Heart Rate Estimation of PPG Signals With Simultaneous Accelerometry Using Adaptive Neural Network Filtering

Abstract

Motion artifacts (MA) are potent sources of noise in wearable photoplethysmography (PPG) signals and can impact the estimation of heart rate (HR) of an individual. In this paper, a method using adaptive neural network filters (ANNF) is proposed for accurate estimation of HR using dual channel PPG signals and simultaneous, three - dimensional acceleration signals. The MA cancellation method using ANNF, utilizes acceleration data as input signal. The PPG signals serve as a target, while the error is the clean PPG signal. The proposed method also includes a post-processing smoothing and median filter which improves the HR estimation. The reason for this approach is that the acceleration signal in wearables are only within 3% of the ground truth value. Experimental results on datasets recorded from 12 subjects, publicly available, showed that the proposed algorithm achieves an absolute error of 1.15 beats per minute (BPM). The results also confirm that the proposed method is highly resilient to motion artifacts and maintains high accuracy for PPG estimation and compares favorably against other methods.