Key result
The proposed machine learning method for non-contact heart rate monitoring decreased the RMSE by 27% compared with state-of-the-art methods in stationary conditions and achieved an RMSE of 1.12 bpm in motion.
Why the study?
Does a machine learning method using RGB camera facial video improve the accuracy of non-contact heart rate monitoring compared to existing methods?
Does a machine learning method using RGB camera facial video improve the accuracy of non-contact heart rate monitoring compared to existing methods?
Effect estimate: 27% decrease in RMSE
A novel machine learning algorithm using RGB camera facial video significantly improves the accuracy of non-contact heart rate monitoring, even during subject movement.
May enhance non-contact heart rate monitoring in controlled settings; leaves open clinical adoption pending prospective validation.
Recording and monitoring vital signs is an essential part of home-based healthcare. Using contact sensors to record physiological signals can cause discomfort to patients, especially after prolonged use. Hence, remote physiological measurement approaches have attracted considerable attention, as they do not require physical contact with the patient's skin. Several studies proposed techniques to measure heart rate (HR) and heart rate variability by detecting the blood volume pulse from human facial video recordings while the subject is in a resting condition. In this paper, we focus on the measurement of HR. We adopt an algorithm that uses the independent component analysis (ICA) to separate the source (physiological) signal from noise in the RGB channels of a facial video. We generalize existing methods to support subject movement during video recording. Furthermore, we improve the accuracy of existing methods by implementing a light equalization scheme to reduce the effect of shadows and unequal facial light on the HR estimation, a machine learning method to select the most accurate channel outputted by the ICA module, and a regression technique to adjust the initial HR estimate. With respect to the ECG measurement ground truth, the proposed method decreases the RMSE by 27% compared with the state of the art in the stationary condition. When the subject is in motion, our proposed method achieves an RMSE of 1.12 bpm.
No takes yet. Share an insight, caveat, or question.
Ghanadian et al. (2018) studied Heart rate monitoring. Machine learning method using ICA and light equalization for non-contact HR monitoring vs. State of the art methods / ECG ground truth was evaluated on Heart rate estimation accuracy (RMSE) (27% decrease in RMSE). The proposed machine learning method for non-contact heart rate monitoring decreased the RMSE by 27% compared with state-of-the-art methods in stationary conditions and achieved an RMSE of 1.12 bpm in motion.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: