Skip to content Home Contact Mobile MyRMIT Library A-Z
RMIT UniversityResearch Repository
 

Analysis of sleep EEG activity during hypopnoea episodes by least squares support vector machine employing AR coefficients

Übeyli, E, Cvetkovic, D, Holland, G and Cosic, I 2010, 'Analysis of sleep EEG activity during hypopnoea episodes by least squares support vector machine employing AR coefficients', Expert Systems with Applications, vol. 37, no. 6, pp. 4463-4467.

Document type: Journal Article
Collection: Journal Articles

Title Analysis of sleep EEG activity during hypopnoea episodes by least squares support vector machine employing AR coefficients
Author(s) Übeyli, E
Cvetkovic, D
Holland, G
Cosic, I
Year 2010
Journal name Expert Systems with Applications
Volume number 37
Issue number 6
Start page 4463
End page 4467
Total pages 5
Publisher Pergamon
Abstract This paper presents the application of least squares support vector machines (LS-SVMs) for automatic detection of alterations in the human electroencephalogram (EEG) activities during hypopnoea episodes. The obstructive sleep apnoea hypopnoea syndrome (OSAH) means ¿cessation of breath¿ during the sleep hours and the sufferers often experience related changes in the electrical activity of the brain and heart. Decision making was performed in two stages: feature extraction by computation of autoregressive (AR) coefficients and classification by the LS-SVMs. The EEG signals (pre and during hypopnoea) from three electrodes (C3, C4 and O2) were used as input patterns of the LS-SVMs. The performance of the LS-SVMs was evaluated in terms of training performance and classification accuracies and the results confirmed that the proposed LS-SVM has potential in detecting changes in the human EEG activity due to hypopnoea episodes.
Keyword(s) AR coefficients
Electroencephalogram (EEG)
Least squares support vector machines
Sleep apnoea hypopnoea
Copyright notice © 2009 Elsevier Ltd. All rights reserved.
ISSN 0957-4174
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 2 times in TR Web of Science
Scopus Citation Count Cited 2 times in Scopus Article | Citations
Access Statistics: 27 Abstract Views  -  Detailed Statistics
Created: Wed, 17 Nov 2010, 16:09:00 EST by Catalyst Administrator