Open AccessA High-Efficiency and Real-Time Method for Quality Evaluation of PPG Signals
Author(s) -
Hongxing Li,
Shizhao Huang
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/711/1/012100
Subject(s) - signal (programming language) , interference (communication) , computer science , correlation coefficient , pulse (music) , pattern recognition (psychology) , artificial intelligence , quality (philosophy) , physics , telecommunications , quantum mechanics , channel (broadcasting) , machine learning , detector , programming language
The pulse oximeter (POM) is a device for real-time detection of HR and SpO2 based on PPG (Photo Plethyamo Graphy) signals, and its detection accuracy varies with diverse interferences. Therefore, it is presented in the paper a method for quality evaluation of PPG signals to detect wavebands of interference signals. Firstly, features of PPG signals are acquired by slope weighted sum function (SSF). Then, the normalized cross-correlation coefficient of each signal and its reference signal is calculated. Finally, signal quality index (SQI) is calculated based on nonlinear scaling function. In the research, 20 PPG signals with 1469 beats are chosen from the CB database to make the experiments of signal quality evaluation. The experimental results show that the method included can effectively identify useful signals from the mixed signals. The sensitivity and positive prediction value are 94.66% and 96.78%, respectively. Consequently, the method proposed has high recognition accuracy with key significance in clinical applications.