Self-Supervised WiFi-Based Activity Recognition

TL;DR

This paper introduces a self-supervised contrastive learning approach for passive indoor activity recognition using WiFi signals, achieving significant performance improvements over traditional methods.

Contribution

It presents a novel application of self-supervised contrastive learning to WiFi-based activity recognition, leveraging multiple signal views for improved accuracy.

Findings

17.7% increase in macro F1 score

Significant improvements in one- and few-shot learning

Effective in both LoS and NLoS conditions

Abstract

Traditional approaches to activity recognition involve the use of wearable sensors or cameras in order to recognise human activities. In this work, we extract fine-grained physical layer information from WiFi devices for the purpose of passive activity recognition in indoor environments. While such data is ubiquitous, few approaches are designed to utilise large amounts of unlabelled WiFi data. We propose the use of self-supervised contrastive learning to improve activity recognition performance when using multiple views of the transmitted WiFi signal captured by different synchronised receivers. We conduct experiments where the transmitters and receivers are arranged in different physical layouts so as to cover both Line-of-Sight (LoS) and non LoS (NLoS) conditions. We compare the proposed contrastive learning system with non-contrastive systems and observe a 17.7% increase in macro averaged F1 score on the task of WiFi based activity recognition, as well as significant improvements in one- and few-shot learning scenarios.