HeartBEAT: Heart Beat Estimation through Adaptive Tracking

TL;DR

HeartBEAT is an adaptive algorithm that accurately estimates heart rate from wrist PPG signals by removing motion artifacts, validated on diverse physical activity datasets with superior correlation metrics.

Contribution

This paper introduces HeartBEAT, a novel adaptive filtering approach for robust heart rate estimation from wrist PPG signals during various physical activities.

Findings

HeartBEAT achieves high correlation with ground truth ECG signals.

It outperforms existing algorithms in Spearman's rho and Kendall's tau.

Effective motion artifact removal during physical activities.

Abstract

In this paper, we propose an algorithm denoted as HeartBEAT that tracks heart rate from wrist-type photoplethysmography (PPG) signals and simultaneously recorded three-axis acceleration data. HeartBEAT contains three major parts: spectrum estimation of PPG signals and acceleration data, elimination of motion artifacts in PPG signals using recursive least Square (RLS) adaptive filters, and auxiliary heuristics. We tested HeartBEAT on the 22 datasets provided in the 2015 IEEE Signal Processing Cup. The first ten datasets were recorded from subjects performing forearm and upper-arm exercises, jumping, or pushing-up. The last twelve datasets were recorded from subjects running on tread mills. The experimental results were compared to the ground truth heart rate, which comes from simultaneously recorded electrocardiogram (ECG) signals. Compared to state-of-the-art algorithms, HeartBEAT not only produces comparable Pearson's correlation and mean absolute error, but also higher Spearman's rho and Kendall's tau.