Avaliação da Latência em Sistemas de Monitoramento Veicular Embarcado com Aprendizado de Máquina
Resumo
O avanço das tecnologias automotivas e a popularização dos dispositivos OBD-II (On-Board Diagnostics) têm viabilizado a coleta de dados veiculares em tempo real, favorecendo aplicações em diagnóstico e análise de desempenho. Apesar da padronização do protocolo OBD-II, a forma como ele é implementado em diferentes hardwares e veículos pode impactar significativamente a latência na comunicação com a Unidade de Controle Eletrônico (ECU). Este trabalho investiga a influência dessas variabilidades sobre a eficiência da coleta de dados e o desempenho de algoritmos de aprendizado de máquina embarcado em um aplicativo móvel. Por meio de um estudo de caso com múltiplos modelos de veículos e dispositivos de coleta, foram analisados os tempos de resposta das ECUs e os tempos de execução dos algoritmos embarcados, considerando diferentes contextos de operação. Os resultados demonstram que o desempenho do sistema é sensível às características do veículo e do hardware de interface, evidenciando a necessidade de ajustes nos parâmetros de aquisição para garantir a confiabilidade e a precisão dos dados processados em tempo real. As análises contribuem para o aprimoramento de soluções embarcadas voltadas à mobilidade inteligente e ao monitoramento veicular.
Palavras-chave:
OBD-II, Latência, ECU, Aprendizagem de Máquina Embarcada, Tempo Real
Referências
Amaral, M., Medeiros, M., Andrade, M., Flores, T., Silva, M., and Silva, I. (2024). TinyML implementation and optimization for fuel type classification on OBD-II edge device. In 2024 Symposium on Internet of Things (SIoT), volume 1, pages 1–5. IEEE.
Andrade, P., Silva, M., Medeiros, M., Costa, D. G., and Silva, I. (2024). TEDA-RLS: A TinyML incremental learning approach for outlier detection and correction. IEEE Sensors Journal.
Costa, H., Silva, M., Sánchez-Gendriz, I., Viegas, C. M. D., and Silva, I. (2024). An evolving multivariate time series compression algorithm for IoT applications. Sensors, 24(22).
Jung, J., Han, S., Park, M., and Cho, S. (2024). Automotive digital forensics through data and log analysis of vehicle diagnosis Android apps. Forensic Science International: Digital Investigation, 49, 301752.
Khan, M. A. A., Ali, M. H., Haque, F., and Habib, M. T. (2023). A machine learning approach for driver identification. Indonesian Journal of Electrical Engineering and Computer Science, 30(1), 276–288.
Kumar, R. and Jain, A. (2023a). Driving behavior analysis and classification by vehicle OBD data using machine learning. The Journal of Supercomputing, 79(16), 18800–18819.
Kumar, R. and Jain, A. (2023b). Driving behavior analysis and classification by vehicle OBD data using machine learning. Journal of Supercomputing, 79(3), 18800–18819.
Malik, M. and Nandal, R. (2023). A framework on driving behavior and pattern using on-board diagnostics (OBD-II) tool. Materials Today: Proceedings, 80, 3762–3768. SI:5 NANO 2021.
Mandala, V. (2024). Predictive failure analytics in critical automotive applications: Enhancing reliability and safety through advanced AI techniques. Journal of Artificial Intelligence and Big Data, 4(1), 48–60.
Manoharan, M., Muthukrishnan, K., Balan, G., Arumugam, S., Muthusamy, S., Ramachandran, M., Balodi, A., Chinnaiyan, V. K., Sekaran, S., and Gnanakkan, C. A. R. C. (2024). A novel method for illegal driver detection and legal driver identification using multitask learning based LSTM models for real-time applications. Wireless Personal Communications, 136(3), 1923–1944.
Medeiros, M., Flores, T., Silva, M., and Silva, I. (2024). A multi-layered methodology for driver behavior analysis using TinyML and edge computing. In 2024 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS), pages 1–8. IEEE.
More, A., Khane, S., Jadhav, D., Sahoo, H., and Mali, Y. K. (2024). Auto-Shield: IoT based OBD application for car health monitoring. In 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), pages 1–10.
