Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.17667 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915431383564288 |
|---|---|
| author | Liu, Junshuo Shi, Xin Zhang, Yunchuan Ge, Yinhao Qiu, Robert C. |
| author_facet | Liu, Junshuo Shi, Xin Zhang, Yunchuan Ge, Yinhao Qiu, Robert C. |
| contents | Radio-frequency (RF)-based human activity recognition (HAR) provides a contactless and privacy-preserving solution for monitoring human behavior in applications such as astronaut extravehicular activity monitoring, human-autonomy collaborative cockpit, and unmanned aerial vehicle surveillance. However, real-world deployments usually face the challenge of domain knowledge 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 collecting data from the target domain. 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 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. The empirical results substantiate the generalization capability of DGAR in real-time RF sensing across dynamic scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17667 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DGAR: A Unified Domain Generalization Framework for RF-Based Human Activity Recognition Liu, Junshuo Shi, Xin Zhang, Yunchuan Ge, Yinhao Qiu, Robert C. Signal Processing Radio-frequency (RF)-based human activity recognition (HAR) provides a contactless and privacy-preserving solution for monitoring human behavior in applications such as astronaut extravehicular activity monitoring, human-autonomy collaborative cockpit, and unmanned aerial vehicle surveillance. However, real-world deployments usually face the challenge of domain knowledge 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 collecting data from the target domain. 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 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. The empirical results substantiate the generalization capability of DGAR in real-time RF sensing across dynamic scenarios. |
| title | DGAR: A Unified Domain Generalization Framework for RF-Based Human Activity Recognition |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2503.17667 |