WiFi CSI-Based Human Activity Recognition Using Deep Recurrent Neural Network

Jianyang Ding,Yong Wang

doi:10.1109/access.2019.2956952

Abstract

Human activity recognition based on channel state information (CSI) using commercial WiFi devices plays an increasingly important role in many applications, such as smart home and interactive games. In this paper, we propose a WiFi CSI based human activity recognition approach using deep recurrent neural network (HARNN). HARNN mainly exploits four key techniques to recognize different human activities. HARNN firstly constructs a novel two-level decision tree for using two environment variation statistics efficiently. Meanwhile, a linear regression method is also introduced to seek for the optimal parameter for the designed decision tree. Depending on this, the decision tree is used to sense indoor environment variation, and then detect whether there is any human activity occurring in a target area. In addition, a noise removal mechanism is devised to eliminate the influence of random noise derived from indoor environments. Then, to characterize various human activities, two representative features are extracted from different statistical profiles, including channel power variation (CPV) and time-frequency analysis (TFA). Finally, a recurrent neural network (RNN) model is utilized to recognize different human activities by leveraging the extracted representative features above. According to the above steps, the proposed HARNN could establish a robust relationship between human activities and WiFi CSI compared with most of the existing WiFi CSI based approaches. The proof-of-concept prototype of HARNN is implemented on a set of commercial WiFi devices, and its overall performance is evaluated in several typical indoor environments. The experimental results demonstrate that HARNN can achieve better recognition performance compared with some benchmark approaches.

Highlights

Human activity recognition is increasingly popular in pervasive computing and human-computer interaction, and can support a wide variety of applications, such as health care [1], smart home [2], augmented reality, and building surveillance [3], etc
Due to establishing a robust corresponding relationship between various human activities and WiFi channel state information (CSI), the proposed HARNN approach is able to achieve the best performance for recognition of all the six activities, and the recognition accuracy of each activity can be more than 95%
In this paper, we propose a WiFi CSI based passive human activity recognition approach using deep recurrent neural network

Summary

INTRODUCTION

Human activity recognition is increasingly popular in pervasive computing and human-computer interaction, and can support a wide variety of applications, such as health care [1], smart home [2], augmented reality, and building surveillance [3], etc. Most of the existing WiFi CSI based approaches only leveraged the variance or the correlation coefficient directly to detect the human activities Their detection performances were influenced heavily by the random noise or channel variation, which may cause false recognition result. Only two representative features are extracted from denoised WiFi CSI data, including channel power variation (CPV) in time domain and time-frequency analysis (TFA) in frequency domain This helps improving the efficiency of activity recognition. 3) To realize HARNN, the proposed RNN model is used to recognize different human activities It can perform activity recognition from the extracted representative features, instead of raw WiFi CSI data. This reduces the influence of the random noise derived from indoor environments significantly.

PRELIMINARY

HUMAN ACTIVITY DETECTING

DATA PROCESSING

PERFORMANCE AND EVALUATION

Findings

CONCLUSION