Purnomo, C. P., Munadi, R., Istikmal, Widodo, A., Kuntadi, S., and Putra, R. H. (2023). Digitalization of public vehicles using on-board diagnostic-II (OBD-II). In 2023 International Conference on Cyber Management and Engineering (CyMaEn), pages 50–54.
Pérez-Moure, H., Lampón, J. F., Velando-Rodriguez, M.-E., and Rodríguez-Comesaña, L. (2023). Revolutionizing the road: How sustainable, autonomous, and connected vehicles are changing digital mobility business models. European Research on Management and Business Economics, 29(3).
Ragab, H., Givigi, S., and Noureldin, A. (2024). Automotive speed estimation: Sensor types and error characteristics from OBD-II to ADAS. arXiv preprint arXiv:2501.00242.
Rana, K. and Khatri, N. (2024). Automotive intelligence: Unleashing the potential of AI beyond advanced driver assisting systems, a comprehensive review. Computers and Electrical Engineering, 117, 109237.
Roque, A. D. S., Alves, L. M. D. S., and de Freitas, E. P. (2024). CAN-Modes: In-vehicle datasets generation and analysis in different driving situations. In 2024 Workshop on Communication Networks and Power Systems (WCNPS), pages 1–7. IEEE.
Silva, M., Medeiros, T., Azevedo, M., Medeiros, M., Themoteo, M., Gois, T., Silva, I., and Costa, D. G. (2023). An adaptive TinyML unsupervised online learning algorithm for driver behavior analysis. In 2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive), pages 199–204. IEEE.
Slimani, C., Morge-Rollet, L., Lemarchand, L., Espes, D., Le Roy, F., and Boukhobza, J. (2025). A study on characterizing energy, latency and security for intrusion detection systems on heterogeneous embedded platforms. Future Generation Computer Systems, 162, 107473.
Tak, S. and Choi, S. (2022). Safety monitoring system of CAVs considering the trade-off between sampling interval and data reliability. Sensors, 22(10).
Thajudheen, S., G, S., and Jesudoss, A. G. (2023). Vehicular data retrieval system. In 2023 International Conference on New Frontiers in Communication, Automation, Management and Security (ICCAMS), volume 1, pages 1–5.
Waisara, S., Charoenlarpnopparut, S., Srisurangkul, C., and Nishio, T. (2023). Vehicle telematics system design for real-time applications using mobile networks. In 2023 18th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP), pages 1–6.
Wohlin, C., Runeson, P., Höst, M., Ohlsson, M. C., Regnell, B., and Wesslén, A. (2024). Experimentation in software engineering. Springer Science & Business Media, 2nd edition.
Andrade, P., Silva, M., Medeiros, M., Costa, D. G., and Silva, I. (2024). TEDA-RLS: A TinyML incremental learning approach for outlier detection and correction. IEEE Sensors Journal.
Costa, H., Silva, M., Sánchez-Gendriz, I., Viegas, C. M. D., and Silva, I. (2024). An evolving multivariate time series compression algorithm for IoT applications. Sensors, 24(22).
Jung, J., Han, S., Park, M., and Cho, S. (2024). Automotive digital forensics through data and log analysis of vehicle diagnosis Android apps. Forensic Science International: Digital Investigation, 49, 301752.
Khan, M. A. A., Ali, M. H., Haque, F., and Habib, M. T. (2023). A machine learning approach for driver identification. Indonesian Journal of Electrical Engineering and Computer Science, 30(1), 276–288.
Kumar, R. and Jain, A. (2023a). Driving behavior analysis and classification by vehicle OBD data using machine learning. The Journal of Supercomputing, 79(16), 18800–18819.
Kumar, R. and Jain, A. (2023b). Driving behavior analysis and classification by vehicle OBD data using machine learning. Journal of Supercomputing, 79(3), 18800–18819.
Malik, M. and Nandal, R. (2023). A framework on driving behavior and pattern using on-board diagnostics (OBD-II) tool. Materials Today: Proceedings, 80, 3762–3768. SI:5 NANO 2021.
Mandala, V. (2024). Predictive failure analytics in critical automotive applications: Enhancing reliability and safety through advanced AI techniques. Journal of Artificial Intelligence and Big Data, 4(1), 48–60.
