudanças no ambiente que possam levar a desastres. O artigo apresenta uma revisão sistemática de identificação e síntese da literatura relevante na área de redes de sensores sem fio para monitoramento e detecção de deslizamentos de terra. Com a revisão sistemática, é fornecida uma visão geral e discussão sobre o estado da arte. Finalmente, são apresentadas dificuldades e desafios relacionados às implementações de campo de redes de sensores sem fio para o problema. Os resultados demonstram que o uso dessas redes para a detecção de deslizamentos de terra é viável, mas ainda é uma área que exige muito esforço em trabalhos futuros.
Video of the presentation: https://ciaca-conf.org/pt/apresentacoes-virtuais/
Davi Viana, Thatiane de Oliveira Rosa, Francisco Silva, Pablo Durans, Fabio Kon, and Alfredo Goldman. Software Engineering Practices in the development of applications for Smart Cities: An Experience Report of Teaching in a Contemporary Context. XXXIII Brazilian Symposium on Software Engineering (SBES 2019), 2019.
The heterogeneity of contemporary systems has turned the Software Engineering (SE) area even more challenging, since it is necessary to identify practices that are more adequate according to the technologies and context. Thus, practitioners need to be better prepared for these new systems. The area of Smart Cities (SC) is emerging and presents new challenges in conceptual, technical and academical degrees. This paper presents an experience report of SE practices in the development of SC applications. Five teams used the SC platform and developed their projects, creating software documentation, while applying agile practices. As a result, we identified that some UML diagrams were not adequate to model specific SC’s aspects and microservices. Furthermore, we identified that there was a low application of the proposed agile practices, such as pair programming and daily meetings. Despite being the first time this class was taught, we identified gaps that need to be investigated in order to identify which SE practices are more adequate for such context.
Leonardo Aguilar and Daniel Batista. Effectiveness of Implementing Load Balancing via SDN. II Workshop de Trabalhos de Iniciação Científica e Graduação (WTG) do SBRC, 2019.
Software-Defined Networking (SDN) is an architecture that allows the creation, management and customization of the network through programmable switches and centralized controllers via a well-defined protocol. Despite the wide dissemination of general advantages in using SDN, it is always important to evaluate the real advantages considering specific network applications. In line with this, the purpose of this work is to analyze the effectiveness of using SDN for load balancing by developing a balancer, made available as free software, that can execute three different algorithms, giving to the administrator the possibility to choose, at run time, which will be used as well as their configurations, and the possibility to implement new algorithms.
Michel Barbeau, Joaquin Garcia-Alfaro, Evangelos Kranakis and Fillipe Santos. Quality Amplification of Error Prone Navigation for Swarms of Micro Aerial Vehicles. GLOBECOM Workshops, 2019.
We present an error tolerant path planning algorithm for Micro Aerial Vehicle (MAV) swarms. It is GPS-free. The MAVs find their way using cameras to identify a series of visual landmarks. The landmarks lead towards the destination. MAVs are unaware of the terrain and landmark locations. Landmarks hold a-priori information whose interpretation is prone to errors. We distinguish two types of errors: recognition and advice. Recognition errors are due to misinterpretation of sensed data or a-priori information, or confusion of objects. Advice errors are due to outdated or wrong information associated to the landmarks. The MAVs cooperate and exchange information wirelessly, to minimize the errors. Consequently, the swarm experiences data quality amplification and error reduction. Quality amplification is related to the number of MAVs. The solution effectively achieves an adaptive error tolerant navigation system.
Christian Bongiorno, Daniele Santucci, Fabio Kon, Paolo Santi, and Carlo Ratti. Comparing bicycling and pedestrian mobility: Patterns of non-motorized human mobility in Greater Boston. Journal of Transport Geography, Volume 80, October, 2019.
During the past 100 years, many large cities around the world prioritized individual transportation in cars over more sustainable and healthier modes of transportation. As a result, traffic jams, air pollution, and fatal accidents are a daily reality in most metropolis, in both developed and developing countries. On the other hand, walking and bicycling are effective means of transportation for short to medium distances that offer advantages to both the city environment and the health of its citizens. While there is a large body of research in modeling and analysis of urban mobility based on motorized vehicles, there is much less research focusing on non-motorized vehicles, and almost no research on comparing pedestrian and cyclist behavior. In this paper, we present a detailed quantitative analysis of two datasets, for the same period and location, covering pedestrian and bike sharing mobility. We contrast the mobility patterns in the two modes and discuss their implications. We show how pedestrian and bike mobility are affected by temperature, precipitation and time of day. We also analyze the spatial distribution of non-motorized trips in Greater Boston and characterize the associated network of mobility flows with respect to multiple metrics. This work contributes to a better understanding of the characteristics of non-motorized urban mobility with respect to distance, duration, time of day, spatial distribution, as well as sensitivity to the weather.
Collaboration between MIT Senseable City Lab and USP
Matias Santos, Rodrigo Tinini, Gustavo Figueiredo and Daniel Batista. Data Analysis and Energy Consumption Prediction in a Cloud-Fog RAN Environment. IEEE Latin-American Conference on Communications (LATINCOM 2019), 2019.
The extraction of information from data collected in a myriad of environments provides unprecedented opportunities for a big range of actions such as decision making and better resource management. Benefits from its processes are relatively large for many network domains such as protocol design, hybrid architectures redesign, and resource management and optimization. Time series or historical data series can be used in several ways, like pattern analysis and prediction support, making it an important support tool for managers to develop goals and objectives focused on their business. The goal of this paper is to discuss the potential of data analysis in hybrid Cloud- Fog Radio Access Networks (CF-RAN) scenarios and present results of applications of the data in the process of prediction energy consumption. In particular, we analysed the knowledge data extraction of some metrics with a strong relationship with energy consumption and we perform a prediction by applying a deep learning algorithm using the previous four hour period to predict the next hour.
Rodrigo Tinini, Gustavo Figueiredo and Daniel Batista. A Batch Scheduling Algorithm for VPON Reconfiguration and BBU Migration in Hybrid Cloud-Fog RAN. 18th IEEE International Symposium on Network Computing and Applications (NCA 2019), 2019.
Hybrid Cloud-Fog Radio Access Network (CF-RAN) is a recent network architecture proposed to increase network coverage from CRAN while leveraging power consumption in future 5G networks. In CF-RAN, the processing of baseband signals from Remote Radio-Heads (RRHs) can be performed in virtualized BaseBand Units (vBBUs) located in the cloud or in fog nodes that are instantiated in function of the network demand. Through a Time-and-Wavelength Division Multiplexing Passive Optical Network (TWDM-PON), virtualized PONs (VPONs) can be dynamically created to support transmissions from RRHs to vBBUs. However, due to traffic fluctuations, the amount of necessary vBBUs and VPONs may change along a day. In this paper, we propose a batch scheduling algorithm based on Integer Linear Programming (ILP) to perform reconfiguration of VPONs and migration of vBBUs among processing nodes in function of fluctuation on traffic demands. Our results show that, in comparison to an incremental algorithm without reconfiguration of VPONs and vBBUs migration capacities, our algorithm reduces power consumption and bandwidth wastage by up to 28% and 57%, respectively, and also eliminates blocking probability.
Rodrigo Tinini, Daniel Batista, Gustavo Figueiredo, Massimo Tornatore and Biswanath Mukherjee. Energy-Efficient BaseBand Processing via vBBU Migration in Virtualized Cloud-Fog RAN. IEEE Global Communications Conference (IEEE GLOBECOM), 2019.
Cloud-Fog Radio Access Networks (CF-RAN) were proposed as an alternative network architecture to alleviate the high fronthaul capacity requested in traditional Cloud RAN (CRAN) by moving some BaseBand Units (BBUs) from the cloud nodes to fog nodes closer to users. However, when BBU processing is moved into fog nodes, OPEX and CAPEX will increase, and the cost and energy savings introduced by CRAN will also reduce. Moreover, mobile traffic fluctuations may lead to an unbalanced resource utilization and energy-inefficient operation in fog nodes. To address this problem, processing functions in fog nodes could be activated and deactivated in function of network traffic and BBUs placed on fog nodes could be migrated to cloud nodes when network traffic is low. In this paper, we propose an Integer Linear Programming (ILP) formulation to address this dynamic resource allocation problem. By means of Network Functions Virtualization (NFV), virtualized BBUs (vBBUs) can be dynamically allocated and deallocated in fog nodes. Furthermore, considering the availability of cloud nodes and the optical fronthaul, vBBUs can be migrated from fog nodes to cloud nodes in order to balance processing loads and save energy. Compared to a baseline incremental algorithm without vBBU migration, our proposal reduces blocking probability in 89% and achieves power savings of 38%, while providing a very small rate of service interruption due to vBBUs migration.
Thales Bandiera Paiva, Javier Navaridas and Routo Terada. Robust Covert Channels Based on DRAM Power Consumption. International Conference on Information Security, 2019.
To improve the energy efficiency of computing systems, modern CPUs provide registers that give estimates on the power consumption. However, the ability to read the power consumption introduces one class of security concerns called covert channels, which are communication channels that enable one process to transmit a message to another one in a system where these processes were meant to be isolated. Our contribution consists in the first covert channel in which messages are transmitted by modulating the DRAM power consumption. The channel implementation outperforms similar proposals, achieving 1800 bps with 10% error, and 2400 bps with 15% error, when running on a notebook and on a desktop platforms, respectively, To test its robustness against application interference, we considered the channel’s performance when running concurrently with different benchmarks: MRBench, Terasort and LINPACK. When running on the notebook, the channel is fairly robust, achieving between 300 and 600 bps with around 10% error depending on the workload considered.
Thales Bandiera Paiva and Routo Terada. A timing attack on the HQC encryption scheme. Selected Areas in Cryptography, 2019.
The HQC encryption scheme is a promising code-based submission to NIST’s post-quantum cryptography standardization process. The scheme is based on the decisional decoding problem for random quasicyclic codes. One problem of the author’s submission to NIST is that the reference implementation is not constant-time. We use this to present the first timing attack against HQC. The attack is practical, requiring the attacker to record the decryption time of around 400 million ciphertexts for a set of HQC parameters corresponding to 128 bits of security. This makes the use of constant-time decoders mandatory for the scheme to be considered secure.
