DGAR: A Unified Domain Generalization Framework for RF-Enabled Human Activity Recognition

Abstract

Radio-frequency (RF)-based human activity recognition (HAR) provides a contactless and privacy-preserving solution for monitoring human behavior in applications such as personalized healthcare, ambient assisted living, and telemedicine. However, real-world deployment is frequently challenged by domain shifts arising from inter-subject variability, heterogeneous physical environments, and unseen activity patterns, resulting in significant performance degradation. To address this issue, we propose DGAR, a domain-generalized activity recognition framework that learns transferable representations without access to target-domain data. DGAR integrates instance-adaptive feature modulation with cross-domain distribution alignment to enhance both personalization and generalization. Specifically, it incorporates a squeeze-and-excitation (SE) block to extract salient spatiotemporal features and employs correlation alignment to mitigate inter-domain discrepancies. Extensive experiments on three public RF-based datasets -- HUST-HAR, Lab-LFM, and Office-LFM -- demonstrate that DGAR consistently outperforms state-of-the-art baselines, achieving up to a 5.81% improvement in weighted F1-score. These results underscore DGAR's potential to enable generalizable, real-time RF sensing systems in dynamic and personalized healthcare scenarios.

Tasks

Reproductions