Radar-Based Cross-Environment Unsupervised Domain Adaptation for Human Activity Recognition

TY - GEN

T1 - Radar-Based Cross-Environment Unsupervised Domain Adaptation for Human Activity Recognition

AU - Li, Ludi

AU - Liu, Jin

AU - Lin, Hanhe

AU - Tian, Xu

AU - Yuan, Mingzi

AU - Zhu, Jianchun

AU - Wang, Jianxin

N1 - Publisher Copyright: © 2025 IEEE.

PY - 2025/1/29

Y1 - 2025/1/29

N2 - Millimeter-wave radar, with its ease of deployment and around-the-clock operation, has become widely adopted for monitoring daily human activities in mobile health. Human activity recognition (HAR) models trained on collected radar data enable persistent detection of critical incidents such as falls, which is critical for reducing in-home care costs and improving healthcare resource utilization efficiency. However, radar signals are easily disrupted by environmental variations, causing models trained in one setting to generalize poorly when applied to new environment. To address this challenge, we propose a radar-based cross-environment unsupervised domain adaptation (UDA) method, which significantly enhances generalization performance in unlabeled target domains (new environment) by leveraging fully labeled source domain data (historical environment). Our approach comprises two key components: a feature fusion module and a knowledge distillation module. First, the feature fusion module employs an attention mechanism to perform weighted linear interpolation between source domain and target domain features and uses an alignment loss to learn a shared feature rep-resentation robust to environmental changes. Next, temperature-scaled knowledge distillation generates soft pseudo labels for unlabeled target domain samples, improving the model's dis-criminatory power without ground-truth annotations. Evaluated on twelve cross-environment HAR tasks, the proposed method achieves an average recognition accuracy of 94.19%, offering an efficient and reliable solution for radar-based mobile health monitoring.

AB - Millimeter-wave radar, with its ease of deployment and around-the-clock operation, has become widely adopted for monitoring daily human activities in mobile health. Human activity recognition (HAR) models trained on collected radar data enable persistent detection of critical incidents such as falls, which is critical for reducing in-home care costs and improving healthcare resource utilization efficiency. However, radar signals are easily disrupted by environmental variations, causing models trained in one setting to generalize poorly when applied to new environment. To address this challenge, we propose a radar-based cross-environment unsupervised domain adaptation (UDA) method, which significantly enhances generalization performance in unlabeled target domains (new environment) by leveraging fully labeled source domain data (historical environment). Our approach comprises two key components: a feature fusion module and a knowledge distillation module. First, the feature fusion module employs an attention mechanism to perform weighted linear interpolation between source domain and target domain features and uses an alignment loss to learn a shared feature rep-resentation robust to environmental changes. Next, temperature-scaled knowledge distillation generates soft pseudo labels for unlabeled target domain samples, improving the model's dis-criminatory power without ground-truth annotations. Evaluated on twelve cross-environment HAR tasks, the proposed method achieves an average recognition accuracy of 94.19%, offering an efficient and reliable solution for radar-based mobile health monitoring.

KW - Human Activity Recognition

KW - Mobile Health

KW - Radar Monitoring

KW - Unsupervised Domain Adaptation

UR - https://www.scopus.com/pages/publications/105033593779

U2 - 10.1109/BIBM66473.2025.11356872

DO - 10.1109/BIBM66473.2025.11356872

M3 - Conference contribution

AN - SCOPUS:105033593779

T3 - Proceedings - 2025 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2025

SP - 2411

EP - 2416

BT - Proceedings - 2025 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2025

A2 - Liu, Juan

A2 - Huang, Jingshan

A2 - Wang, Xiaowo

A2 - Zhang, Fa

A2 - Zou, Xiufen

A2 - Tian, Tian

A2 - Hu, Xiaohua

A2 - Hu, Bin

A2 - Xiong, Yi

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2025 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2025

Y2 - 15 December 2025 through 18 December 2025

ER -