A Transformer-Based Methodology for Person-Independent Sweeping Activity Recognition Using Wi-Fi CSI Data

• Allan Costa Nascimento dos Santos UFF / Brunel University London
• Iandra Galdino UFF
• Julio C. H. Soto UFF
• Taiane C. Ramos UFF
• Celio V. N. de Albuquerque UFF
• Raphael Guerra UFF
• Cledson de Sousa UFF
• Natalia C. Fernandes UFF
• Débora Muchaluat-Saade UFF
• Gheorghita Ghinea Brunel University London

DOI: https://doi.org/10.5753/sbcas.2025.7853

Abstract

The use of channel state information (CSI) for human activity recognition holds promise in healthcare, especially for remote patient monitoring. By capturing and interpreting Wi-Fi signals in indoor environments, CSI can be used to detect physical activity, falls, or daily movements of a patient, allowing caregivers and healthcare professionals to monitor patients without the need for wearable sensors or invasive cameras. CSI also has great potential in elderly care. Therefore, this paper proposes a methodology called DVC-CSI to identify the floor sweeping activity of a person in a room through the analysis of CSI data and a dataset used for its evaluation. DVC-CSI uses Transformer models developed to process time series data featuring a structure that allows capturing temporal dependencies. DVC-CSI is capable of identifying activities of people who did not participate in the training phase. The accuracy of floor sweeping activity identification is 88.89% using a CSI dataset of 86 volunteers (60 participants for training, 17 participants for validation, and 9 participants for testing).

References

Bulugu, I. (2023). Gesture recognition system based on cross-domain csi extracted from wi-fi devices combined with the 3d cnn. Signal, Image and Video Processing, 17(6):3201–3209.

Caballero, E., Galdino, I., Soto, J. C., Ramos, T. C., Guerra, R., Muchaluat-Saade, D., and Albuquerque, C. (2023). Human Activity Recognition Using Wi-Fi CSI. In International Conference on Pervasive Computing Technologies for Healthcare, pages 309–321. Springer.

de Almeida, G. C., dos Santos, A. C., Soares, C. L. d. A., Pinto, P. C. A., Dal Bello, F. d. S., Boechat, Y. E. M., Seixas, F. L., dos Santos, A. A. S., Mesquita, C. T., Mesquita, E. T., et al. (2023). Nova geração da telessaúde: Oportunidades, tendências e desafios. In Minicursos do XXIII Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS).

de Sousa, C., Fernandes, V., Coimbra, E. A., and Huguenin, L. (2024). Subcarrier Selection for HAR Using CSI and CNN: Reducing Complexity and Enhancing Accuracy. In 2024 IEEE Virtual Conference on Communications (VCC), pages 1–7.

dos Santos, A. C. N., de Paula, K., Vidal, M. T. L., da Silva, J. M. M., de Sousa, C., Fernandes, L. A. F., de Castro, T. B., Bedo, M., Kohwalter, T. C., Bastos, C. A. M., Seixas, F. L., Fernandes, N. C., Muchaluat-Saade, D. C., and Ghinea, G. (2024). A computer vision model to support individuals with disabilities within university campuses. In 2024 IEEE International Conference on E-health Networking, Application & Services (HealthCom), pages 1–7.

dos Santos, A. C. N., Seixas, F. L., and Fernandes, N. C. (2022). Provendo um modelo automático de detecção de quedas baseado em rede adversária generativa para assistência de idosos. In Anais do XXII Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 120–131. SBC.

Galdino, I., Soto, J. C. H., Caballero, E., Ferreira, V., Ramos, T. C., Albuquerque, C., and Muchaluat-Saade, D. C. (2023). eHealth CSI: A Wi-Fi CSI Dataset of Human Activities. IEEE Access, 11:71003–71012.

Rothman, D. (2021). Transformers for Natural Language Processing: Build innovative deep neural network architectures for NLP with Python, PyTorch, TensorFlow, BERT, RoBERTa, and more. Packt Publishing Ltd.

Santos, A. C., Firmino, R. M., Soto, J. C., Medeiros, D. S., Mattos, D. M., Albuquerque, C. V., Seixas, F., Muchaluat-Saade, D. C., and Fernandes, N. C. (2020). Aplicações em redes de sensores na área da saúde e gerenciamento de dados médicos: tecnologias em ascensão. In Minicursos do XX Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 137–186.

Soto, J. C., Galdino, I., Caballero, E., Ferreira, V., Muchaluat-Saade, D., and Albuquerque, C. (2022). A survey on vital signs monitoring based on wi-fi csi data. Computer Communications, 195:99–110.

Wang, Y., Wu, K., and Ni, L. M. (2017). Wifall: Device-free fall detection by wireless networks. IEEE Transactions on Mobile Computing, 16(2):581–594.

Xiao, C., Han, D., Ma, Y., and Qin, Z. (2019). Csigan: Robust channel state information-based activity recognition with gans. IEEE Internet of Things Journal, 6(6):10191–10204.

Zheng, Y., Zhang, Y., Qian, K., Zhang, G., Liu, Y., Wu, C., and Yang, Z. (2019). Zero-effort cross-domain gesture recognition with wi-fi. In Proceedings of the 17th annual international conference on mobile systems, applications, and services, pages 313–325.