The Automatic Sleep Scoring Method Based on Multiscale Entropy Analysis of EOG Signals

DOI: 10.5176/2251-3833_GHC12.45

Authors: Chih-En Kuo, Tsung-Hao Hsieh and Sheng-Fu Liang

Abstract: In this study, an automatic sleep scoring method based on multiscale entropy analysis of EOG signals was developed. Compared to EEG, EOG has the advantage of easy placement and can be measured by the user individually without help. We firstly applied MSE to analysis EOG to investigate the relations between changes of sleep stages and the MSE values. Compared to the single-scale sample entropy, we find that MSE has more powerful ability for sleep scoring. Then a MSE-based sleep scoring method for sleep EOG was developed. After training based on the data from 10 subjects, the overall sensitivity of the proposed automatic sleep scoring method combining MSE, autoregressive models, and linear discriminant analysis can reach 81.89{6e6090cdd558c53a8bc18225ef4499fead9160abd3419ad4f137e902b483c465} evaluated by the data of the other 10 subjects. Due resultant accuracy and using EOG recording only, the proposed method has good applicability for sleep monitoring at home

Keywords: Multiscale entropy (MSE), automatic sleep scoring, EOG, autoregressive (AR) model, linear discriminant analysis (LDA).