Luis Sant'Ana, Daniel Cordeiro and Raphael Y. de Camargo. PLB-HAC: Dynamic Load-Balancing for Heterogeneous Accelerator Clusters. 25th International Conference on Parallel and Distributed Computing (EuroPar 2019), Göttingen, Germany, August 26–30, 2019, 2019.
Efficient usage of Heterogeneous clusters containing combinations of CPUs and accelerators, such as GPUs and Xeon Phi boards requires balancing the computational load among them. Their relative processing speed for each target application is not available in advance and must be computed at runtime. Also, dynamic changes in the environment may cause these processing speeds to change during execution. We propose a Profile-based Load-Balancing algorithm for Heterogeneous Accelerator Clusters (PLB-HAC), which constructs a performance curve model for each resource at runtime and continuously adapt it to changing conditions. It dispatches execution blocks asynchronously, preventing synchronization overheads and other idleness periods due to imbalances. We evaluated the algorithm using data clustering, matrix multiplication, and bioinformatics applications and compared with existing load-balancing algorithms. PLB-HAC obtained the highest performance gains with more heterogeneous clusters and larger problems sizes, where a more refined load-distribution is required.
Gabriel Leopoldino and Ricardo da Rocha. An architecture for spontaneous and secure communication for mobile IoT in smart cities (in portuguese). XIII Workshop de Trabalhos de Iniciação Científica e de Graduação (WTICG) on XIX Simpósio Brasileiro de Segurança da Informação e de Sistemas Computacionais (SBSeg), 2019.
Uma Cidade Inteligente compreende soluções que integram Internet das Coisas e serviços de software para permitir a construção de aplicações que explorem a disseminação de informações para melhorar a qualidade de vida da população. Neste cenário, arquiteturas de software devem permitir que dispositivos de IoT se conectem à infraestrutura de software que permeia uma Cidade Inteligente de maneira espontânea e mediada por dispositivos de maior poder computacional, como smartphones. Em contrapartida, tais arquiteturas devem prover serviços de segurança para impedir de agentes maliciosos explorem a infraestrutura e afetem o correto funcionamento das suas aplicações. Este trabalho apresenta uma arquitetura de comunicação segura para Internet das Coisas Móveis em cidades inteligentes baseada em uma infraestrutura de chaves públicas, que provê serviços de autenticação, confidencialidade e integridade das informações consumidas e publicadas por dispositivos e que são adequadas a diversos cenários de conectividade.
Ademar T. Akabane, Roger Immich, Edmundo R. M. Madeira and Leandro A. Villas. Applying the Vehicular Social Networks Paradigm to Improve the Urban Mobility Management (in Portuguese). XXXVII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, 2019.
The Advanced Traffic Management System (ATMS) has been increasingly used by urban mobility managers to improve vehicular traffic management. Many ATMSs employ centralized solutions because of the difficulty of selecting the most relevant vehicles, in highly dynamic networks, to detect congestion and suggest alternative routes. Furthermore, such solutions are not always scalable. On the other hand, the distributed solution needs to previously segment the entire scenario to select the vehicles. Moreover, such a solution suggests alternative routes, in a selfish fashion, which can lead to secondary congestions. Based on the found open issues, this work proposes a distributed urban mobility management system based on the vehicular social networks paradigm (VSNs) named MAESTRO. The VSNs paradigm emerged from the integration of intelligent wireless communication devices and social networks in the vehicular environment. Two different approaches can be explored in VSNs, i.e., the Social network analysis (SNA) and the Social Network Concepts (SNC). The proposed MAESTRO system adopts a combined use of both SNA and SNC approaches. Simulation results showed that the use of SNA and SNC, in a vehicular environment, has great potential in increasing the scalability of the system and also improving efficiency in the management of urban mobility.
Ademar Takeo Akabane, Roger Immich, Richard Wenner Pazzi, Edmundo Roberto Mauro Madeira and Leandro Aparecido Villas. Exploiting Vehicular Social Networks and Dynamic Clustering to Enhance Urban Mobility Management. Sensors 2019, 2019.
Transport authorities are employing advanced traffic management system (ATMS) to improve vehicular traffic management efficiency. ATMS currently uses intelligent traffic lights and sensors distributed along the roads to achieve its goals. Furthermore, there are other promising technologies that can be applied more efficiently in place of the abovementioned ones, such as vehicular networks and 5G. In ATMS, the centralized approach to detect congestion and calculate alternative routes is one of the most adopted because of the difficulty of selecting the most appropriate vehicles in highly dynamic networks. The advantage of this approach is that it takes into consideration the scenario to its full extent at every execution. On the other hand, the distributed solution needs to previously segment the entire scenario to select the vehicles. Additionally, such solutions suggest alternative routes in a selfish fashion, which can lead to secondary congestions. These open issues have inspired the proposal of a distributed system of urban mobility management based on a collaborative approach in vehicular social networks (VSNs), named SOPHIA. The VSN paradigm has emerged from the integration of mobile communication devices and their social relationships in the vehicular environment. Therefore, social network analysis (SNA) and social network concepts (SNC) are two approaches that can be explored in VSNs. Our proposed solution adopts both SNA and SNC approaches for alternative route-planning in a collaborative way. Additionally, we used dynamic clustering to select the most appropriate vehicles in a distributed manner. Simulation results confirmed that the combined use of SNA, SNC, and dynamic clustering, in the vehicular environment, have great potential in increasing system scalability as well as improving urban mobility management efficiency.
Roger Immich, Leandro Villas, Luiz Bittencourt and Edmundo Madeira. Multi-Tier Edge-to-Cloud Architecture for Adaptive Video Delivery. 7th International Conference on Future Internet of Things and Cloud (FiCloud 2019), 2019.
In the last few years, there has been a rapid proliferation of a wide range of real-time video services and applications. These technologies flood the wireless systems with video content on a daily basis. As a result of this sharp increase in video traffic, the prospect of errors due to network interference and congestion rises. Incidentally, the adoption of the 5th generation of wireless systems (5G) will allow this growth to be even greater due to its high bandwidth capacity and low latency. However, even with these improvements on the wireless capabilities, a reliable and high-quality video transmission still imposes several challenges, such as how to handle a large number of heterogeneous devices and how to better use the resource-richer Edge, Fog, and Cloud computing sources to meet the user’s requirements. To overcome these issues, this work proposes a multi-tier video delivery architecture relying upon several technologies such as Multi-access Edge computing (MEC), 5G slices, and microservice placement/chaining. Furthermore, to assess the proposed idea an experimental proof-of-concept testbed of the multi-tier architecture was designed, implemented, and evaluated using real-world tools and actual video sequences. The results obtained supported our claim that a multi-tier video delivery system is feasible and can greatly benefit the end-users.
Davi Morales, Antônio Chaves and Alvaro Fazenda. Parallel Clustering Search Applied to Capacitated Centered Clustering Problem. 2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2019.
The Clustering Search (CS) is a hybrid method that tries to combine metaheuristics and local search heuristics so that the search is intensified only in promising regions of the solution space. In this paper we propose a new parallel method based on the CS, using the Genetic Algorithm as a solutions generator, to solve the Capacitated Centered Clustering Problem (CCCP). The CCCP is to partition a set of n points into p disjoint groups with limited capacity. Each point is associated with a demand value and the objective is to minimize the sum of the Euclidean distances between the points and their respective geometric centers. The parallel CS consists in a master-slave system implemented following a message passing approach in order to parallelize the local search component, which is the most computationally demanding procedure. The computational results show that the parallel CS is an effective strategy in terms of computational time and efficiency.
Andreiwid Correa and Flavio Silva. Laying the foundations for benchmarking open data automatically: a method for surveying data portals from the whole web. 20th Annual International Conference on Digital Government Research (dg.o 2019), 2019.
The widespread of open data portals in the global scenario makes automated methods for data gathering and assessment a landmark in benchmarking. Some practitioners have already introduced automated approaches focused on mainly quality assessment of selected lists of data portals, but little has been studied about how to ensure exercises happen on the widest range of initiatives across the world, even incipient ones. The purpose of this paper is to provide a method for surveying data portals from the whole web, aiming to produce a whitelist of URLs that point to healthy data portals on the internet. The method was tested on 3.3 billion web addresses from which we found 1,339 open data portals worldwide using the main software platforms in the market CKAN, Socrata, OpenDataSoft and ArcGIS Open Data. Findings showed the choice of the whole web approach increased the number of data portals found, besides offering a workaround for redundancy, discoverability and traceability issues of current sparse and manual-based repositories. This work contributes to development of a fully automated method towards building an independent, reliable and up to date repository as a single source of open data portals operated around the world as well as provide insights about dataset estimation and geographic localization, from which benchmarking exercises may benefit to happen on a larger scale, at higher frequency and with lower costs.
Shortlisted for the award
Fernanda Dallaqua, Alvaro Fazenda and Fabio Faria. ForestEyes Project: Can Citizen Scientists Help Rainforests?. 15th International Conference on eScience (eScience), 2019.
Scientific projects involving volunteers for analyzing, collecting data, and using their computational resources, known as Citizen Science (CS), have become popular due to advances in information and communication technology (ICT). Many CS projects have been proposed to involve citizens in different knowledge domain such as astronomy, chemistry, mathematics, and physics. This work presents a CS project called ForestEyes, which proposes to track deforestation in rainforests by asking volunteers to analyze and classify remote sensing images. These manually classified data are used as input for training a pattern classifier that will be used to label new remote sensing images. ForestEyes project was created on the Zooniverse.org CS platform, and to attest the quality of the volunteers’ answers, were performed early campaigns with remote sensing images from Brazilian Legal Amazon (BLA). The results were processed and compared to an oracle classification (PRODES – Amazon Deforestation Monitoring Project). Two and a half weeks after launch, more than 35,000 answers from 383 volunteers (117 anonymous and 266 registered users) were received, completing all 2050 tasks. The ForestEyes campaigns’ results have shown that volunteers achieved excellent effectiveness results in remote sensing image classification task. Furthermore, these results show that CS might be a powerful tool to quickly obtain a large amount of high-quality labeled data.
