TY - JOUR
T1 - radarODE-MTL
T2 - A Multitask Learning Framework With Eccentric Gradient Alignment for Robust Radar-Based ECG Reconstruction
AU - Zhang, Yuanyuan
AU - Yang, Rui
AU - Yue, Yutao
AU - Gee Lim, Eng
N1 - Publisher Copyright:
© 1963-2012 IEEE.
PY - 2025/4/21
Y1 - 2025/4/21
N2 - Millimeter-wave radar is promising to provide robust and accurate vital sign monitoring unobtrusively. However, the radar signal might be distorted in propagation by ambient noise or random body movement (RBM), ruining the subtle cardiac activities and destroying the vital sign recovery. In particular, the recovery of electrocardiogram (ECG) signal heavily relies on the deep-learning model and is sensitive to noise. Therefore, this work creatively deconstructs the radar-based ECG recovery into three individual tasks and proposes a multitask learning (MTL) framework, radarODE-MTL, to increase the robustness against consistent and abrupt noises. In addition, to alleviate the potential conflicts in optimizing individual tasks, a novel multitask optimization strategy, eccentric gradient alignment (EGA), is proposed to dynamically trim the task-specific gradients based on task difficulties in orthogonal space. The proposed radarODE-MTL with EGA is evaluated on the public dataset with prominent improvements in accuracy, and the performance remains consistent under noises. The experimental results indicate that radarODE-MTL could reconstruct accurate ECG signals robustly from radar signals and imply the application prospect in real-life situations.
AB - Millimeter-wave radar is promising to provide robust and accurate vital sign monitoring unobtrusively. However, the radar signal might be distorted in propagation by ambient noise or random body movement (RBM), ruining the subtle cardiac activities and destroying the vital sign recovery. In particular, the recovery of electrocardiogram (ECG) signal heavily relies on the deep-learning model and is sensitive to noise. Therefore, this work creatively deconstructs the radar-based ECG recovery into three individual tasks and proposes a multitask learning (MTL) framework, radarODE-MTL, to increase the robustness against consistent and abrupt noises. In addition, to alleviate the potential conflicts in optimizing individual tasks, a novel multitask optimization strategy, eccentric gradient alignment (EGA), is proposed to dynamically trim the task-specific gradients based on task difficulties in orthogonal space. The proposed radarODE-MTL with EGA is evaluated on the public dataset with prominent improvements in accuracy, and the performance remains consistent under noises. The experimental results indicate that radarODE-MTL could reconstruct accurate ECG signals robustly from radar signals and imply the application prospect in real-life situations.
KW - Body movement
KW - contactless vital sign monitoring
KW - deep learning
KW - multitask learning (MTL)
KW - radio frequency sensing
UR - http://www.scopus.com/inward/record.url?scp=105003371199&partnerID=8YFLogxK
U2 - 10.1109/TIM.2025.3562975
DO - 10.1109/TIM.2025.3562975
M3 - Article
AN - SCOPUS:105003371199
SN - 0018-9456
VL - 74
JO - IEEE Transactions on Instrumentation and Measurement
JF - IEEE Transactions on Instrumentation and Measurement
M1 - 4008315
ER -