Heart Rate Estimation from Ballistocardiography Based on Hilbert Transform and Phase Vocoder

TL;DR

This paper introduces a novel method combining Hilbert Transform and phase vocoder to improve heart rate estimation accuracy from ballistocardiography signals, outperforming traditional FFT-based methods.

Contribution

The proposed algorithm enhances HR estimation from BCG signals by integrating Hilbert Transform and phase vocoder, addressing limitations of FFT-based approaches.

Findings

Mean absolute error of 0.90 BPM in HR estimation

Pearson correlation coefficient of 0.98 with ground truth

Effective in experiments with 7 subjects

Abstract

This paper presents a robust method to monitor heart rate (HR) from BCG (Ballistocardiography) signal, which is acquired from the sensor embedded in a chair or a mattress. The proposed algorithm addresses the shortfalls in traditional Fast Fourier Transform (FFT) based approaches by introducing Hilbert Transform to extract the pulse envelope that models the repetition of J-peaks in BCG signal. The frequency resolution is further enhanced by applying FFT and phase vocoder to the pulse envelope. The performance of the proposed algorithm is verified by experiment from 7 subjects. For HR estimation, mean absolute error (MAE) of 0.90 beats per minute (BPM) and standard deviation of absolute error (STD) of 1.14 BPM are obtained. Pearson correlation coefficient between estimated HR and ground truth HR of 0.98 is also achieved.