Julian J. Arango and Fernando Iazzetta. Silicon sounds (in Portuguese). Exposition catalog - Espaço das Artes, Universidade de São Paulo, April 1 to April 26, 2019., 2019.
Alfredo Goldman and Viviane Almeida Santos. Continuous Improvement of an XP Laboratory Course: An 18 year History. Agile 2019 Conference, 2019.
Since Agile Methods formalization, software engineering education has also been impacted. Universities had to adapt their courses as a way to suit these new software processes. At the University of São Paulo (USP), in Brazil, a course called XP Laboratory was created in 2001. Although the name refers to eXtreme Programming, the discipline aims at teaching agile methods in practice, considering several elements that are crucial for providing the student with real knowledge and experience with agile methods. We have adopted practices inside and across teams, such as rotation of team members to solve project problems, mini-lectures or lightning talks at lunch, and whole-class retrospectives in fishbowl format, among others. We present our experiences of more than 18 years on teaching agile methods and how we have evolved and improved the course based on student feedback.
L. S. Oshiro and Daniel M. Batista. Preliminary Analysis of the Detection of Obfuscated Attacks with Low Cost Hardware in a Threat Detection System (in Portuguese). II Workshop de Trabalhos de Iniciação Científica e Graduação (WTG) do SBRC, 2019.
Tráfego de rede transmitido a altas taxas traz como consequência a necessidade de mecanismos de segurança mais eficientes, já que analisar pacote por pacote antes de tomar uma ação torna-se uma tarefa custosa em termos de processamento. Uma forma de resolver esse problema é com o desenvolvimento e implantação de sistemas de detecção de ameaças que utilizem mecanismos de aprendizado de máquina para antecipar os ataques. Este artigo apresenta os resultados preliminares obtidos na tentativa de melhorar um sistema como esse por meio da análise de ataques automatizados que empregam ofuscação e por meio da avaliação de desempenho de uma unidade Raspberry Pi que poderá ser usada como nó de processamento no sistema melhorado.
R. I. TININI, D. M. BATISTA, GUSTAVO BITTENCOURT FIGUEIREDO, M. TORNATORE, and B. MUKHERJEE. Low-Latency and Energy-Efficient BBU Placement and VPON Formation in Virtualized Cloud-Fog RAN. Journal of Optical Communications and Networking, 2019.
Cloud radio access networks (CRANs) make it possible to reduce power consumption in future 5G networks by decoupling baseband units (BBUs) from cell sites and centralizing the baseband processing from remote radio-heads (RRHs) in BBU pools in a cloud. Although this centralization can enable power savings, it imposes much higher traffic on the optical transport network used to connect RRHs to the BBU pool, i.e., the fronthaul. In this paper, we propose a hybrid cloud-fog RAN (CF-RAN) architecture that resorts to fog computing and to network function virtualization to replicate the processing capacity of a CRAN in local fog nodes closer to the RRHs that can be activated on demand to process surplus fronthaul/cloud traffic. We devise an integer linear programming (ILP) formulation and graph-based heuristics to decide when to activate fog nodes and how to dimension wavelengths on a time-and-wavelength division multiplexing passive optical network to support the fronthaul. Our results show that our architecture can consume up to 96% less energy than a traditional distributed RAN, providing a maximum transmission latency of about 20 μs between RRHs and BBUs even in large traffic scenarios. Moreover, we demonstrate that our graph-based heuristics can achieve the same optimal solutions of the ILP formulation but with a reduction of 99.86% in the execution time.
Diogo Goncalves and Luiz Bittencourt and Edmundo Madeira. An Analysis of User Mobility Prediction for Mobile Applications Migration On Fog Computing Environments(In Portuguese). Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), 2019.
A Computação em Névoa provê a dispositivos IoT acesso com baixa latência a recursos computacionais presentes na borda da rede. Porém, neste ambiente a alta mobilidade de alguns desses dispositivos, como wearables ou dispositivos embarcados em veículos, traz grandes desafios para a alocação e gerência de recursos. Trabalhos recentes têm apresentado os benefícios do uso de predição de mobilidade dos usuários no processo de migração de aplicações neste ambiente. No entanto, uma má escolha do local de execução da aplicação devido a uma imprecisão na localização futura do usuário pode comprometer a qualidade da execução. Este trabalho apresenta uma análise do impacto de uma baixa acurácia na predição de mobilidade do usuário para melhorar o processo de migração de aplicações em ambientes de Névoa. Resultados de simulações indicaram que o uso de predição de mobilidade pode reduzir o número de migrações, mas um erro de cálculo da posição futura do usuário pode aumentar a latência média experimentada por ele em até 30%.
Allan Barbosa, Francisco Silva, Luciano Coutinho, Davi Santos and Ariel Teles. A Domain-Specific Modeling Language for Specification of Clinical Scores in Mobile Health. Proceedings of the 14th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE, 104-113, Heraklion, Crete, Greece, 2019.
Clinical scores are a widely discussed topic in health as part of modern clinical practice. In general, these tools predict clinical outcomes, perform risk stratification, aid in clinical decision making, assess disease severity or assist diagnosis. However, the problem is that clinical scores data are traditionally obtained manually, which can lead to incorrect data and result. In addition, by collecting biological/health data in real time from humans, the current mobile health (mHealth) solutions that computationally solve that problem are limited because those systems are developed considering the specificities of a single clinical score. This work is part of the MDD4ClinicalScores project that addresses the productivity in developing mHealth solutions for clinical scores through the use of Model Driven Development concepts. This paper focus in describing DSML4ClinicalScore, a high-level domain-specific modeling language that uses the Ecore metamodel to describe a clinical score sp ecification. To propose the DSML4ClinicalScore we analysed 89 clinical scores to define the artifacts of this proposed Metamodel. In the end, a practical case study using this DSML is provided to validate the DSML4ClinicalScore Metamodel, and to show how to use the proposal in a clinical situation scenario.
Adalberto Azevedo Jr., Fernando Benedito, Luciano Coutinho, Francisco Silva, Marcos Roriz Junior and Markus Endler. A Mobility Restriction Authoring Tool Approach based on a Domain Specific Modeling Language and Model Transformation. Proceedings of the 21st International Conference on Enterprise Information Systems - Volume 1: ICEIS, 525-534, Heraklion, Crete, Greece, 2019.
There are many situations in which there is a need to monitor the location and behavior of people and/or vehicles in order to detect possible irregularities and control where they are located and how they move, such as in companies, public transportation and public security. In this paper, we present MobCons-AT (Mobility Constraints Authoring Tool), an authoring tool that allows the specification of mobility restrictions rules that must be followed by mobile nodes. Rules are specified through a Domain-Specific Modeling Language (DSML) called MobCons-SL (Mobility Constraints Specification Language). Once specified in MobCons-SL, these rules are automatically transformed into software artifacts that performs the detection of the mobility restrictions violations performed by mobile nodes. This approach allows faster delivery time and lower the cost for the development of software systems aiming the detection of mobility restrictions. This paper also describes the use of MobCons-AT in two case studies, showing its applicability for diverse mobility scenarios.
Received the Best Paper Award in the Multiagent systems section.
Alexandre Heideker, Dener Silva, Ivan Zyrianoff, João Kleinschmidt and Carlos Kamienski. IMAIoT – Infrastructure Monitoring Agent for IoT (In Portuguese). Salão de Ferramentas do SBRC, 2019.
O conceito Internet da Coisas (IoT) é caracterizado pela presença de um número muito grande de dispositivos ligados à Internet, o que inclui ambientes urbanos, industriais e de agricultura. O gerenciamento e monitoramento destes dispositivos, virtuais ou físicos, em múltiplas plataformas de hardware e software, representa um grande desafio. Há soluções disponíveis no mercado, porém, específicas para certos domínios e plataformas e, em sua maioria, proprietárias e pouco personalizáveis. Apresentamos o IMAIoT, uma ferramenta para monitoramento de infraestruturas que utiliza protocolos e arquitetura altamente escalável de IoT para disponibilizar suas métricas. A versatilidade da ferramenta permite monitorar desde máquinas reais em um datacenter até dispositivos com como nós de computação em névoa.
Pedro Rezende, Somayeh Kianpisheh, Roch Glitho and Edmundo Madeira. An SDN-Based Framework for Routing Multi-Streams Transport Traffic Over Multipath Networks. 53rd IEEE International Conference on Communications, 2019.
Multi-stream transport protocols, such as SCTP and QUIC, tackle challenges such as Head of Line (HoL) faced by TCP. They are getting more and more deployed and currently carry more than 7% of the global Internet traffic. However, since these protocols have limited control over the actual routes the streams will take in the network, the streams are generally forwarded through a single and same path, even though there are generally multiple paths available in the network. Consequently, the traffic streams do not fully benefit from the available bandwidth and performance improvement remains limited. Software Defined Networks (SDN) separate control planes and data planes. It offers a complete view of the network to applications and enables network programmability through flexible rules. These rules may be used to ensure that the different streams generated by multi-stream transport protocols follow multiple paths in the network. In this paper, we propose an SDN-based framework for multi-stream transport protocols in multipath networks. The proposed framework provides an interface for applications to specify multi-stream rules. Based on these rules, the framework uses the services offered by the SDN Controller to ensure that the multiple streams go over multiple paths in the network. Experiments performed show that our proposal improves the QoS offered to the end users.
Mayurí Morais and Raphael de Camargo. A Framework for Scalable Data Analysis and Model Aggregation for Public Bus Systems. III Workshop de Computação Urbana (III CoUrb), 2019.
Urban mobility through quality public transportation is one of the major challenges for the consolidation of smart cities. Researchers developed different approaches for improving bus system reliability and information quality, including travel time prediction algorithms, network state evaluations, and bus bunching prevention strategies. The information provided by these approaches are complementary and could be aggregated for better predictions. In this work, we propose the architecture and a present a prototype implementation of a framework that enables the integration of several approaches, which we call models, into scalable and efficient composite models. For instance, travel time prediction models can use estimators of bus position, network state, and bus headways to deliver more accurate and reliable predictions. We evaluate the scalability of the framework, the CPU usage of the framework components, and the predictions of the travel time models. We show that real-time predictions using this framework can be feasible in large metropolitan areas, such as São Paulo city.
