radarODE: An ODE-Embedded Deep Learning Model for Contactless ECG Reconstruction from Millimeter-Wave Radar

2024-08-03

IEEE Transactions on Mobile Computing

AI Summary

This study addresses the distortion problem in contactless electrocardiogram (ECG) reconstruction from millimeter-wave radar signals, arising from the coupling between electrophysiological activity and mechanical cardiac motion. We propose an end-to-end deep learning framework that jointly leverages temporal modeling and morphological priors: (1) for the first time, an ordinary differential equation (ODE) module is embedded in the decoder to explicitly model ECG waveform dynamics; (2) multi-scale temporal feature extraction is integrated with morphology-aware constraints to enhance motion robustness and training stability. Evaluated on a public benchmark dataset, our method reduces false-negative detection rate by 9%, decreases root-mean-square error (RMSE) by 16%, and improves Pearson correlation coefficient by 19% over state-of-the-art baselines. The approach achieves high-fidelity, interference-resilient contactless ECG reconstruction and demonstrates practical deployability in real-world scenarios.

Technology Category

• Machine Learning: Multimodal Learning
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Radar-based contactless cardiac monitoring has become a popular research direction recently, but the fine-grained electrocardiogram (ECG) signal is still hard to reconstruct from millimeter-wave radar signal. The key obstacle is to decouple the cardiac activities in the electrical domain (i.e., ECG) from that in the mechanical domain (i.e., heartbeat), and most existing research only uses pure data-driven methods to map such domain transformation as a black box. Therefore, this work first proposes a signal model for domain transformation, and then a novel deep learning framework called radarODE is designed to fuse the temporal and morphological features extracted from radar signals and generate ECG. In addition, ordinary differential equations are embedded in radarODE as a decoder to provide morphological prior, helping the convergence of the model training and improving the robustness under body movements. After being validated on the dataset, the proposed radarODE achieves better performance compared with the benchmark in terms of missed detection rate, root mean square error, Pearson correlation coefficient with the improvement of 9%, 16% and 19%, respectively. The validation results imply that radarODE is capable of recovering ECG signals from radar signals with high fidelity and can be potentially implemented in real-life scenarios.

Problem

• Reconstructing ECG signals from millimeter-wave radar contactlessly
• Decoupling cardiac activities in electrical and mechanical domains
• Improving robustness and accuracy in ECG signal recovery

Innovation

• ODE-embedded deep learning for ECG reconstruction
• Fuses temporal and morphological radar features
• Uses differential equations as morphological prior