Automatic sleep staging using multi-dimensional feature extraction and multi-kernel fuzzy support vector machine

This paper employed the clinical Polysomnographic (PSG) data, mainly including all-night Electroencephalogram (EEG), Electrooculogram (EOG) and Electromyogram (EMG) signals of subjects, and adopted the American Academy of Sleep Medicine (AASM) clinical staging manual as standards to realize automati...

Full description

Saved in:
Bibliographic Details
Published in:Journal of healthcare engineering 2014, Vol.5 (4), p.505-520
Main Authors: Zhang, Yanjun, Zhang, Xiangmin, Liu, Wenhui, Luo, Yuxi, Yu, Enjia, Zou, Keju, Liu, Xiaoliang
Format: Article
Language:English
Subjects:
Adult
Aged
Electrodiagnosis - methods
Female
Fuzzy Logic
Humans
Male
Middle Aged
Polysomnography - methods
Signal Processing, Computer-Assisted
Sleep Stages - physiology
Support Vector Machine
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper employed the clinical Polysomnographic (PSG) data, mainly including all-night Electroencephalogram (EEG), Electrooculogram (EOG) and Electromyogram (EMG) signals of subjects, and adopted the American Academy of Sleep Medicine (AASM) clinical staging manual as standards to realize automatic sleep staging. Authors extracted eighteen different features of EEG, EOG and EMG in time domains and frequency domains to construct the vectors according to the existing literatures as well as clinical experience. By adopting sleep samples self-learning, the linear combination of weights and parameters of multiple kernels of the fuzzy support vector machine (FSVM) were learned and the multi-kernel FSVM (MK-FSVM) was constructed. The overall agreement between the experts' scores and the results presented was 82.53%. Compared with previous results, the accuracy of N1 was improved to some extent while the accuracies of other stages were approximate, which well reflected the sleep structure. The staging algorithm proposed in this paper is transparent, and worth further investigation.
ISSN:2040-2295
2040-2309
DOI:10.1260/2040-2295.5.4.505