WiFi-Based Robust Human and Non-human Motion Recognition With Deep Learning

• Published in: IEEE International Conference on Pervasive Computing and Communications workshops (Online) pp. 769 - 774
• Main Authors: Zhu, Guozhen, Wang, Beibei, Gao, Weihang, Hu, Yuqian, Wu, Chenshu, Ray Liu, K. J.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 11.03.2024
• Subjects: Artificial neural networks; Conferences; Deep learning; Human and non-human recognition; Interference; Pervasive computing; Pet recognition; Robustness; Sensors; WiFi sensing
• ISSN: 2766-8576
• DOI: 10.1109/PerComWorkshops59983.2024.10502413

As WiFi becomes increasingly pervasive in communications, its role in sensing applications is likewise expanding. However, current WiFi-based sensing technologies often operate under the limit assumption that all detected motion originates from human activities, there by neglecting influences from non-human subjects. Being able to differentiate human motions from non-human ones is essential in many application use cases. This paper presents a deep learning framework that can accurately recognize human and various non-human moving subjects using single-pair WiFi devices, even through the walls. Utilizing environment-invariant features, the framework is tested across three settings with commodity WiFi devices and various deep neural network architectures for four-class recognition. Achieving an average validation accuracy of 95.57% and an average testing accuracy of 87.09% in unseen environments with a challenging dataset, our approach demonstrates its robustness and readiness for integration into intelligent IoT systems and applications.