Combining Adaptive Filter and Phase Vocoder for Heart Rate Monitoring Using Photoplethysmography During Physical Exercise

This study presents a robust heart rate monitoring algorithm using photoplethysmography (PPG) signal during physical exercise. The proposed method combines two stage: motion artifact removal and frequency refinement. The cascaded normalized least mean square adaptive filter is used to attenuate the noise introduced by motion artifacts in the PPG signal. A phase vocoder technique is used to refine the frequency calculated by Fourier Transform, from which the heart rate is finally tracked. On a publicly available database of twelve PPG recordings, the proposed technique obtains an average absolute error (AAE) of 1.08 beat per minute (BPM). Person correlation coefficient of 0.997 is achieved between true heart rate and estimated heart rate. In contrast to other available approaches, the proposed method has merely one parameter to tune in spectral peak tracking step for heart rate estimation.