Multivariate Signal Decomposition for Vital Signal Extraction using UWB Impulse Radar

Remote sensing of vital signals, including respiration and heartbeat, is an important application used in smart homes, smart hospitals, or car driver assistant systems. Ultra-wideband impulse (UWB) radar recently became popular because of its ability to sense tiny motions from breathing and cardiac activities. The heartbeat signal is in order of magnitudes smaller than the respiration signal and is usually buried in a noisy signal. In this research, we propose a multivariate signal decomposition for efficiently extracting the heartbeat signal. The results show that the proposed method significantly improves the accuracy of the signal-to-noise ratio of the heartbeat signal compared to the recent advanced methods such as wavelet transform, singular spectral analysis, and multivariate singular spectral analysis. The proposed method also improves the stability of heartbeat monitoring in real-time applications.