Table of Contents Author Guidelines Submit a Manuscript
Journal of Healthcare Engineering
Volume 5, Issue 4, Pages 505-520
Research Article

Automatic Sleep Staging using Multi-dimensional Feature Extraction and Multi-kernel Fuzzy Support Vector Machine

Yanjun Zhang,1,3 Xiangmin Zhang,2 Wenhui Liu,3 Yuxi Luo,1 Enjia Yu,2 Keju Zou,1 and Xiaoliang Liu1

1School of Engineering, Sun Yat-sen University, Guangdong 510006, China
2Sleep-disordered Breathing Center of the 6th affiliated hospital, Sun Yat-Sen University, Guangdong 510655, China
3Jinan University, Guangdong 510632, China

Received 1 February 2014; Accepted 1 August 2014

Copyright © 2014 Hindawi Publishing Corporation. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


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.