Peer-Reviewed Journal Details
Mandatory Fields
Authors
Thomas, E; Temko, A; Lightbody, G; Marnane, W. P. and Boylan, G;
Year
2010
Month
July
Journal
Physiological Measurement
Title
Gaussian mixture models for classification of neonatal seizures using EEG
Status
Validated
Times Cited
()
Optional Fields
Keywords
Neonatal EEG seizure detection Gaussian mixture models EPILEPTIC SEIZURES SYSTEM ALGORITHM FEATURES INFANTS
Volume
31
Issue
7
Start Page
1047
End Page
1064
Abstract
A real-time neonatal seizure detection system is proposed based on a Gaussian mixture model classifier. The system includes feature transformation techniques and classifier output postprocessing. The detector was evaluated on a database of 20 patients with 330 h of recordings. A detailed analysis of the choice of parameters for the detector is provided. A mean good detection rate of 79% was obtained with only 0.5 false detections per hour. Athorough review of all misclassified events was performed, from which a number of patterns causing false detections were identified.
Publisher Location
United Kingdom
ISBN / ISSN
0967-3334
Edition
URL
http://iopscience.iop.org/0967-3334/
DOI Link
DOI 10.1088/0967-3334/31/7/013
Grant Details
Funding Body
Science Foundation Ireland
Grant Details
Science Foundation Ireland (SFI/05/PICA/1836), Wellcome Trust (085249/Z/08/Z)