Attention-based Walking Gait and Direction Recognition in Wi-Fi Networks

TL;DR

This paper introduces an attention-based RNN framework for Wi-Fi signal analysis to recognize human gait and walking direction accurately, using CSI data from multiple receivers in indoor environments.

Contribution

It presents a novel attention-based RNN approach for cycle-independent gait and direction recognition using Wi-Fi CSI data, improving recognition accuracy and adaptability.

Findings

Achieved 89.69% F1 score for gait recognition among 8 subjects.

Attained 95.06% accuracy for direction recognition from 8 directions.

Overall recognition accuracy exceeded 97% for both tasks.

Abstract

The study of human gait recognition has been becoming an active research field. In this paper, we propose to adopt the attention-based Recurrent Neural Network (RNN) encoder-decoder framework to implement a cycle-independent human gait and walking direction recognition system in Wi-Fi networks. For capturing more human walking dynamics, two receivers together with one transmitter are deployed in different spatial layouts. In the proposed system, the Channel State Information (CSI) measurements from different receivers are first gathered together and refined to form an integrated walking profile. Then, the RNN encoder reads and encodes the walking profile into primary feature vectors. Given a specific recognition task, the decoder computes a corresponding attention vector which is a weighted sum of the primary features assigned with different attentions, and is finally used to predict the target. The attention scheme motivates our system to learn to adaptively align with different critical clips of CSI data sequence for human walking gait and direction recognitions. We implement our system on commodity Wi-Fi devices in indoor environment, and the experimental results demonstrate that our system can achieve average F1 scores of 89.69% for gait recognition from a group of 8 subjects and 95.06% for direction recognition from 8 walking directions, in addition, the average accuracies of these two recognition tasks both exceed 97%.