A Supervised Learning Approach for Real Time Vital Sign Radar Harmonics Cancellation

摘要: Vital signs radar has proven to be an interesting and useful tool; however it is still limited by a few key problems. One of these the generation harmonics due nonlinearities arising from large signal amplitude respiration when compared that heartbeat. As result, arise in spectrum which confound accurate measurement either. The gamma filter supervised machine learning based approach offers calibration-free computationally efficient solution for many nonlinear filtering applications. Here, demonstrated first time as tool real-time heart rate estimation using baseband non-contact vital sign measured 5.8-GHz quadrature Doppler radar. Experimental results show proposed removing can accurately measure even if weak or overwhelmed respiratory movement.