Indoor Micro-Activity Recognition Method Using Ubiquitous WiFi Devices

摘要

This paper presents a wireless device-free WiFi-based micro-activity recognition system by leveraging the Channel State Information (CSI) of WiFi signals. Unlike previous CSI-based micro-activity recognition methods, the proposed method extracts both amplitude and phase information of CSI, which provides more information and increased the detection accuracy. The proposed approach presents an efficient signal processing method to expose unique patterns of each activity. Moreover, a machine learning algorithm is applied to classify the proposed micro-activities. The proposed prototype has been evaluated in different indoor environments, and the empirical results show the efficiency of the proposed prototype with several volunteer users.