An Unobtrusive System for Heart Rate Monitoring Based on Ballistocardiogram Using Hilbert Transform and Viterbi Decoding

This paper presents an unobtrusive system for monitoring heart rate (HR) based on ballistocardiogram (BCG). The system contains a piezoelectric sensor, which can be embedded into a chair or bed, to convert small body vibrations caused by heart beating into BCG signal and a novel algorithm to estimate HR from the BCG. The algorithm employs the Hilbert Transform to reveal the frequency content of J-peak in the BCG signal for HR estimation. The Viterbi Decoding is applied to improve the HR accuracy for noisy BCG signal by finding the most likely path through time-frequency state-space plane. The performance of the proposed algorithm is evaluated by BCG recordings from 32 subjects. Mean absolute error (MAE) of 2.17 beats per minute (BPM) and standard deviation of absolute error (SDAE) of 2.34 BPM are achieved. Pearson correlation coefficient of 0.956 between estimated HR and true HR is obtained.