A Survey on Behavior Recognition Using WiFi Channel State Information

Abstract

In this article, we present a survey of recent advances in passive human behaviour recognition in indoor areas using the channel state information (CSI) of commercial WiFi systems. Movement of human body causes a change in the wireless signal reflections, which results in variations in the CSI. By analyzing the data streams of CSIs for different activities and comparing them against stored models, human behaviour can be recognized. This is done by extracting features from CSI data streams and using machine learning techniques to build models and classifiers. The techniques from the literature that are presented herein have great performances, however, instead of the machine learning techniques employed in these works, we propose to use deep learning techniques such as long-short term memory (LSTM) recurrent neural network (RNN), and show the improved performance. We also discuss about different challenges such as environment change, frame rate selection, and multi-user scenario, and suggest possible directions for future work.

Framework for a Perceptive Mobile Network Using Joint Communication and Radar Sensing

“…For radio sensing, however, the system needs to resolve the detailed channel structure and estimate the sensing parameters. For extended sensing primarily based on machine learning techniques [26], these parameters may be not explicitly needed, which is beyond the scope of this paper.…”

Device-Free User Authentication, Activity Classification and Tracking using Passive Wi-Fi Sensing: A Deep Learning Based Approach

“…Both amplitude and phase values are finer-grained descriptors of the wireless channel [27]. However, the phase values are affected by several sources of error, including the carrier frequency offset (CFO) and the sampling frequency offset (SFO) [16]. Although these errors can be eliminated using a calibration technique termed data sanitization in [28], we avoid phase values in the learning process to reduce the computational and implementational complexity.…”

“…2) Activity Recognition: Wireless aided activity recognition is a well studied area in the literature [13]- [16]. It has been already established that deep learning based techniques do outperform the conventional signal processing based techniques [13]- [15] with regards to activity recognition (see [16] and references therein). However, the existing deep learning based systems face difficulties in deployment due to them not considering the recurring periods without any activities in their models.…”

WiFi Motion Detection: A Study into Efficacy and Classification

“…While received signal strength (RSS) has been used for the same purposes, CSI is selected because RSS cannot capture the real changes in the signal due to the movement of the person. By obtaining the CSI for each subcarrier in orthogonal frequency division multiplexing (OFDM) systems, the observed channel dynamics will display diversity, as opposed to RSS, which cannot capture the change at certain frequencies [6].…”