EEG sleep stages classification based on time domain features and structural graph similarity

Diykh, Mohammed and Li, Yan and Wen, Peng (2016) EEG sleep stages classification based on time domain features and structural graph similarity. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 24 (11). pp. 1159-1168. ISSN 1534-4320


Abstract-The electroencephalogram (EEG) signals are commonly used in diagnosing and treating sleep disorders. Many existing methods for sleep stages classification mainly depend on the analysis of EEG signals in time or frequency domain to obtain a high accuracy of classification. In this paper, a novel method is proposed, which uses the statistical features in time domain and the structural graph similarity combined with k-means (SGSKM) to identify six sleep stages using a single channel EEG signals. Firstly, each EEG segment is partitioned into sub-segments. The size of a sub-segment is determined empirically. Secondly, statistical features are extracted and different sets of features are forwarded to the SGSKM to classify EEG sleep stages. We have also investigated the relation between sleep stages and the time domain features of the EEG data. The experimental results show that the proposed method yields better classification results compared to other four existing methods and the support vector machine (SVM) classifier. A 95.93% average classification accuracy is achieved by the proposed method.

Statistics for USQ ePrint 29382
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Additional Information: Files associated with this item cannot be displayed due to copyright restrictions.
Faculty / Department / School: Current - Faculty of Health, Engineering and Sciences - School of Agricultural, Computational and Environmental Sciences
Date Deposited: 06 Jul 2016 06:08
Last Modified: 06 Mar 2018 06:36
Uncontrolled Keywords: EEG signal; structural graph similarity; time domain features; sleep stages
Fields of Research : 08 Information and Computing Sciences > 0803 Computer Software > 080301 Bioinformatics Software
Socio-Economic Objective: E Expanding Knowledge > 97 Expanding Knowledge > 970111 Expanding Knowledge in the Medical and Health Sciences
Identification Number or DOI: 10.1109/TNSRE.2016.2552539

Actions (login required)

View Item Archive Repository Staff Only