A Tutorial-cum-Survey on Self-Supervised Learning for Wi-Fi Sensing: Trends, Challenges, and Outlook

TL;DR

This paper provides a comprehensive tutorial and survey on Wi-Fi sensing, emphasizing the role of self-supervised learning techniques in improving activity recognition and other applications using channel state information.

Contribution

It offers an in-depth review of Wi-Fi CSI, discusses ML preprocessing, compares datasets, and highlights the potential of self-supervised learning for Wi-Fi sensing advancements.

Findings

Self-supervised learning improves classification accuracy in Wi-Fi sensing

Contrastive and non-contrastive SSL methods are effective for activity recognition

Existing datasets have limitations that need addressing for better model training

Abstract

Wi-Fi technology has evolved from simple communication routers to sensing devices. Wi-Fi sensing leverages conventional Wi-Fi transmissions to extract and analyze channel state information (CSI) for applications like proximity detection, occupancy detection, activity recognition, and health monitoring. By leveraging existing infrastructure, Wi-Fi sensing offers a privacy-preserving, non-intrusive, and cost-effective solution which, unlike cameras, is not sensitive to lighting conditions. Beginning with a comprehensive review of the Wi-Fi standardization activities, this tutorial-cum-survey first introduces fundamental concepts related to Wi-Fi CSI, outlines the CSI measurement methods, and examines the impact of mobile objects on CSI. The mechanics of a simplified testbed for CSI extraction are also described. Then, we present a qualitative comparison of the existing Wi-Fi sensing datasets, their specifications, and pin-point their shortcomings. Next, a variety of preprocessing techniques are discussed that are beneficial for feature extraction and explainability of machine learning (ML) algorithms. We then provide a qualitative review of recent ML approaches in the domain of Wi-Fi sensing and present the significance of self-supervised learning (SSL) in that context. Specifically, the mechanics of contrastive and non-contrastive learning solutions is elaborated in detail and a quantitative comparative analysis is presented in terms of classification accuracy. Finally, the article concludes by highlighting emerging technologies that can be leveraged to enhance the performance of Wi-Fi sensing and opportunities for further research in this domain