Received an honorable mention
Matheus Leal, Flávia Pisani and Markus Endler. Inviolable Presence Registration of Mobile Entities in the ContextNet Middleware (Short Paper). 9th Latin-American Symposium on Dependable Computing (LADC 2019), 2019.
Several applications can benefit from recording information about the places a mobile entity visits and the length of time it spends there (e.g., shoppers, employees, buses, movable equipment, autonomous robots, etc.). In this paper, we present our approach to recording spatio-temporal information in a secure and inviolable way using a Distributed Ledger Technology. So far in this work, we observe that, although sending data to the blockchain is a heavy process, there are ways that this transaction time does not disrupt the flow of new data such as adding these data to a queue. However, this makes the sending process overall longer. We intend to continue this study by testing different blockchain services and comparing their performances.
Received the Best Short Paper Award
Debora Lina Ciriaco, Alexandre Pessoa, Laís Salvador and Renata Wassermann. Semantic Data Integration for Public Health in Brazil. LatinX in AI Research at ICML, 2019.
The lack of semantic information is a big challenge, even in context-driven areas like Healthcare, characterized by established terminologies. Here, semantic data integration is the solution to provide precise information and answers to questions like: What is the care pathway of newborns diagnosed with a congenital anomaly in consequence of congenital syphilis in the city of São Paulo? This project will use a semantic data integration technique, ontology based data integration, to integrate three health databases from the city of São Paulo-Brazil: mortality, live births and hospital information system. It is expected that the integration of public health databases will help to map patient care pathways, predict public resource needs and minimize unnecessary spending.
Jucele França de Alencar Vasconcelos, Edson Norbeto Cáceres, Henrique Mongelli, Siang Wun Song, Frank Dehne and Jayme Luiz Szwarcfiter. New BSP/CGM algorithms for spanning trees. International Journal of High Performance Computing Applications. Volume 33, Issue 3, pp. 441-461, 2019.
Computing a spanning tree (ST) and a minimum spanning tree (MST) of a graph are fundamental problems in Graph Theory and arise as a subproblem in many applications. In this paper, we propose parallel algorithms to these problems. One of the steps of previous parallel MST algorithms relies on the heavy use of parallel list ranking which, though efficient in theory, is very time-consuming in practice. Using a different approach with a graph decomposition, we devised new parallel algorithms that do not make use of the list ranking procedure. We proved that our algorithms are correct, and for a graph G = (V;E), |V| = n and |E| = m, the algorithms can be executed on a BSP/CGM model using O(log p) communications rounds with O((n+m)/p) computation time for each round. To show that our algorithms have good performance on real parallel machines, we have implemented them on GPU (Graphics Processing Unit). The obtained speedups are competitive and showed that the BSP/CGM model is suitable for designing general purpose parallel algorithms.
Gustavo Covas, Eduardo F. Z. Santana and Fabio Kon. Evaluating Exclusive Lanes for Autonomous Vehicle Platoons. 33 rd ECMS International Conference on Modelling and Simulation (ECMS), 2019.
Digital Rails (DR) is a proposal for a system of exclusive lanes intended for autonomous vehicles. This paper presents the evaluation of this system using macroscopic traffic metrics, mainly average travel time. The DR system consists of a network of arterial roads with exclusive lanes where autonomous vehicles can travel in platoons. We
evaluated the impacts of this system on travel time using mesoscopic traffic simulation and real data from the city of São Paulo to create the simulation scenarios. The results show that the proposed system would bring reductions on the average travel time of the city commuters.
Arthur de M. Del Esposte, Eduardo F. Z. Santana, Lucas Kanashiro, Fabio M. Costa, Kelly R. Braghetto, Nelson Lago and Fabio Kon. Design and evaluation of a scalable smart city software platform with large-scale simulations. Future Generation Computer Systems, vol 93, 2019.
Smart Cities combine advances in Internet of Things, Big Data, Social Networks, and Cloud Computing technologies with the demand for cyber–physical applications in areas of public interest, such as Health, Public Safety, and Mobility. The end goal is to leverage the use of city resources to improve the quality of life of its citizens. Achieving this goal, however, requires advanced support for the development and operation of applications in a complex and dynamic environment. Middleware platforms can provide an integrated infrastructure that enables solutions for smart cities by combining heterogeneous city devices and providing unified, high-level facilities for the development of applications and services. Although several smart city platforms have been proposed in the literature, there are still open research and development challenges related to their scalability, maintainability, interoperability, and reuse in the context of different cities, to name a few. Moreover, available platforms lack extensive scientific validation, which hinders a comparative analysis of their applicability. Aiming to close this gap, we propose InterSCity, a microservices-based, open-source, smart city platform that enables the collaborative development of large-scale systems, applications, and services for the cities of the future, contributing to turn them into truly smart cyber–physical environments. In this paper, we present the architecture of the InterSCity platform, followed by a comprehensive set of experiments that evaluate its scalability. The experiments were conducted using a smart city simulator to generate realistic workloads used to assess the platform in extreme conditions. The experimental results demonstrate that the platform can scale horizontally to handle the highly dynamic demands of a large smart city while maintaining low response times. The experiments also show the effectiveness of the technique used to generate synthetic workloads.
Eduardo S. Gama, Roger Immich, and Luiz F. Bittencourt. Towards a Multi-Tier Fog/Cloud Architecture for Video Streaming. 2018 IEEE/ACM International Conference on Utility and Cloud Computing Companion (UCC Companion), 2019.
The video streaming services are already responsible for the majority of the Internet traffic. A good cloud-level architecture partially solves some issues related to the video streaming services. At the same time, however, it introduces new ones such as higher latency and core network congestion. In order to improve on this matter, this work proposes a multi-tier architecture composed of a set of services to video streaming in a fog computing environment. It also takes into consideration classified hierarchical tiers and the ETSI-NFV architecture. The main goal is to design and assess a reliable and high-quality multi-tier services architecture to be used in the Smart City environments. To this end, we introduced a set of video streaming services in the fog/cloud computing, and also proposed how these services may be used to improve the Quality of Experience (QoE) for end-users.
Arthur Selle Jacobs, Ricardo José Pfitscher, Ronaldo Alves Ferreira, and Lisandro Zambenedetti Granville. Refining Network Intents for Self-Driving Networks. ACM SIGCOMM Computer Communication Review, Volume 48, Issue 5, October 2018., 2018.
Recent advances in artificial intelligence (AI) offer an opportunity for the adoption of self-driving networks. However, network operators or home-network users still do not have the right tools to exploit these new advancements in AI, since they have to rely on low-level languages to specify network policies. Intent-based networking (IBN) allows operators to specify high-level policies that dictate how the network should behave without worrying how they are translated into configuration commands in the network devices. However, the existing research proposals for IBN fail to exploit the knowledge and feedback from the network operator to validate or improve the translation of intents. In this paper, we introduce a novel intent-refinement process that uses machine learning and feedback from the operator to translate the operator’s utterances into network configurations. Our refinement process uses a sequence-to-sequence learning model to extract intents from natural language and the feedback from the operator to improve learning. The key insight of our process is an intermediate representation that resembles natural language that is suitable to collect feedback from the operator but is structured enough to facilitate precise translations. Our prototype interacts with a network operator using natural language and translates the operator input to the intermediate representation before translating to SDN rules. Our experimental results show that our process achieves a correlation coefficient squared (i.e., R-squared) of 0.99 for a dataset with 5000 entries and the operator feedback significantly improves the accuracy of our model.
Received the Best Paper Award of the ACM SIGCOMM Workshop on Self-Driving Networks 2018 in Budapest.
Fernanda de Camargo Magano and Kelly Rosa Braghetto. Abstracting Big Data Processing Tools for Smart Cities. 37th IEEE International Symposium on Reliable Distributed Systems, 2018.
Large volumes of data from various sources are generated continuously in cities. The processing and analysis of these data play a key role in the implementation of initiatives for smart cities. In order to process urban Big Data, it is essential to use high-performance tools to accelerate processing and provide quick answers. However, this use is not trivial because Big Data tools are not interoperable and require from their users knowledge of parallel and distributed computing and databases. In this work, we compare popular open-source Big Data processing frameworks and propose a software system to abstract and facilitate their use in smart city applications. The architecture of the system is composed by an interface to specify dataflow models as well as services to interpret these models and instantiate them in different Big Data tools. An implementation of the system on top of a smart city platform is also addressed.
Fernando Freire Scattone and Kelly Rosa Braghetto. A Microservices Architecture for Distributed Complex Event Processing in Smart Cities. 2018 IEEE 37th International Symposium on Reliable Distributed Systems Workshops (SRDSW), 2018.
A considerable volume of data is collected from sensors today and needs to be processed in real time. Complex Event Processing (CEP) is one of the most important techniques developed for this purpose. In CEP, each new sensor measurement is considered an event and new event types can be defined based on other events occurrence. There exists several open-source CEP implementations currently available, but all of them use orchestration to distribute event processing. This kind of architectural organization may harm system resilience, since it relies on a central core (i.e. the orchestrator). Any failures in the core might impact the whole system. Moreover, the core can become a bottleneck on system performance. In this work, a choreography-based microservices architecture is proposed for distributed CEP, in order to benefit from the low coupling and greater horizontal scalability this kind of architecture provides.
Roberto Rodrigues Filho, Marcio Pereira de Sá, Barry Porter, and Fábio M. Costa. Towards emergent microservices for client-tailored design. ARM '18: Proceedings of the 19th Workshop on Adaptive and Reflexive Middleware, 2018.
Contemporary systems are increasingly complex, with both large codebases and constantly changing environments which make them challenging to develop, deploy and manage. We consider two recent efforts to tackle this complexity: microservices and emergent software. Microservices have gained recent popularity in industry, in which monoliths of software are broken down into compositions of single-objective, end-to-end services running on HTTP which can be scaled out on cloud hosting systems. From the research community, the emergent systems concept demonstrates promise in using real-time learning to autonomously compose and optimise software systems from small building blocks, rapidly finding the best behavioural composition to match the current deployment conditions. We argue that emergent software and microservice architectures have strong potential for synergy in complex systems, offering mutually compatible lessons in dealing with complexity via scale-out design and real-time client-tailored behaviour. We explore self-designing microservices, built with emergent software, to demonstrate the complementary boundaries of both concepts – and how future intersections may offer novel architectures that lie at a compelling point between human- and machine-designed systems. We present the conceptual synergy and demonstrate a specific microservice architecture for a smart city example where scoped microservices are continually self-composed according to the demands of the applications and operating environment. For the purpose of reproducibility of the study, we make available all the code used in the evaluation of the proposed approach.
Alexandre Meslin, Noemi Rodriguez, and Markus Endler. A Scalable Multilayer Middleware for Distributed Monitoring and Complex Event Processing for Smart Cities. 2018 IEEE International Smart Cities Conference (ISC2), 2018.
In this paper, we present a hierarchical, distributed, cloud-based, context-aware architecture for collecting, processing and distributing data in a smart city. The architecture we are proposing has three hierarchical levels, and supports complex event processing (CEP) in several of them. At the lower layer, several mobile objects work as interfaces to sensors and actuators and provide processing capability for local filtering and detection. A second level, consisting of gateways and processing nodes, processes information from its locale and sends the data received from the mobile objects to the storage level using the existing network infrastructure. The highest level provides support for structured storage and queries of the information. Applications outside the platform can collect data through the external interface of the highest level. The system is under development using the InterSCity platform in the upper layer, the ContextNet middleware at the middle layer, and the Mobile-Hub application at the lower layer. It currently collects and processes data on buses running in the City of Rio de Janeiro.
Fernanda BJR Dallaqua, Fabio Augusto Faria, Alvaro L Fazenda. Active Learning Approaches for Deforested Area Classification. 31st Conference on Graphics, Patterns and Images (SIBGRAPI), 2018.
The conservation of tropical forests is a social and ecological relevant subject because of its important role in the global ecosystem. Forest monitoring is mostly done by extraction and analysis of remote sensing imagery (RSI) information. In the literature many works have been successful in remote sensing image classification through the use of machine learning techniques. Generally, traditional learning algorithms demand a representative and huge training set which can be an expensive procedure, especially in RSI, where the imagery spectrum varies along seasons and forest coverage. A semi-supervised learning paradigm known as active learning (AL) is proposed to solve this problem, as it builds efficient training sets through iterative improvement of the model performance. In the construction process of training sets, unlabeled samples are evaluated by a user-defined heuristic, ranked and then the most relevant samples are labeled by an expert user. In this work two different AL approaches (Confidence Heuristics and Committee) are presented to classify remote sensing imagery. In the experiments, our AL approaches achieve excellent effectiveness results compared with well-known approaches existing in the literature for two different datasets.
Thales Bandiera Paiva and Routo Terada. Improving the efficiency of a reaction attack on the QC-MDPC McEliece. IEICE Transactions on Fundamentals, Vol. E101-A, No. 10, pp1676-1686, October, 2018.
The QC-MDPC McEliece scheme was considered one of the most promising public key encryption schemes for efficient post-quantum secure encryption. As a variant of the McEliece scheme, it is based on the syndrome decoding problem, which is a hard problem from Coding Theory. Its key sizes are competitive with the ones of the widely used RSA cryptosystem, and it came with an apparently strong security reduction. For three years, the scheme has not suffered major threats, until the end of 2016, at the Asiacrypt, when Guo, Johansson, and Stankovski presented a reaction attack on the QC-MDPC that exploits one aspect that was not considered in the security reduction: the probability of a decoding failure to occur is lower when the secret key and the error used for encryption share certain properties. Recording the decoding failures, the attacker obtains information about the secret key and then use the information gathered to reconstruct the key. Guo et al. presented an algorithm for key reconstruction for which we can point two weaknesses. The first one is that it cannot deal with partial information about the secret key, resulting in the attacker having to send a large number of decoding challenges. The second one is that it does not scale well for higher security levels. To improve the attack, we propose a key reconstruction algorithm that runs faster than Guo’s et al. algorithm, even using around 20% less interactions with the secret key holder than used by their algorithm, considering parameters suggested for 80 bits of security. It also has a lower asymptotic complexity which makes it scale much better for higher security parameters. The algorithm can be parallelized straightforwardly, which is not the case for the one by Guo et al.
Danilo Carastan Santos, David C. Martins-Jr, Siang W. Song, Luiz C. S. Rozante and Raphael Y. de Camargo. A hybrid CPU-GPU-MIC algorithm for minimal hitting set enumeration. Concurrency and Computation: Practice and Experience. Accepted in 2018. Available online, 2018.
We present a hybrid exact algorithm for the Minimal Hitting Set (MHS) Enumeration Problem for highly heterogeneous CPU-GPU-MIC platforms. With several techniques that permit an efficient exploitation of each architecture, low communication cost and effective load balancing, we were able to enumerate MHSs for large instances in reasonable time, achieving good performance and scalability.We obtained speedups of up to 25.32 in comparison with using two six-core CPUs and we also enumerated MHSs for instances with tens of thousands of variables in less than 5 hours. We also evaluated our algorithm with a real-world driven dataset and, with a largeCPU-GPUcluster, we unprecedentedly enumerated in parallel large minimal hitting sets of this dataset in less than 8 hours. These results reinforce the statement that heterogeneous clusters of CPUs, GPUs and MICs can be used efficiently for high-performance computing.
Jucele França de Alencar Vasconcelos, Edson Norbeto Cáceres, Henrique Mongelli and Siang Wun Song. A new efficient parallel algorithm for minimum spanning tree. 30th International Symposisum on Computer Architecture and High Performance Computing (SBAC-PAD). Lyon, France, September 24 - 27, 2018.
In this paper, using the BSP/CGM model, we propose a parallel algorithm and implement it on a GPGPU to obtain a minimum spanning tree of a graph. Previous works for this problem are based on the solution of the list ranking problem which, though efficient in theory, did not produce good speedups in practice. In a later work, based on the idea of computing a structure called strut, we proposed a parallel algorithm under the BSP/CGP model to obtain a minimum spanning tree without using list ranking. It is based on the construction of an auxiliary bipartite graph and uses integer sorting. In this paper, we improve that work in some aspects. The proposed algorithm does not require the computation of the bipartite graph, and the strut construction does not require the sorting algorithm. The efficiency and scalability of the proposed algorithm are verified through experimental results obtained by an implementation on GPGPU.
Ademar T. Akabane, Roger Immich, Richard W. Pazzi, Edmundo R. M. Madeira and Leandro A. Villas. Distributed Egocentric Betweenness Measure as a Vehicle Selection Mechanism in VANETs: A Performance Evaluation Study. Sensors 2018, 18(8), 2731, August, 2018.
In the traditional approach for centrality measures, also known as sociocentric, a network node usually requires global knowledge of the network topology in order to evaluate its importance. Therefore, it becomes difficult to deploy such an approach in large-scale or highly dynamic networks. For this reason, another concept known as egocentric has been introduced, which analyses the social environment surrounding individuals (through the ego-network). In other words, this type of network has the benefit of using only locally available knowledge of the topology to evaluate the importance of a node. It is worth emphasizing that in this approach, each network node will have a sub-optimal accuracy. However, such accuracy may be enough for a given purpose, for instance, the vehicle selection mechanism (VSM) that is applied to find, in a distributed fashion, the best-ranked vehicles in the network after each topology change. In order to confirm that egocentric measures can be a viable alternative for implementing a VSM, in particular, a case study was carried out to validate the effectiveness and viability of that mechanism for a distributed information management system. To this end, we used the egocentric betweenness measure as a selection mechanism of the most appropriate vehicle to carry out the tasks of information aggregation and knowledge generation. Based on the analysis of the performance results, it was confirmed that a VSM is extremely useful for VANET applications, and two major contributions of this mechanism can be highlighted: (i) reduction of bandwidth consumption; and (ii) overcoming the issue of highly dynamic topologies. Another contribution of this work is a thorough study by implementing and evaluating how well egocentric betweenness performs in comparison to the sociocentric measure in VANETs. Evaluation results show that the use of the egocentric betweenness measure in highly dynamic topologies has demonstrated a high degree of similarity compared to the sociocentric approach.
Karima Velasquez, David Perez Abreu, Marcio R. M. Assis, Carlos Senna, Diego F. Aranha, Luiz F. Bittencourt, Nuno Laranjeiro, Marilia Curado, Marco Vieira, Edmundo Monteiro and Edmundo Madeira. Fog orchestration for the Internet of Everything: state-of-the-art and research challenges. Journal of Internet Services and Applications, 9 (14) July, 2018.
Recent developments in telecommunications have allowed drawing new paradigms, including the Internet of Everything, to provide services by the interconnection of different physical devices enabling the exchange of data to enrich and automate people’s daily activities; and Fog computing, which is an extension of the well-known Cloud computing, bringing tasks to the edge of the network exploiting characteristics such as lower latency, mobility support, and location awareness. Combining these paradigms opens a new set of possibilities for innovative services and applications; however, it also brings a new complex scenario that must be efficiently managed to properly fulfill the needs of the users. In this scenario, the Fog Orchestrator component is the key to coordinate the services in the middle of Cloud computing and Internet of Everything. In this paper, key challenges in the development of the Fog Orchestrator to support the Internet of Everything are identified, including how they affect the tasks that a Fog service Orchestrator should perform. Furthermore, different service Orchestrator architectures for the Fog are explored and analyzed in order to identify how the previously listed challenges are being tackled. Finally, a discussion about the open challenges, technological directions, and future of the research on this subject is presented.
Paulo César Ferreira Melo and Fábio Moreira Costa. Model-Driven Mobile CrowdSensing for Smart Cities. WBCI 2018: 1st Brazilian Workshop on Smart Cities, 2018.
Making cities smarter can help improve city services, optimize resource and infrastructure utilization and increase citizens’ quality of life. The Smart Cities connects citizens in novel ways by leveraging the latest advances in information and communication technologies (ICT). The integration of rich sensing capabilities (e.g. camera, microphone, accelerometer, GPS) in today’s mobile devices allows their users to sense their environment. In Mobile CrowdSensing (MCS) the citizens of the Smart City collect, share and jointly use services based on the sensed data. The main challenges for smart city regarding MCS is the heterogeneity of devices and the dynamism of the environment. To overcome these challenges, this paper presents an architecture based on models at runtime (M@rt) to support MCS queries in Smart Cities. This new architecture is an extension of the InterSCity platform to leverage all existing infrastructure.
Diogo Gonçalves, Karima Velasquez, Marilia Curado, Luiz Bittencourt and Edmundo Madeira. Proactive Virtual Machine Migration in Fog Environments. IEEE Symposium on Computers and Communications (ISCC 2018), 2018.
Fog computing provides a low latency access to resources at the edge of the network for resource-constrained devices. The high mobility of some of these devices, such as vehicles, brings great challenges related to resource allocation and management. In order to improve the management of computing resources utilized by mobile users connected to the Fog infrastructure, this paper proposes a virtual machine placement and migration decision model based on mobility prediction. Simulations have shown that moving the virtual machine to a Fog node ahead of the user’s route using the proposed approach can decrease by almost 50% the number of migrations needed by the user. The Fog architecture provides an average latency of about 15 milliseconds for the users’ applications and the proposed approach presents a lower latency compared to a greedy approach for the VM placement problem.
RODRIGO IZIDORO TININI, DANIEL MACEDO BATISTA, and GUSTAVO BITTENCOURT FIGUEIREDO. Energy-Efficient VPON Formation and Wavelength Dimensioning in Cloud-Fog RAN over TWDM-PON. IEEE Symposium on Computers and Communications (ISCC), 2018.
Optical networks are commonly adopted to implement the fronthaul of Cloud-RAN (CRAN) and Hybrid-CRAN (H-CRAN) architectures to support the 5G traffic. The Cloud-Fog RAN (CF-RAN) architecture promotes cloud and local fog processing of baseband signals with the novelty of activating on demand processing capabilities under the Fog Computing and Network Functions Virtualization (NFV) paradigms. Timeand-Wavelength-Division-Multiplexed Passive Optical Networks (TWDM-PON) are used to implement the fronthaul due to the capacity of Virtual-PON (VPON) formation, which can reduce power consumption by allocating as many Remote Radio Heads (RRH) as possible into a single optical channel. However, the TWDM-PON wavelengths must be assigned to the VPONs in an exclusive manner so different VPONs do not share a common wavelength and thus VPONs do not collide on the optical links. In this paper we propose an Energy-Efficient VPON Formation and Wavelength Dimensioning formulation through Integer Linear Programming (ILP) to efficiently form VPONs and dimension the wavelengths so collisions never occurs. Results from the experiments show that the ILP formulation was able to form VPONs and dimension the wavelengths to the network nodes on the most energy-efficient way, achieving gains in the order of 80.27% in comparison to a random VPON formation approach.
Luis Gustavo A. Rodriguez, Julia S. Trazzi, Victor Fossaluza, Rodrigo Campiolo and Daniel M. Batista. Analysis of Vulnerability Disclosure Delays from the National Vulnerability Database. I Workshop de Segurança Cibernética em Dispositivos Conectados (WSCDC) do SBRC, 2018.
The Internet contains vast amounts of data; consequently, hindering information retrieval. Resources, such as the National Vulnerability Database (NVD), have emerged to remedy this situation. Organizations largely depend on the NVD in order to disclose vulnerabilities and collaborate towards a solution. However, there has been evidence that other sources are disclosing vulnerabilities more efficiently and rapidly. The objective of this paper is to evaluate vulnerability disclosure delays from the NVD in order to state its efficiency. Among several findings, we observed that the majority of vulnerabilities are delayed within 1-7 days. Based on these results, we provide recommendations for those who currently rely only on NVD, such as IoT manufacturers and developers.
Mateus Riva, Henrique Donâncio, Felipe Almeida, Gustavo B. Figueiredo, Rodrigo I. Tinini, Roberto M. Cesar Jr. and Daniel M. Batista. An Elastic Optical Network-based Architecture for the 5G Fronthaul. Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), 2018.
In 5G networks, the traffic demands are expected to increase significantly. To deal with this problem, many research efforts focus on TWDM-PON for the fronthaul. However, TWDM-PON suffers from the issue of wasted bandwidth when a demand is smaller than the channel. In order to avoid this inefficiency, we propose an OFDM-PON supported architecture for the CloudRadio Access Network (C-RAN) topology to implement the technology of elastic optical networks into C-RAN. Experiments show that OFDM-PON allows for improved usage of the bandwidth (between 145% and 218% improvement), similar average wait time for requests (average difference below 7%), and similar request loss (average difference below 2%) in comparison to TWDM.
Antonio Deusany de Carvalho Junior and Victor Seiji Hariki and Alfredo Goldman. Sensing Trees in Smart Cities with Open-Design Hardware. IEEE 17th International Symposium on Network Computing and Applications (NCA), 2018.
Tree fall is a major issue in large cities as it may obstruct roads and lead to traffic jams, and even injure people. Following these kind of incidents, monitoring the environment through sensors and Internet of Things technologies emerges as an important preventive approach. Another point is that the net primary productivity has a sensitive relation with trees characteristics including plant respiration and net photosynthesis which are highly sensitive to temperature. The health of the tree can then be monitored through leaf transpiration, sap flow measurement, environment evaluation as these methods offer indicators on any chance of a fall. The solution proposed in this paper includes an open-design hardware setup for monitoring trees in Smart Cities with Internet of Things. The setup is connected to a Smart City platform aiming to facilitate the use by other researchers and botanics, specially. Therefore, we noticed that the daily sensing data results in a huge amount of information that requires a balance between Big Data and Edge Computing approaches to process the whole collected data. The evaluation of the sensing data is presented together with the proposed architecture.
Markus Endler and Francisco Silva e Silva. Past, Present and Future of the ContextNet IoMT Middleware. International Workshop on Very Large Internet of Things - VLIoT, 2018.
The Internet of Things with support to mobility is already transforming many application domains, such as smart cities and homes, environmental monitoring, health care, manufacturing, logistics, public security etc. in that it allows to collect and analyze data from the environment, people and machines, and to implement some form of digital control or steering on these elements of the physical world. But in order to speed the development of applications for the Internet of Mobile Things (IoMT), some middleware is required. This paper summarizes seven years of research and development on the ContextNet middleware aimed at IoMT, discusses what we achieved and what we have learned so far. We also share our vision of possible future challenges and developments in the Internet of Mobile Things.
Diego Vieira Neves, Felipe Cordeiro Alves Dias and Daniel Cordeiro. Using Supervised learning to analyze reliability of crowdsourced bus location data (in Portuguese). WBCI 2018: Primeiro Workshop Brasileiro de Cidades Inteligentes, 2018.
Intelligent Transportation Systems allows sensors and GPS devices to monitor public transport systems in Smart Cities. Capturing and processing this data should, in theory, allow systems to make the public transport more reliable and predictable for the citizens, which would improve the quality of life of the urban population and the environment. Insufficient or low-quality data, nevertheless, may prevent its use on such real-time systems. This work studies the use of data obtained from crowdsourcing as an alternative to augment this data. In order to mitigate the uncertainties introduced by the crowdsourced data, this work proposes a reliability model for crowdsourced data conceived for the São Paulo bus-based public transport system.
Original title: Uso de aprendizado supervisionado para análise de confiabilidade de dados de crowdsourcing sobre posicionamento de ônibus
Diogo M. Gonçalves, Luiz F. Bittencourt and Edmundo M. R. Madeira. Proactive migration of virtual machines for mobile applications in fog computing (in Portuguese). XXXVI Simpósio Brasileiro de Redes de Computadores (SBRC), 2018.
Applications often utilize the cloud as support for processing and storage. The variety of mobile applications also brings a diversity of quality of service requirements, as for example strict delay and availability requirements. Fog computing includes computing services at the edge of the network so as response times can be reduced. In this paper, we present one policy for proactive virtual machine migration in fog computing in order to improve management of computing resources utilized by vehicles connected to this infrastructure. Simulations suggest that using knowledge about the future user’s path can improve the resource management of fog ecosystem, maintaining users’ virtual machine in fog devices as close as possible to the vehicle path. Simulations suggest that the presented policy reduce the total of migration along the user’s path without affecting the quality response time of virtual machines allocated to the fog.
Original title: Migração proativa de máquinas virtuais para aplicações móveis na computação em névoa.
Pedro H. A. Rezende and Edmundo R. M. Madeira. A network slicing component for multi-tenant support in LTE RANs (in Portuguese). XXXVI Simpósio Brasileiro de Redes de Computadores (SBRC), 2018.
5G networks intend to integrate network slicing into their architecture aiming to satisfy the different service levels of an abundant amount of devices. Network Slicing relies on softwarization technologies, such as SDN and NFV, to instantiate slices (virtual networks) on top of the same physical substrate. This work introduces the “Otimizador de Slices”, a component developed as an extension of LTE’s evolved NodeB, responsible to perform network slicing for LTE downlink transmission. This component receives slice’s information from multiple Service Providers and, based on the analysis of these information and on the network state, the proposed component selects the best slice to be scheduled at the moment. Simulations were performed to validate our proposal and expose the benefits that can be obtained by it, such as an enhancement of end user’s QoS experience.
Original title: Um componente de network slicing para o suporte de multi-inquilinos nas RANs do LTE
Melissa Wen, Thatiane de O. Rosa, Mariana C. Souza, Robson P. Aleixo, Camilla Alves, Lucas Sá, Eduardo Felipe Zambom Santana, Fabio Kon. Creation of a Model for Bus Movement Simulation Based on Real Data (in Portuguese). Primeiro Workshop Brasileiro de Cidades Inteligentes, 2018.
The socio-spatial dynamics of a city undergoes constant changes over time. Consequently,the road network and the public transport system need continuous optimization to meet citizen demands. An alternative to reduce costs and impacts on evaluation of solutions is the use of simulators and models consistent with reality. Considering that, we processed vehicle tracking data and bus system planning information of São Paulo to improve the bus movement model used by InterSCSimulator, a highly scalable simulator for smart cities. In this paper, we present a mobility model based on real data from the São Paulo bus service to make the simulator more effective when recreating urban mobility scenarios.
Original title: Criação de Modelo para Simulação de Movimentação de Ônibus a Partir de Dados Reais
Eduardo Felipe Zambom Santana, Lucas Kanashiro, Fabio Kon. Mobility Traces Generation for Vehicular Network Experiments (in Portuguese). Segundo Workshop de Computação Urbana (CoUrb 2018), 2018.
Information and Communication Technologies can improve the traffic in big cities. The deployment of vehicular networks, in which cars can communicate to each other and with the road infrastructure, is an area that is receiving a lot of attention in the last years. However, make tests and experiments in real environments are yet a challenge. This paper presents the development of a mobility trace to the city of São Paulo using InterSCSimulator, a large-scale, open-source Smart City simulator. The trace covers an area of 25 km2 and simulates more than 4 million travels (cars and buses) during a day in the city. The generated trace was tested as input in the NS-3 network simulator.
Original title: Geração de Rastros de Mobilidade para Experimentos em Redes Veiculares
Pedro H. A. Rezende and Edmundo R. M. Madeira. An adaptive network slicing for LTE Radio Access Networks. 10th Wireless Days Conference - WD'18, 2018.
5G mobile systems are envisioned to satisfy the service requirements from a diversity of vertical industries. Network Slicing, which is a promising technology to be integrated into 5G systems, enables multiple virtual networks to be created on top of a physical substrate. These multiple virtual networks (or network slices) are tailored according to the users’ needs. The consolidation of multiple technologies, such as SDN and NFV, provides all the elasticity, programmability and modularity necessary to manage network slices. In this paper, we present a Slice Optimizer component as an extension to LTE’s evolved NodeB to realize the concept of network slicing on LTE Radio Access Networks. This proposed component communicates with an SDN Controller to receive information regarding the network slices and adapts the slices according to the network state. Simulations were performed to validate the Slice Optimizer and highlight the benefits that can be achieved with our proposal, such as the improvement of user’s QoS experience due to a more efficient use of network resources.
Antonio Gonzalez Pastana Lobato, Martin Andreoni Lopez, Igor Jochem Sanz, Alvaro A. Cardenas, Otto Carlos Muniz Bandeira Duarte, Guy Pujolle. An Adaptive Real-Time Architecture for Zero-Day Threat Detection. International Conference on Communications - ICC 2018, 2018.
Attackers create new threats and constantly change their behavior to mislead security systems. In this paper, we propose an adaptive threat detection architecture that trains its detection models in real time. The major contributions of the proposed architecture are: i) gather data about zero-day attacks and attacker behavior using honeypots in the network; ii) process data in real time and achieve high processing throughput through detection schemes implemented with stream processing technology; iii) use of two real datasets to evaluate our detection schemes, the first from a major network operator in Brazil and the other created in our lab; iv) design and development of adaptive detection schemes including both online trained supervised classification schemes that update their parameters in real time and learn zero-day threats from the honeypots, and online trained unsupervised anomaly detection schemes that model legitimate user behavior and adapt to changes. The performance evaluation results show that proposed architecture maintains an excellent trade-off between threat detection and false positive rates and achieves high classification accuracy of more than 90%, even with legitimate behavior changes and zero-day threats.
Eduardo Felipe Zambom Santana, Lucas Kanashiro, Diego Bogado Tomasiello, Fabio Kon and Mariana Gianotti. Analyzing Urban Mobility Carbon Footprint with Large-scale, Agent-based Simulation. 7th International Conference on Smart Cities and Green ICT Systems, 2018.
The growth of cities around the world bring new challenges to urban management and planning. Tools, such as simulators, can help the decision-making process by enabling the understanding of the current situation of the city and comparison of multiple scenarios with regard to changes in the urban infrastructure and in public policy. This paper presents an analysis of mobility parameters, such as distance, cost, travel time, and carbon footprint, for different simulated scenarios in a large metropolis in a developing country. We simulated the scenarios using an open source, large-scale, agent-based Smart City simulator that we developed.
Antonio D. de Carvalho Jr., Alfredo Goldman, Fabio Kon and Marcos Buckeridge. IoTrees: Sensing the city through its trees (in Portuguese). Revista Computação Brasil n. 37, 2018.
A presença de árvores saudáveis no espaço urbano é algo fundamental para a qualidade de vida na cidade. Um projeto de design aberto para monitorar o ambiente por meio das árvores pode dar bons frutos? Esse é o desafio do projeto “Internet of Trees”.
Hugo Resende, Alvaro Luiz Fazenda and Marcos Gonçalves Quiles. Parallel Algorithm for Dynamic Community Detection. 8th Workshop on Applications for Multi-Core Architectures, 2017.
Many real systems can be naturally modeled by complex networks. A complex network represents an abstraction of the system regarding its components and their respective interactions. Thus, by scrutinizing the network, interesting properties of the system can be revealed. Among them, the presence of communities, which consists of groups of densely connected nodes, is a significant one. For instance, a community might reveal patterns, such as the functional units of the system, or even groups correlated people in social networks. Albeit important, the community detection process is not a simple computational task, in special when the network is dynamic. Thus, several researchers have addressed this problem providing distinct methods, especially to deal with static networks. Recently, a new algorithm was introduced to solve this problem. The approach consists of modeling the network as a set of particles inspired by a N-body problem. Besides delivering similar results to state-of-the-art community detection algorithm, the proposed model is dynamic in nature; thus, it can be straightforwardly applied to time-varying complex networks. However, the Particle Model still has a major drawback. Its computational cost is quadratic per cycle, which restricts its application to mid-scale networks. To overcome this limitation, here, we present a novel parallel algorithm using many-core high-performance resources. Through the implementation of a new data structure, named distance matrix, was allowed a massive parallelization of the particles interactions. Simulation results show that our parallel approach, running both traditional CPUs and hardware accelerators based on multicore CPUs and GPUs, can speed up the method permitting its application to large-scale networks.
Danilo Carastan-Santos, David Martins Jr., Luiz Rozante, Siang Song and Raphael de Camargo. A hybrid CPU-GPU-MIC algorithm for hitting set problem. XVIII Simpósio em Sistemas Computacionais de Alto Desempenho - WSCAD 2017. Campinhas, 17 a 20 de outubro de 2017, pp. 196-207, 2017.
We present a hybrid exact algorithm for the Hitting Set Problem (HSP) for highly heterogeneous CPU-GPU-MIC platforms. With several techniques that permit an efficient exploitation of each architecture, low communication cost and effective load balancing, we were able to solve large HSP instances in reasonable time, achieving good performance and scalability. We obtained speedups of up to 25.32 in comparison with using two six-core CPUs and exact HSP solutions for instances with tens of thousands of variables in less than 5 hours. These results reinforce the statement that heterogeneous clusters of CPUs, GPUs and MICs can be used efficiently for high-performance computing.
Rodrigo Izidoro Tinini, Larissa C. M. Reis, Daniel Macêdo Batista, Gustavo Bittencourt Figueiredo, Massimo Tornatore, and Biswanath Mukherjee. Optimal Placement of Virtualized BBU Processing in Hybrid Cloud-Fog RAN over TWDM-PON. Accepted for publication in IEEE Global Communications Conference (GLOBECOM), 2017.
In the context of future Cloud Radio Access Net- works (CRAN), optical networks will play an important role to provide the required transport capacity between cell-sites and processing pools, especially for future 5G scenarios. For instance, using CPRI fronthaul technologies a single antenna element can generate data up to 24.3Gbps even with current configurations of radio transmissions, and it is expected to generate up to Tbps with the advance of technology. So, the transport segment of a 5G network needs to be accurately planned to accommodate all the generated traffic. In this work, we propose the use of a Passive Optical Network (PON) jointly with the emergent paradigms of Fog Computing and Network Function Virtualization (NFV) to energy-efficiently support the high traffic transported in emergent mobile networks in an hybrid architecture called Cloud/Fog RAN (CF-RAN) that allows local and remote baseband processing. We introduce an Integer Linear Programming (ILP) model to schedule the processing of CPRI demands among the processing nodes of the network and turn on or off processing functions on demand. Our approach is able to accommodate demands on the nodes of the network in the most energy efficient way. We compare our results with CRAN and distributed architectures (DRAN) and show that an energy efficient planning can achieve considerable gains in power consumption.
Accepted for publication in IEEE Global Communications Conference (GLOBECOM) 2017
Eduardo Felipe Zambom Santana, Ana Paula Chaves, Marco Aurelio Gerosa, Fabio Kon and Dejan Milojicic. Software Platforms for Smart Cities: Concepts, Requirements, Challenges, and a Unified Reference Architecture. ACM Computing Surveys, 50 (6), January, 2017.
Making cities smarter help improve city services and increase citizens’ quality of life. Information and communication technologies (ICT) are fundamental for progressing towards smarter city environments. Smart City software platforms potentially support the development and integration of Smart City applications. However, the ICT community must overcome current significant technological and scientific challenges before these platforms can be widely used. This paper surveys the state-of-the-art in software platforms for Smart Cities. We analyzed 23 projects with respect to the most used enabling technologies, as well as functional and non-functional requirements, classifying them into four categories: Cyber-Physical Systems, Internet of Things, Big Data, and Cloud Computing. Based on these results, we derived a reference architecture to guide the development of next-generation software platforms for Smart Cities. Finally, we enumerated the most frequently cited open research challenges, and discussed future opportunities. This survey gives important references for helping application developers, city managers, system operators, end-users, and Smart City researchers to make project, investment, and research decisions.
F. M. Costa, K. A. Morris, F. Kon and P. J. Clarke. Model-Driven Domain-Specific Middleware. 37th IEEE International Conference on Distributed Computing Systems (ICDCS), 2017.
Middleware was introduced to facilitate the development of sophisticated applications based on a uniform methodology and industry standards. However, early research and practice suggested that no one-size-fits-all approach was suitable for all application domains and scenarios. This gave rise to industry initiatives to standardize domain-specific middleware services and profiles, as well as research efforts on configurable, reflective, and adaptive middleware. The industry’s approach led to easy deployment, although with a level of flexibility limited by the extent of existing profiles. The approach of the research community, on the other hand, enabled high flexibility, allowing any middleware configuration to be defined. Nevertheless, creating sound configurations using this approach is a challenging task, limiting the target audience to expert engineers. As a consequence, both initiatives do not scale with the current proliferation of specialized application domains. In this paper, we target this problem with an approach that leverages model-driven engineering for the construction of domain-specific middleware platforms. A set of high-level, yet expressive, building blocks is defined in the form of a metamodel, which is used to create models that specify the desired middleware configuration. We argue that this approach enables the rapid development of middleware platforms to match the proliferation of application domains, at the same time as it does not require per-application middleware construction or even highly skilled middleware engineers. We present the current state of our research and discuss research directions to fully realize the approach.