Manoharan, M., Muthukrishnan, K., Balan, G., Arumugam, S., Muthusamy, S., Ramachandran, M., Balodi, A., Chinnaiyan, V. K., Sekaran, S., and Gnanakkan, C. A. R. C. (2024). A novel method for illegal driver detection and legal driver identification using multitask learning based LSTM models for real-time applications. Wireless Personal Communications, 136(3), 1923–1944.
Medeiros, M., Flores, T., Silva, M., and Silva, I. (2024). A multi-layered methodology for driver behavior analysis using TinyML and edge computing. In 2024 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS), pages 1–8. IEEE.
More, A., Khane, S., Jadhav, D., Sahoo, H., and Mali, Y. K. (2024). Auto-Shield: IoT based OBD application for car health monitoring. In 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), pages 1–10.
Purnomo, C. P., Munadi, R., Istikmal, Widodo, A., Kuntadi, S., and Putra, R. H. (2023). Digitalization of public vehicles using on-board diagnostic-II (OBD-II). In 2023 International Conference on Cyber Management and Engineering (CyMaEn), pages 50–54.
Pérez-Moure, H., Lampón, J. F., Velando-Rodriguez, M.-E., and Rodríguez-Comesaña, L. (2023). Revolutionizing the road: How sustainable, autonomous, and connected vehicles are changing digital mobility business models. European Research on Management and Business Economics, 29(3).
Ragab, H., Givigi, S., and Noureldin, A. (2024). Automotive speed estimation: Sensor types and error characteristics from OBD-II to ADAS. arXiv preprint arXiv:2501.00242.
Rana, K. and Khatri, N. (2024). Automotive intelligence: Unleashing the potential of AI beyond advanced driver assisting systems, a comprehensive review. Computers and Electrical Engineering, 117, 109237.
Roque, A. D. S., Alves, L. M. D. S., and de Freitas, E. P. (2024). CAN-Modes: In-vehicle datasets generation and analysis in different driving situations. In 2024 Workshop on Communication Networks and Power Systems (WCNPS), pages 1–7. IEEE.
Silva, M., Medeiros, T., Azevedo, M., Medeiros, M., Themoteo, M., Gois, T., Silva, I., and Costa, D. G. (2023). An adaptive TinyML unsupervised online learning algorithm for driver behavior analysis. In 2023 IEEE International Workshop on Metrology for Automotive (MetroAutomotive), pages 199–204. IEEE.
Slimani, C., Morge-Rollet, L., Lemarchand, L., Espes, D., Le Roy, F., and Boukhobza, J. (2025). A study on characterizing energy, latency and security for intrusion detection systems on heterogeneous embedded platforms. Future Generation Computer Systems, 162, 107473.
Tak, S. and Choi, S. (2022). Safety monitoring system of CAVs considering the trade-off between sampling interval and data reliability. Sensors, 22(10).
Thajudheen, S., G, S., and Jesudoss, A. G. (2023). Vehicular data retrieval system. In 2023 International Conference on New Frontiers in Communication, Automation, Management and Security (ICCAMS), volume 1, pages 1–5.
Waisara, S., Charoenlarpnopparut, S., Srisurangkul, C., and Nishio, T. (2023). Vehicle telematics system design for real-time applications using mobile networks. In 2023 18th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP), pages 1–6.
Wohlin, C., Runeson, P., Höst, M., Ohlsson, M. C., Regnell, B., and Wesslén, A. (2024). Experimentation in software engineering. Springer Science & Business Media, 2nd edition.
Publicado
19/05/2025
Como Citar
MACHADO, Hilton; ANDRADE, Matheus; MEDEIROS, Thaís; SILVA, Marianne; SILVA, Ivanovitch.
Avaliação da Latência em Sistemas de Monitoramento Veicular Embarcado com Aprendizado de Máquina. In: WORKSHOP DE TESTES E TOLERÂNCIA A FALHAS (WTF), 25. , 2025, Natal/RN.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 71-84.
ISSN 2595-2684.
DOI: https://doi.org/10.5753/wtf.2025.8831.
