RFBoost: Understanding and Boosting Deep WiFi Sensing via Physical Data Augmentation

TL;DR

RFBoost introduces novel physical data augmentation techniques to enhance deep WiFi sensing, significantly improving accuracy without extra data collection or model changes, and sets a foundation for future research in radio data augmentation.

Contribution

RFBoost pioneers the study of radio data augmentation for WiFi sensing, providing a plug-and-play framework that boosts deep learning performance in wireless sensing tasks.

Findings

Achieves an average accuracy improvement of 5.4% across multiple datasets.

Outperforms 11 state-of-the-art baseline models without additional data or modifications.

Demonstrates the effectiveness of physical data augmentation in deep wireless sensing.

Abstract

Deep learning shows promising performance in wireless sensing. However, deep wireless sensing (DWS) heavily relies on large datasets. Unfortunately, building comprehensive datasets for DWS is difficult and costly, because wireless data depends on environmental factors and cannot be labeled offline. Despite recent advances in few-shot/cross-domain learning, DWS is still facing data scarcity issues. In this paper, we investigate a distinct perspective of radio data augmentation (RDA) for WiFi sensing and present a data-space solution. Our key insight is that wireless signals inherently exhibit data diversity, contributing more information to be extracted for DWS. We present RFBoost, a simple and effective RDA framework encompassing novel physical data augmentation techniques. We implement RFBoost as a plug-and-play module integrated with existing deep models and evaluate it on multiple datasets. Experimental results demonstrate that RFBoost achieves remarkable average accuracy improvements of 5.4% on existing models without additional data collection or model modifications, and the best-boosted performance outperforms 11 state-of-the-art baseline models without RDA. RFBoost pioneers the study of RDA, an important yet currently underexplored building block for DWS, which we expect to become a standard DWS component of WiFi sensing and beyond. RFBoost is released at https://github.com/aiot-lab/RFBoost.