A Cross-Modal Autoencoder for Contactless Electrocardiography Monitoring Using Frequency-Modulated Continuous Wave Radar

While traditional electrocardiogram (ECG) monitoring provides vital clinical information, its electrode-based setup restricts patient movement. To address this limitation, contactless ECG monitoring using frequency-modulated continuous-wave (FMCW) radar and deep learning has been developed. However, such approaches face challenges owing to the limited availability of training data and inherent discrepancies between radar and ECG signals. This article introduces a novel approach to transforming high-fidelity ECG signals from millimeter-wave (mmWave) radar signals reflecting cardiac mechanical activity. The proposed method uses a cascade framework with a cross-modal autoencoder trained using joint waveforms, spectrograms, and deep feature losses. This strategy enables the model to leverage a pretrained ECG-to-ECG autoencoder and a cardiac event (CE) predictor for learning general ECG representations while simultaneously capturing time- and frequency-domain features from limited data. We evaluated the effectiveness of the proposed autoencoder model in terms of signal quality and CE integrity using ablation studies on data from 20 healthy participants. The model achieved high transformation accuracy with a cross correlation of 0.914 and average timing errors below 31 ms for critical ECG features. These findings demonstrate the feasibility and effectiveness of the proposed FMCW radar-based contactless ECG monitoring method, particularly in overcoming the limitations imposed by small datasets and domain discrepancies.