Through-the-Wall Human Behavior Recognition Algorithm with Commercial Wi-Fi Devices

Abstract

Wi-Fi-based human behavior recognition technology is one of the research hotspots in the field of wireless sensing. However, the traditional Wi-Fi-based human behavior recognition algorithm does not consider the attenuation of Wi-Fi signals in the condition of wall barrier under complex indoor environments. As a result, the robustness of the Wi-Fi indoor human behavior recognition system is poor. In order to solve this problem, this paper proposes a Wi-Fi based behavior recognition algorithm through the wall. Firstly, the Wi-Fi signal distribution is analyzed according to the Wi-Fi signal model. Then, according to the distribution characteristics of different Wi-Fi signals, the principal component analysis (PCA) algorithm is used to reconstruct the signal to complete the de-nosing processing of the Wi-Fi signal. Finally, feature extraction and feature classification in the time-frequency domain is performed to complete the human behavior recognition. The experimental results show that the proposed algorithm has higher recognition accuracy in terms of walking and running than the traditional Wi-Fi based indoor recognition algorithms.