Contactless ECG Reconstruction from Millimeter-Wave Radar Signals Using a CNN-BiLSTM Network

To investigate the feasibility of reconstructing electrocardiogram (ECG) waveforms from non-contact millimeter-wave radar measurements, a radar-based ECG reconstruction method using a CNN-BiLSTM network is presented. A synchronous acquisition platform integrating a millimeter-wave radar and a BIOPAC physiological signal acquisition system was established to collect chest-wall vibration signals and reference ECG signals. A multi-channel cross-correlation-based channel selection and temporal alignment procedure was employed to construct paired radar–ECG samples. The radar chest-wall vibration signals were filtered using an 8–30 Hz band-pass filter and then fed into the CNN-BiLSTM model, while a joint time–frequency loss function was introduced to constrain ECG reconstruction. On the self-built vital sign dataset, the reconstructed ECG achieved a correlation coefficient of 0.5631 with the reference ECG, while the mean absolute errors of heart rate and R–R interval were 1.00 BPM and 10.02 ms, respectively. These results suggest that the reconstructed signals preserve basic heartbeat timing and overall rhythm-related information, although the waveform-level agreement varies among samples and does not yet demonstrate consistent recovery of fine-grained ECG morphology. Evaluation on a public dataset further showed condition-dependent reconstruction performance under Resting, Apnea, and Valsalva conditions. Published MultiRes-LinkNet values were included only as contextual numerical references because the baseline was not reimplemented within the same experimental pipeline. Overall, the results provide preliminary evidence for the feasibility of contactless ECG reconstruction from millimeter-wave radar signals and suggest its potential value for radar-based vital sign monitoring.