Gaussian mixture models for classification of neonatal seizures using EEG
- 28 June 2010
- journal article
- research article
- Published by IOP Publishing in Physiological Measurement
- Vol. 31 (7) , 1047-1064
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. A thorough review of all misclassified events was performed, from which a number of patterns causing false detections were identified.Keywords
This publication has 30 references indexed in Scilit:
- A Multistage System for the Automated Detection of Epileptic Seizures in Neonatal ElectroencephalographyJournal Of Clinical Neurophysiology, 2009
- