Jekyll2026-05-27T14:33:57+00:00https://bps90.github.io/feed.xmlBruno P. S.This is a Bruno Pereira dos Santos home page!Bruno Pereira dos SantosA Privacy-Preserving Contact Tracing System based on a Publish-Subscribe Model2024-08-11T00:00:00+00:002024-08-11T00:00:00+00:00https://bps90.github.io/papers/paper-44In the context of the COVID-19 pandemic, using contact-tracking apps and measures such as social isolation and mask-wearing has emerged as an efficient strategy to mitigate the spread of the virus. Nonetheless, these apps have raised privacy concerns. This paper introduces a technique for enhancing Privacy in contact-tracing systems while preserving the data for research purposes. The contact-tracing system employs a unique identifier signed with a key associated with the application and the user. In this system, mobile devices serve as sensors sending beacons, actively detecting nearby devices, and transmitting the identifiers of surrounding contacts to a cloud-based platform. When a user reports a positive COVID-19 diagnosis, a dedicated web service identifies and tracks the identifiers associated with at-risk contacts. The system uses a topic-based publish-subscribe broker, and each identifier represents an individual topic to abstract contact communication and disseminate alert messages. To assess the system’s efficacy, we conducted a use case with twenty volunteers using the mobile application for two weeks, representing a small university campus. The quantitative results of the use case demonstrated the system’s capability of analyzing potential virus transmission and observing user’s social interactions while maintaining their anonymity.

Please cite:

@article{da2024privacy,
  title={A Privacy-Preserving Contact Tracing System based on a Publish-Subscribe Model},
  author={da Silva, Mikaella F and Santos, Bruno P and Rettore, Paulo HL and Mota, Vin{\'\i}cius FS},
  journal={Journal of Internet Services and Applications},
  volume={15},
  number={1},
  pages={244--257},
  year={2024}
}

Mikaella F. da Silva, Bruno P. Santos, Paulo H. L. Rettore, Vinícius F. S. Mota.

Founding agencies: CNPq/CAPES/FAPEMIG.
]]>Bruno Pereira dos SantosUma abordagem Q-Learning para escalonamento dinâmico de comunicação do TSCH2024-05-20T00:00:00+00:002024-05-20T00:00:00+00:00https://bps90.github.io/papers/paper-43Uma rede mesh 6TiSCH provê conectividade IPv6 usando enlaces IEEE 802.15.4 governados pelo Time Slotted Channel Hopping (TSCH). Essencialmente, o TSCH promete baixo consumo de energia e alta confiabilidade através do escalonamento de tempo e salto de canais de comunicação, respectivamente. Entretanto, o 6TiSCH não define as políticas para construir e manter o cronograma de comunicação. Este trabalho propõe uma nova função de escalonamento de comunicação que utiliza Q-Learning, que leva em consideração a variação no tráfego da rede, o consumo de energia e o tamanho da fila de mensagens a serem enviadas pelo dispositivo. Comparamos a abordagem proposta com Minimal Scheduling Function (MSF), o escalonador de facto usada na literatura. Os experimentos mostram que a abordagem proposta reduz a latência da comunicação, enquanto mantém a confiabilidade alta, o consumo de energia e tempo de junção da rede baixos, mostrando que a abordagem é promissora.

Please cite:

@inproceedings{cardel2024uma,
 author = {Victor Cardel and Paulo Rettore and Bruno Santos},
 title = { Uma abordagem Q-Learning para escalonamento dinâmico de comunicação do TSCH},
 booktitle = {Anais do XLII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos},
 location = {Niterói/RJ},
 year = {2024},
 keywords = {},
 issn = {2177-9384},
 pages = {113--126},
 publisher = {SBC},
 address = {Porto Alegre, RS, Brasil},
 doi = {10.5753/sbrc.2024.1275},
 url = {https://sol.sbc.org.br/index.php/sbrc/article/view/29787}
}

Victor Cardel, Paulo Rettore, Bruno Santos

Founding agencies: CNPq/CAPES/FAPEMIG.
]]>Bruno Pereira dos SantosTowards a Cyber Defense System in Software-Defined Tactical Networks2024-04-23T00:00:00+00:002024-04-23T00:00:00+00:00https://bps90.github.io/papers/paper-42This study investigates the robustness of a Software-defined Networking (SDN) controller when confronted with a Distributed Denial-of-Service (DDOS) attack in a tactical environment. A proactive defense mechanism is introduced to detect and respond to a flooding of “packet-in” requests, triggering a response once the network features indicate an anomaly. The methodology consists of two components: the Cyber Defense Agent (CDA), consisting of monitoring, feature engineering, detection, and responses, and the Cyber Attack Agent (CAA), including the preparation, execution, and evaluation of the attack. The CDA monitors all the IP flows from the SDN controller and processes four main features such as the average number of “packet-in” requests, the response time to these requests, the entropy of IP addresses and ports for source and destination, and “packet-in” requests per switch to identify compromised switches. All the components were emulated and tested, collecting quantitative evidence to demonstrate the effectiveness of both agents.

Please cite:

@article{Kloth2024TowardsAC,
  title={Towards a Cyber Defense System in Software-Defined Tactical Networks},
  author={Sean Kloth and Paulo H. L. Rettore and Philipp Zi{\ss}ner and Bruno P. Santos and Peter Sevenich},
  journal={2024 International Conference on Military Communication and Information Systems (ICMCIS)},
  year={2024},
  pages={1-8},
  url={https://api.semanticscholar.org/CorpusID:270260554}
}

Sean Kloth, Paulo H. L. Rettore, Philipp Zißner, Bruno P. Santos, P. Sevenich

Founding agencies: CNPq/CAPES/FAPEMIG.
]]>Bruno Pereira dos SantosImproving Robustness and Reducing Control Overhead via Dynamic Clustering in Tactical SDN2023-10-30T00:00:00+00:002023-10-30T00:00:00+00:00https://bps90.github.io/papers/paper-41This study presents a dynamic clustering approach to address the challenges of managing modern and dynamic tactical communication using diverse radio links in Software-Defined Tactical Networks (SDTNs). State-of-the-art conventional Software-Defined Networking (SDN) protocols, which rely on centralized controllers, are unsuitable for tactical scenarios due to their inherent demands for high-throughput, low-latency control planes, and static nodes. To enable SDTN, we propose a clustering solution designed to distribute network nodes across multiple remote controllers, thereby reducing the control message overhead created by the OpenFlow protocol. Moreover, we propose a flexible controller assignment strategy to dynamically balance the network load during runtime and improve network robustness using backup controllers. Our comparative analysis suggests a significant reduction of control overhead across heterogeneous topologies with VHF and UHF links using our clustering solution. Furthermore, we replicate a real-world scenario by emulating a convoy of military vehicles demonstrating the effective distribution of low control overhead among the controllers and maintaining robust network connectivity, even in the event of a controller failure.

Please cite:

@INPROCEEDINGS{zibner2023improving,
  author={Zißner, Philipp and Rettore, Paulo H. L. and Santos, Bruno P. and Lopes, Roberto Rigolin F. and Loevenich, Johannes F. and Sevenich, Peter},
  booktitle={MILCOM 2023 - 2023 IEEE Military Communications Conference (MILCOM)}, 
  title={Improving Robustness and Reducing Control Overhead via Dynamic Clustering in Tactical SDN}, 
  year={2023},
  volume={},
  number={},
  pages={491-496},
  keywords={Protocols;Runtime;Network topology;UHF measurements;Radio links;Robustness;Topology;Software-defined Tactical Network;Control Overhead;Clustering},
  doi={10.1109/MILCOM58377.2023.10356288}
}

Philipp Zißner; Paulo H. L. Rettore; Bruno P. Santos; Roberto Rigolin F. Lopes; Johannes F. Loevenich; Peter Sevenich

Founding agencies: CNPq/CAPES/FAPEMIG.
]]>Bruno Pereira dos SantosA Mobility Model for The Internet of Things2023-10-23T00:00:00+00:002023-10-23T00:00:00+00:00https://bps90.github.io/papers/paper-40This study introduces a novel mobility model designed for the Internet of Things (IoT). While the study of movement patterns is crucial for designing and evaluating mobile solutions in the IoT, there is a lack of focus on the mobility of IoT objects. In this work, Small World In Motion (SWIM), a model that mimetic human mobility patterns, was extended to reproduce the mobility of IoT objects. We establish a relationship between objects and their locomotion characteristics based on two key premises. Firstly, certain IoT devices exhibit movement patterns similar to humans (e.g., smartphones). Secondly, some devices are predominantly stationary (e.g., smart TVs). Our model is open-source code, enabling further research and development. We conduct a comprehensive analyze the output mobility model trace, considering spatial, temporal, and social aspects. Additionally, we propose adjustments to the existing literature taxonomy to suitably accommodate the proposed model.

Please cite:

@inproceedings{webmedia,
 author = {Talita Alves and Paulo Rettore and Bruno Santos},
 title = { A Mobility Model of The Internet of Things},
 booktitle = {Proceedings of the 29th Brazilian Symposium on Multimedia and the Web},
 location = {Ribeirão Preto/SP},
 year = {2023},
 keywords = {},
 issn = {0000-0000},
 pages = {221–229},
 publisher = {SBC},
 address = {Porto Alegre, RS, Brasil},
 url = {https://sol.sbc.org.br/index.php/webmedia/article/view/25883}
}

Talita Alves, Paulo Rettore, Bruno Santos

Founding agencies: CNPq/CAPES/FAPEMIG.
]]>Bruno Pereira dos SantosDataFITS: A Heterogeneous Data Fusion Framework for Traffic and Incident Prediction2023-06-12T00:00:00+00:002023-06-12T00:00:00+00:00https://bps90.github.io/papers/paper-39This paper introduces DataFITS (Data Fusion on Intelligent Transportation System), an open-source framework that collects and fuses traffic-related data from various sources, creating a comprehensive dataset. We hypothesize that a heterogeneous data fusion framework can enhance information coverage and quality for traffic models, increasing the efficiency and reliability of Intelligent Transportation System (ITS) applications. Our hypothesis was verified through two applications that utilized traffic estimation and incident classification models. DataFITS collected four data types from seven sources over nine months and fused them in a spatiotemporal domain. Traffic estimation models used descriptive statistics and polynomial regression, while incident classification employed the k-nearest neighbors (k-NN) algorithm with Dynamic Time Warping (DTW) and Wasserstein metric as distance measures. Results indicate that DataFITS significantly increased road coverage by 137% and improved information quality for up to 40% of all roads through data fusion. Traffic estimation achieved an R2 score of 0.91 using a polynomial regression model, while incident classification achieved 90% accuracy on binary tasks (incident or non-incident) and around 80% on classifying three different types of incidents (accident, congestion, and non-incident).

Please cite:

@ARTICLE{zibner2023datafits,
  author={Zißner, Philipp and Rettore, Paulo H. L. and Santos, Bruno P. and Loevenich, Johannes F. and Lopes, Roberto Rigolin F.},
  journal={IEEE Transactions on Intelligent Transportation Systems}, 
  title={DataFITS: A Heterogeneous Data Fusion Framework for Traffic and Incident Prediction}, 
  year={2023},
  volume={24},
  number={10},
  pages={11466-11478},
  keywords={Data integration;Data models;Sensors;Spatiotemporal phenomena;Correlation;Transportation;Social networking (online);Intelligent transportation systems;heterogeneous data fusion;traffic estimation;incident classification},
  doi={10.1109/TITS.2023.3281752}
  }

Philipp Zißner; Paulo H. L. Rettore; Bruno P. Santos; Johannes F. Loevenich; Roberto Rigolin F. Lopes

Founding agencies: CNPq/CAPES/FAPEMIG.
]]>Bruno Pereira dos SantosUtilizando aprendizado por representação para a classificação de laços sociais da IoT2022-11-07T00:00:00+00:002022-11-07T00:00:00+00:00https://bps90.github.io/papers/paper-33A Internet of Things (IoT) tem sido marcada pelas interações entre dispositivos que cooperam para realizar atividades. A partir deste ambiente cibernético e conectado, um possível paradigma derivado é o Social IoT (SIoT), onde múltiplos tipos de relacionamentos e confiabilidade podem ser estabelecidos entre dispositivos. Neste cenário, abordamos as questões de como modelar laços sociais em IoT e na proposição de modelos para, automaticamente, classificar e predizer relações em SIoT. Este artigo propõe a utilização de aprendizado por representação para classificar diferentes tipos de laços sociais em SIoT. Para isso, utiliza-se como estratégias para classificação Graph Neural Networks (GNN) ou Algoritmos Tradicionais de Classificação (ATC). Em nossos experimentos, GNN é rápido na etapa de treinamento e apresenta métricas F1-{macro, micro} de 0.61 e 0.88, respectivamente. Ao usar ATC, o treinamento é 121× até 11.235× mais lento que GNN, ao passo que as métricas F1-score alcançam 0.86 e 0.95, respetivamente.

Please cite:

@inproceedings{junior2022utilizando,
 author = {Jamisson J. Júnior and Thiago Figueiredo and Ramon Lopes and Luiz Torres and Bruno Santos},
 title = { Utilizando aprendizado por representação para a classificação de laços sociais da IoT},
 booktitle = {Anais do VI Workshop de Computação Urbana},
 location = {Fortaleza},
 year = {2022},
 keywords = {},
 issn = {2595-2706},
 pages = {112--125},
 publisher = {SBC},
 address = {Porto Alegre, RS, Brasil},
 doi = {10.5753/courb.2022.223493},
 url = {https://sol.sbc.org.br/index.php/courb/article/view/21448}
}

Jamisson J. Júnior, Thiago Figueiredo, Ramon Lopes, Luiz Torres, Bruno Santos

Founding agencies: CNPq/CAPES/FAPEMIG.
]]>Bruno Pereira dos SantosPolarização em Redes Sociais: Conceitos, Aplicações e Desafios2022-11-07T00:00:00+00:002022-11-07T00:00:00+00:00https://bps90.github.io/papers/paper-34A polarização aferida em redes sociais tem refletido a predisposição da sociedade para o embate de ideias e o recente incentivo a rivalidade política no mundo. Deste contexto, diversas questões são levantadas, tais como: As pessoas estão se tornando mais polarizadas? Em caso afirmativo, quais são os impactos positivos e negativos das redes sociais neste processo? É possível medir polarização nas redes sociais? Neste minicurso, o objetivo é discutir o atual cenário de pesquisa em polarização, através de uma visão crítica geral da área, seus desafios e oportunidades. Para tal, os principais conceitos e definições sobre polarização serão apresentados. Assim como o fluxo de coleta dados sobre polarização, seu processamento, análises e extração de conhecimento. Para este último, será dado enfoque especial em uma proposta de taxonomia para métricas de polarização em redes sociais. Ao final, exercitaremos nossos conhecimentos em uma análise prática de polarização aplicada ao tópico Covid-19.

Please cite:

@article{hott2022polarizaccao,
  title={Polariza{\c{c}}ao em redes sociais: Conceitos, aplica{\c{c}}oes e desafios},
  author={Hott, Bruno and Santos, Bruno P and Loures, T{\'u}lio Corr{\^e}a and Benevenuto, Fabr{\'\i}cio and Vaz-de-Melo, Pedro OS},
  journal={Sociedade Brasileira de Computa{\c{c}}{\~a}o},
  year={2022}
}

Bruno Hott, Bruno P. Santos, Túlio Corrêa Loures, Fabrício Benevenuto, e Pedro O.S. Vaz-de-Melo

Founding agencies: CNPq/CAPES/FAPEMIG.
]]>Bruno Pereira dos SantosOTALab: um ambiente de experimentação remota de protocolos e aplicações em Internet das Coisas2022-07-23T00:00:00+00:002022-07-23T00:00:00+00:00https://bps90.github.io/papers/paper-32Este artigo apresenta o OTALab, uma ferramenta para criação e implantação de ambientes de experimentação de aplicações de Internet of Things (IoT) em microcontroladores de baixo custo. O OTALab visa a rápida implantação e configuração de um testbed de ambiente de experimentação. O OTALab possui dois perfis de usuários: administradores e experimentadores. Para os primeiros, o OTALab expõe uma interface de administração capaz de adicionar/remover dispositivos IoT, serviços e funcionalidades ao sistema. Já os experimentadores podem visualizar os serviços disponíveis em cada dispositivo e enviar seu próprio código aos dispositivos via linha de comando ou interface Web. O OTALab recebe o código-fonte, compila-o para o microcontrolador específico e atualiza o firmware do dispositivo através do paradigma Over the Air (OTA). O OTALab é composto por uma biblioteca de microcontroladores, um servidor de gerenciamento de dispositivos e uma aplicação Web. A ferramenta pode ser instanciada localmente ou de forma distribuída, melhorando sua flexibilidade.

Please cite:

@inproceedings{cussuol2022otalab,
 author = {Enzo Cussuol and Lucas Sachetti and Bruno Santos and Vinicius Mota},
 title = { OTALab: um ambiente de experimentação remota de protocolos e aplicações em Internet das Coisas},
 booktitle = {Anais Estendidos do XL Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos},
 location = {Fortaleza/CE},
 year = {2022},
 keywords = {},
 issn = {2177-9384},
 pages = {73--80},
 publisher = {SBC},
 address = {Porto Alegre, RS, Brasil},
 doi = {10.5753/sbrc_estendido.2022.223464},
 url = {https://sol.sbc.org.br/index.php/sbrc_estendido/article/view/21421}
}

Enzo B. Cussuol1, Lucas L. S. Sachetti1, Bruno P. Santos2, Vinicius F. S. Mota

Founding agencies: CNPq/CAPES/FAPEMIG.
]]>Bruno Pereira dos SantosRoad Traffic Density Estimation Based on Heterogeneous Data Fusion2022-06-30T00:00:00+00:002022-06-30T00:00:00+00:00https://bps90.github.io/papers/paper-30This investigation starts with the hypothesis that fusing heterogeneous data sources can increase the data coverage and improve the accuracy of traffic-related applications in Intel-ligent Transportation Systems (ITS). Therefore, we designed (i) a Data Fusion on Intelligent Transportation Systems (DataFITS) framework that allows collecting data from numerous sources and fusing them according to spatial and temporal criteria; (ii) a traffic estimation method that groups road segments into regions, identify correlations between them, and measure the traffic distribution to estimate traffic. As a result, DataFITS increased by 130% the number of road segments coverage and enhanced, by fusion process, around 35% of road overlapping data sources. We evaluate the traffic estimation of the 15 most correlated regions, where the fused data together with correlated areas resulted in the best traffic estimation accuracy by reaching up to 40% in some cases and 9% on average.

Please cite:

@INPROCEEDINGS{zibner2022road,
  author={Zißner, Philipp and Rettore, Paulo H. L. and Santos, Bruno P. and Lopes, Roberto Rigolin F. and Sevenich, Peter},
  booktitle={2022 IEEE Symposium on Computers and Communications (ISCC)}, 
  title={Road Traffic Density Estimation Based on Heterogeneous Data Fusion}, 
  year={2022},
  volume={},
  number={},
  pages={1-6},
  keywords={Measurement;Correlation;Roads;Soft sensors;Urban areas;Estimation;Data integration;ITS;Smart Cities;Traffic estimation;Data Fusion},
  doi={10.1109/ISCC55528.2022.9912917}
}
Founding agencies: CNPq/CAPES/FAPEMIG.
]]>Bruno Pereira dos Santos