Avaliação de Desempenho de Modelos de ML para IoMT em uma Plataforma ARM de Borda
Resumo
A Inteligência Artificial de Borda (Edge AI) permite o processamento local de dados para aplicações de saúde sensíveis à latência. Em ambientes de assistência à vida independente (AAL), tarefas como detecção de quedas e reconhecimento facial se beneficiam da inferência no próprio dispositivo, visto que soluções baseadas exclusivamente em nuvem podem introduzir atrasos. Este trabalho apresenta um estudo experimental de modelos de aprendizado de máquina (ML) implantados em uma plataforma de borda baseada em ARM, a Orange Pi Plus, para detecção de quedas e reconhecimento facial. A análise considera métricas de classificação, tempo de treinamento e medições de hardware, incluindo uso de CPU, consumo de memória e temperatura de operação. Os resultados mostram que modelos baseados em árvores oferecem o melhor equilíbrio entre desempenho preditivo e custo computacional na detecção de quedas, enquanto o reconhecimento facial atinge alta acurácia com diferentes configurações de ML.
Referências
Aceto, G., Persico, V., and Pescapé, A. (2018). The role of information and communication technologies in healthcare: taxonomies, perspectives, and challenges. Journal of Network and Computer Applications, 107:125–154.
Bezerra, T., Vinicius, M., Ciane, A., Callou, G., França, C., and Tavares, E. (2025). An approach based on iot and machine learning for monitoring patients on healthcare centers. In Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 260–271. SBC.
Cao, Q., Shen, L., Xie, W., Parkhi, O. M., and Zisserman, A. (2018). Vggface2: A dataset for recognising faces across pose and age. In 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018), pages 67–74. IEEE.
Giri, A., Hasib, A., Islam, M., Tazim, M. F., Rahman, M. S., Khadgi, M., and Akib, A. A. S. (2025). Real-time human fall detection using yolov5 on raspberry pi: An edge ai solution for smart healthcare and safety monitoring. In International Conference on Data Analytics & Management, pages 493–507. Springer.
Jiménez Bravo, D. M., Lozano Murciego, A., Sales Mendes, A., Hernández de la Iglesia, D., Silva, L. A., et al. (2022). Edge face recognition system based on one-shot augmented learning. International Journal of Interactive Multimedia and Artificial Intelligence, 7(6):31–44.
Min, W., Yao, L., Lin, Z., and Liu, L. (2018). Support vector machine approach to fall recognition based on simplified expression of human skeleton action and fast detection of start key frame using torso angle. IET Computer Vision, 12(8):1133–1140.
Ouloul, M. I., Moutakki, Z., Amghar, A., and Afdel, K. (2025). Low-cost embedded facial recognition system based on overlapped local binary pattern. e-Prime-Advances in Electrical Engineering, Electronics and Energy, 11:100924.
Pecolt, S., Błażejewski, A., Królikowski, T., Maciejewski, I., Gierula, K., and Glowinski, S. (2025). Personal identification using embedded raspberry pi-based face recognition systems. Applied Sciences, 15(2):887.
Rashidi, P. and Mihailidis, A. (2012). A survey on ambient-assisted living tools for older adults. IEEE journal of biomedical and health informatics, 17(3):579–590.
Shi, W., Cao, J., Zhang, Q., Li, Y., and Xu, L. (2016). Edge computing: Vision and challenges. IEEE internet of things journal, 3(5):637–646.
Shu, F. and Shu, J. (2021). An eight-camera fall detection system using human fall pattern recognition via machine learning by a low-cost android box. Scientific reports, 11(1):2471.
Sucerquia, A., López, J. D., and Vargas-Bonilla, J. F. (2017). Sisfall: A fall and movement dataset. Sensors, 17(1):198.
Sze, V., Chen, Y.-H., Yang, T.-J., and Emer, J. S. (2017). Efficient processing of deep neural networks: A tutorial and survey. Proceedings of the IEEE, 105(12):2295–2329.
Valentim, T., Callou, G., França, C., and Tavares, E. (2024). Availability and performance assessment of iomt systems: A stochastic modeling approach. Journal of Network and Systems Management, 32(4):95.
