SPECMAR: Fast Heart Rate Estimation from PPG Signal using a Modified Spectral Subtraction Scheme with Composite Motion Artifacts Reference Generation

TL;DR

This paper introduces SPECMAR, a fast and accurate heart rate estimation algorithm from PPG signals that effectively reduces motion artifacts using a modified spectral subtraction scheme and composite motion artifacts reference generation, suitable for wearable devices.

Contribution

The paper presents a novel SPECMAR algorithm that combines spectral subtraction with composite motion artifacts reference generation for improved heart rate estimation from PPG signals.

Findings

Average heart rate estimation error of 2.09 BPM

Pearson correlation coefficient of 0.9907

Faster and low computational complexity than existing methods

Abstract

The task of heart rate estimation using photoplethysmographic (PPG) signal is challenging due to the presence of various motion artifacts in the recorded signals. In this paper, a fast algorithm for heart rate estimation based on modified SPEctral subtraction scheme utilizing Composite Motion Artifacts Reference generation (SPECMAR) is proposed using two-channel PPG and three-axis accelerometer signals. First, the preliminary noise reduction is obtained by filtering unwanted frequency components from the recorded signals. Next, a composite motion artifacts reference generation method is developed to be employed in the proposed SPECMAR algorithm for motion artifacts reduction. The heart rate is then computed from the noise and motion artifacts reduced PPG signal. Finally, a heart rate tracking algorithm is proposed considering neighboring estimates. The performance of the SPECMAR algorithm has been tested on publicly available PPG database. The average heart rate estimation error is found to be 2.09 BPM on 23 recordings. The Pearson correlation is 0.9907. Due to low computational complexity, the method is faster than the comparing methods. The low estimation error, smooth and fast heart rate tracking makes SPECMAR an ideal choice to be implemented in wearable devices.