João Eduardo Ferreira, José Antônio Visintin, Jun Okamoto Jr. and Calton Pu. Smart Services: A Case Study on Smarter Public Safety by a Mobile App for University of São Paulo. The 2017 IEEE Conference on Smart City Innovations (IEEE SCI), 2017.
The University of São Paulo has faced public safety issues a long the years. Due to its size preventive surveillance by the campus security guard cannot be effective all the times. In order to bring a safer environment to its public of more than 60,000 daily users, a smart public safety system is being developed. This is a complex system, spread throughout all the University’s campuses. It is composed of a smart surveillance cameras system, a back office system with a workflow engine and a mobile application within a collaborative concept. The smart cameras system is being deployed and the mobile application together with the back office system is being used this past year with satisfactory results. The mobile application is the user entry point to report several security and campus maintenance related issues that are automatically directed to the responder team for immediate action in the case of security or enters an automated workflow engine in the case of campus maintenance. This paper presents the structure created towards achieving a smarter public safety environment, details of the implementation, presents statistical data collected by the system showing its effectiveness and concludes showing the improvements introduced in the university community safety and welfare.
Danilo Carastan Santos, Raphael Y. de Camargo, David C. Martins-Jr, Siang W. Song and Luiz C. S. Rozante. Finding exact hitting set solutions for systems biology applications using heterogeneous GPU clusters. Future Generation Computer Systems. Elsevier. Vol. 67, pp. 418-429., 2017.
The Systems Biology field presents several complex combinatorial problems that can be in part reduced to an instance of the Hitting Set Problem (HSP), which is NP-Hard. These reduced problems often come with a large amount of data that needs to be processed, such as gene expression profiles, resulting in prohibitive computational costs for finding the exact solutions. There are some proposals to obtain exact solutions for HSP, including an approach which uses GPUs. However, such an approach is not scalable for real input sizes (thousands of variables). We propose a novel algorithm for solving HSP instances with thousands of variables by using: (i) clause sorting, which enables the efficient discarding of non-solution candidates, (ii) parallel generation and evaluation of candidate solutions through the use of GPUs, and (iii) support for multiple GPUs. To permit the execution on heterogeneous clusters, we determine the minimum kernel size that does not incur extra overhead and distribute tasks among available GPUs on demand. Our experimental results show that the combination of these techniques results in a speedup of 118.5, when using eight NVIDIA Tesla K20c in comparison with a ten-core Intel Xeon E5-2690 processor. Consequently, our algorithm can enable the usage of exact algorithms for solving the Hitting Set problem and applying it to real world problems.
Leissi Margarita Castañeda Leon and Paulo André Vechiatto De Miranda. Multi-Object Segmentation by Hierarchical Layered Oriented Image Foresting Transform. 30th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2017.
This paper introduces a new method for multi-object segmentation in images, named as Hierarchical Layered Oriented Image Foresting Transform (HLOIFT). As input, we have an image, a tree of relations between image objects, with the individual high-level priors of each object coded in its nodes, and the objects’ seeds. Each node of the tree defines a weighted digraph, named as layer. The layers are then integrated by the geometric interactions, such as inclusion and exclusion relations, extracted from the given tree into a unique weighted digraph, named as hierarchical layered digraph. A single energy optimization is performed in the hierarchical layered weighted digraph by Oriented Image Foresting Transform (OIFT) leading to globally optimal results satisfying all the high-level priors. We evaluate our framework in the multi-object segmentation of medical and synthetic images, obtaining results comparable to the state-of-the-art methods, but with low computational complexity. Compared to multi-object segmentation by min-cut/max-flow algorithm, our approach is less restrictive, leading to globally optimal results in more general scenarios.
Jucele Vasconcelos, Edson Caceres, Henrique Mongelli and Siang Wun Song. A parallel algorithm for minimum spanning tree on GPU. International Symposium on Computer Architecture and High Performance Computing Workshops (WAMCA 2017), 2017.
Computing a minimum spanning tree (MST) of a graph is a fundamental problem in Graph Theory and arises as a subproblem in many applications. In this paper, we propose a parallel MST algorithm and implement it on a GPU (Graphics Processing Unit). One of the steps of previous parallel MST algorithms is a heavy use of parallel list ranking. Besides the fact that list ranking is present in several parallel libraries, it is very time-consuming. Using a different graph decomposition, called strut, we devised a new parallel MST algorithm that does not make use of the list ranking procedure. Based on the BSP/CGM model we proved that our algorithm is correct and it finds the MST after O(log p) iterations (communication and computation rounds). To show that our algorithm has a good performance onreal parallel machines, we have implemented it on GPU. The way that we have designed the parallel algorithm allowed us to exploit the computing power of the GPU. The efficiency of the algorithm was confirmed by our experimental results. The tests performed show that, for randomly constructed graphs, with vertex numbers varying from 10,000 to 30,000 and density between 0.02 and 0.2, the algorithm constructs an MST in a maximum of six iterations. When the graph is not very sparse, our implementation achieved a speedup of more than 50, for some instances as high 296, over a minimum spanning tree sequential algorithm previously proposed in the literature.
Received the best paper award.
Arthur de M. Del Esposte, Fabio Kon, Fabio M. Costa and Nelson Lago. InterSCity: A Scalable Microservice-based Open Source Platform for Smart Cities. 6th International Conference on Smart Cities and Green ICT Systems, 2017.
Smart City technologies emerge as a potential solution to tackle common problems in large urban centers by using city resources efficiently and providing quality services for citizens. Despite the various advances in middleware technologies to support future smart cities, there are no universally accepted platforms yet. Most of the existing solutions do not provide the required flexibility to be shared across cities. Moreover, the extensive use and development of non-open-source software leads to interoperability issues and limits the collaboration among R&D groups. In this paper, we explore the use of a microservices architecture to address key practical challenges in smart city platforms. We present InterSCity, a microservice-based open source smart city platform that aims at supporting collaborative, novel smart city research, development, and deployment initiatives. We discuss how the microservice approach enables a flexible, extensible, and loosely coupled architecture and present experimental results demonstrating the scalability of the proposed platform.
Received the Best Student Paper Award
Eduardo F. Z. Santana, Nelson Lago, Fabio Kon and Dejan S. Milojicic. InterSCSimulator: Large-Scale Traffic Simulation in Smart Cities using Erlang. 18th Workshop on Multi-agent-based Simulation, 2017.
Large cities around the world face numerous challenges to guarantee the quality of life of its citizens. A promising approach to cope with these problems is the concept of Smart Cities, of which the main idea is the use of Information and Communication Technologies to improve city services. Being able to simulate the execution of Smart Cities scenarios would be extremely beneficial for the advancement of the field. Such a simulator, like many others, would need to represent a large number of various agents (e.g. cars, hospitals, and gas pipelines). One possible approach for doing this in a computer system is to use the actor model as a programming paradigm so that each agent corresponds to an actor. The Erlang programming language is based on the actor model and is the most commonly used implementation of it. In this paper, we present the first version of InterSCSimulator, an open-source, extensible, large-scale Traffic Simulator for Smart Cities developed in Erlang, capable of simulating millions of agents using a real map of a large city. Future versions will be extended to address other Smart City domains.
Daniel Macêdo Batista, Alfredo Goldman, Roberto Hirata Jr., Fabio Kon, Fabio M. Costa and Markus Endler. InterSCity: Addressing Future Internet Research Challenges for Smart Cities. 7th IEEE International Conference on Network of the Future, 2016.
The Future Internet will integrate large-scale systems constructed from the composition of thousands of distributed services, while interacting directly with the physical world via sensors and actuators, which compose the Internet of Things. This Future Internet will enable the realization of the Smart Cities vision, in which the urban infrastructure will be used to its fullest extent to offer a better quality of life for its citizens. Key to the efficient and effective realization of Smart Cities is the scientific and technological research covering the multiple layers that make up the Internet. This paper discusses the research challenges and initiatives related to Future Internet and Smart Cities in the scope of the InterSCity project. The challenges and initiatives are organized in three fronts: (1) Networking and High-Performance Distributed Computing; (2) Software Engineering for the Future Internet; and (3) Analysis and Mathematical Modeling for the Future Internet and Smart Cities. InterSCity aims at developing an integrated open-source platform containing all the major building blocks for the development of robust, integrated, sophisticated applications for the smart cities of the future.
Fabio Kon, Nelson Lago and Roberto Speicys Cardoso. Smart Cities for better quality of life (in Portuguese). Artigo opinativo publicado no Jornal O Estado de São Paulo (edição de 14 de outubro), 2016.
A preocupação atual com os recursos tecnológicos na gestão urbana é a chave para a melhoria da vida nas cidades e para a cidadania nas décadas vindouras, com foco em:
Original title: Cidades Inteligentes por mais Qualidade de Vida
Fabio Kon and Eduardo Felipe Zambom Santana. Smart Cities: Concepts, platforms, and challenges (in Portuguese). Jornadas de Atualização em Informática (JAI), 2016.
With the growth of the urban population, the infrastructural problems and limited resources of thousands of cities around the world affect negatively the lives of billions of people. Making cities smarter can help improving city services and increasing the quality of life of their citizens. Information and communication technologies (ICT) are a fundamental means to move towards smarter city environments. Using a software platform on top of which Smart City applications can be deployed facilitates the development and integration of such applications. However, there are, currently, significant technological and scientific challenges that must be faced by the ICT community before these platforms can be widely used. This chapter presents the state-of-the-art and the state-of-the-practice in Smart Cities environments. We analyze eleven smart city platforms and eleven smart city initiatives with respect to the most used enabling technologies as well as functional and non-functional requirements. Finally, we enumerate open research challenges and comment on our vision for the area in the future.
Original title: Cidades Inteligentes: Conceitos, plataformas e desafios