Wang, X., Han, Y., Leung, V. C., Niyato, D., Yan, X., and Chen, X. (2020). Convergence of edge computing and deep learning: A comprehensive survey. IEEE communications surveys & tutorials, 22(2):869–904.
Yacchirema, D., de Puga, J. S., Palau, C., and Esteve, M. (2019). Fall detection system for elderly people using iot and ensemble machine learning algorithm. Personal and Ubiquitous Computing, 23(5):801–817.
Bezerra, T., Vinicius, M., Ciane, A., Callou, G., França, C., and Tavares, E. (2025). An approach based on iot and machine learning for monitoring patients on healthcare centers. In Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 260–271. SBC.
Cao, Q., Shen, L., Xie, W., Parkhi, O. M., and Zisserman, A. (2018). Vggface2: A dataset for recognising faces across pose and age. In 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018), pages 67–74. IEEE.
Giri, A., Hasib, A., Islam, M., Tazim, M. F., Rahman, M. S., Khadgi, M., and Akib, A. A. S. (2025). Real-time human fall detection using yolov5 on raspberry pi: An edge ai solution for smart healthcare and safety monitoring. In International Conference on Data Analytics & Management, pages 493–507. Springer.
Jiménez Bravo, D. M., Lozano Murciego, A., Sales Mendes, A., Hernández de la Iglesia, D., Silva, L. A., et al. (2022). Edge face recognition system based on one-shot augmented learning. International Journal of Interactive Multimedia and Artificial Intelligence, 7(6):31–44.
Min, W., Yao, L., Lin, Z., and Liu, L. (2018). Support vector machine approach to fall recognition based on simplified expression of human skeleton action and fast detection of start key frame using torso angle. IET Computer Vision, 12(8):1133–1140.
Ouloul, M. I., Moutakki, Z., Amghar, A., and Afdel, K. (2025). Low-cost embedded facial recognition system based on overlapped local binary pattern. e-Prime-Advances in Electrical Engineering, Electronics and Energy, 11:100924.
Pecolt, S., Błażejewski, A., Królikowski, T., Maciejewski, I., Gierula, K., and Glowinski, S. (2025). Personal identification using embedded raspberry pi-based face recognition systems. Applied Sciences, 15(2):887.
Rashidi, P. and Mihailidis, A. (2012). A survey on ambient-assisted living tools for older adults. IEEE journal of biomedical and health informatics, 17(3):579–590.
Shi, W., Cao, J., Zhang, Q., Li, Y., and Xu, L. (2016). Edge computing: Vision and challenges. IEEE internet of things journal, 3(5):637–646.
Shu, F. and Shu, J. (2021). An eight-camera fall detection system using human fall pattern recognition via machine learning by a low-cost android box. Scientific reports, 11(1):2471.
Sucerquia, A., López, J. D., and Vargas-Bonilla, J. F. (2017). Sisfall: A fall and movement dataset. Sensors, 17(1):198.
Sze, V., Chen, Y.-H., Yang, T.-J., and Emer, J. S. (2017). Efficient processing of deep neural networks: A tutorial and survey. Proceedings of the IEEE, 105(12):2295–2329.
Valentim, T., Callou, G., França, C., and Tavares, E. (2024). Availability and performance assessment of iomt systems: A stochastic modeling approach. Journal of Network and Systems Management, 32(4):95.
Wang, X., Han, Y., Leung, V. C., Niyato, D., Yan, X., and Chen, X. (2020). Convergence of edge computing and deep learning: A comprehensive survey. IEEE communications surveys & tutorials, 22(2):869–904.
Yacchirema, D., de Puga, J. S., Palau, C., and Esteve, M. (2019). Fall detection system for elderly people using iot and ensemble machine learning algorithm. Personal and Ubiquitous Computing, 23(5):801–817.
Publicado
19/07/2026
Como Citar
CLEBSON, José; VINÍCIUS, Marcos; LIRA, Rodrigo Cesar; CALLOU, Gustavo; ARAÚJO, Verlaynne; LOPES, Diogo; TAVARES, Eduardo; BEZERRA, Thiago.
Avaliação de Desempenho de Modelos de ML para IoMT em uma Plataforma ARM de Borda. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO UBÍQUA E PERVASIVA (SBCUP), 18. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 92-102.
ISSN 2595-6183.
DOI: https://doi.org/10.5753/sbcup.2026.23944.
