Heart rate tracking in photoplethysmography signals affected by motion artifacts: a review

Abstract

Non-invasive photoplethysmography (PPG) technology was developed to track heart rate during motion. Automated analysis of PPG has made it useful in both clinical and non-clinical applications. However, PPG-based heart rate tracking is a challenging problem due to motion artifacts (MAs) which are main contributors towards signal degradation as they mask the location of heart rate peak in the spectra. A practical analysis system must have good performance in MA removal as well as in tracking. In this article, we have presented state-of-art techniques in both areas of the automated analysis, i.e., MA removal and heart rate tracking, and have concluded that adaptive filtering and multi-resolution decomposition techniques are better for MA removal and machine learning-based approaches are future perspective of heart rate tracking. Hence, future systems will be composed of machine learning-based trackers fed with either empirically decomposed signal or from output of adaptive filter.

Optimal Preprocessing of Raw Signals from Reflective Mode Photoplethysmography in Wearable Devices

“…Since modern wearable applications demand for these measures, this research concentrates on HR tracking algorithms applied in time domain. Before the pulse feature detection and validation takes place, usually preprocessing and motion artifact removal stages are applied [19], [40].…”

“…Consequently, the universal cardiac and respiratory frequency bands, for both infants and adults, overlap. The separation of the desired signal components from in-band noise, especially motion artifacts from daily activities such as walking and jogging (1.0 to 2.5 Hz), becomes even more challenging [18], [40].…”

An Adaptive Heart Rate Monitoring Algorithm for Wearable Healthcare Devices

“…Due to the high probability of the proximity of HR and motion artifact spectral peaks and spectral peak randomness, the removal of motion artifacts is an important preprocessing step in classical signal processing to calculate the HR from PPG. In [19], HR calculations were divided into four phases, including pre-filtering, motion artifact removal, peak detection, and peak tracking. Zong [20] addressed the HR tracking problem in two distinct stages: pre-filtering and peak tracking.…”

“…Ismail [19] showed that the Laplacian model exhibited the best fit for analyzing the d process. Based on the analytical results, the probability density function ( ) is given by the following:…”

Multi-Headed Conv-LSTM Network for Heart Rate Estimation during Daily Living Activities

“…The periodicity of measured light corresponds to the cardiac rhythm, which is used for HR estimation [ 6 ]. However, this method has one major drawback: during intense physical activity, the PPG signal is very susceptible to interference [ 7 ]. Reducing the influence of motion artifacts is currently a leading research direction in HR estimation.…”