A Review of WiFi Sensing-based Gait Recognition from A Deep Learning Perspective

Yifei Chen

doi:10.54097/3q982d19

Authors

Yifei Chen

DOI:

https://doi.org/10.54097/3q982d19

Keywords:

Deep learning, gait recognition, device-based sensing, machine learning.

Abstract

Gait recognition based on WiFi sensing has emerged as a prominent area of research, driven by its potential for a diverse range of applications, the ability to recognize identity without being intrusive, and its cost-effectiveness. Deep learning models have been widely used in this recognition method, and different researchers have proposed the use of different neural networks to address different aspects of model-based gait recognition. However, the extant literature on these issues is lacking in a systematic compilation and evaluation. An overview of recent developments in deep learning models for WiFi-sensing-based gait identification is provided in this paper. It highlights key issues such as the removal of environmental dependency, the ability to deal with environmental random noise, and the handling of complex CSI data. Furthermore, research is conducted into the utilisation of multimodal recognition methods. In conclusion, the paper presents prospective solutions to the aforementioned issues and proposes avenues for future research.

Downloads

Download data is not yet available.

References

[1] Liu, Z., Liu, X., Zhang, J., Li, K. Opportunities and challenges of wireless human sensing for the smart IoT world: A survey. IEEE Network, 2019, 33 (5), 104 - 110.

[2] Ahmad, I., Ullah, A., Choi, W. WiFi-Based Human Sensing with Deep Learning: Recent Advances, Challenges, and Opportunities. IEEE Open Journal of the Communications Society. 2024.

[3] Wang, Z., Huang, Z., Zhang, C., Dou, W., Guo, Y., Chen, D. CSI-based human sensing using model-based approaches: a survey. Journal of Computational Design and Engineering, 2021, 8 (2): 510 - 523.

[4] Halperin, D., Hu, W., Sheth, A., Wetherall, D. Tool release: Gathering 802.11 n traces with channel state information. ACM SIGCOMM computer communication review, 2011, 41 (1): 53 - 53.

[5] Xie, Y., Li, Z., Li, M. Precise power delay profiling with commodity WiFi. In Proceedings of the 21st Annual International Conference on Mobile Computing and Networking 2015.

[6] Li, H., Yang, W., Wang, J., Xu, Y., Huang, L. WiFinger: Talk to your smart devices with finger-grained gestures. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing,2016.

[7] Wang, Z., Huang, Z., Zhang, C., Dou, W., Guo, Y., & Chen, D. CSI-based human sensing using model-based approaches: a survey. Journal of Computational Design and Engineering, 2021, 8 (2): 510 - 523.

[8] Santhalingam, P. S., Hosain, A. A., Zhang, D., Pathak, P., Rangwala, H., & Kushalnagar, R mmASL: Environment-independent ASL gesture recognition using 60 GHz millimeter-wave signals. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2020, 4 (1): 1 - 30.

[9] Ge, Y., Taha, A., Shah, S. A., Dashtipour, K., Zhu, S., Cooper, J., Imran, M. A. Contactless WiFi sensing and monitoring for future healthcare-emerging trends, challenges, and opportunities. IEEE Reviews in Biomedical Engineering, 2022, 16, 171 - 191.

[10] Patil, M. N., Iyer, B., & Arya, R. Performance evaluation of PCA and ICA algorithm for facial expression recognition application. In Proceedings of Fifth International Conference on Soft Computing for Problem Solving: SocProS, 2016, 1: 965 – 976.

[11] Ali, H. A. H., Seytnazarov, S. Human Walking Direction Detection Using Wireless Signals, Machine and Deep Learning Algorithms. Sensors, 2023, 23 (24): 9726.

[12] Yang, J., Chen, X., Zou, H., Wang, D., Xie, L. Autofi: Toward automatic wi-fi human sensing via geometric self-supervised learning. IEEE Internet of Things Journal, 2022, 10 (8): 7416 - 7425.

[13] Ding, J., Wang, Y., Fu, X. Wihi: WiFi-based human identity identification using deep learning. IEEE Access, 2020,8: 129246 - 129262.

[14] Li, T., Chen, T., Li, K., Ao, R. Vi-WiFi-Gate: a WiFi sensing gait recognition method inspired by the image vision field. In International Conference on Internet of Things and Machine Learning, 2023, 12937: 376 – 381.

[15] Deng, L., Yang, J., Yuan, S., Zou, H., Lu, C. X., Xie, L. GaitFi: Robust device-free human identification via WiFi and vision multimodal learning. IEEE Internet of Things Journal, 2022 10 (1): 625 - 636.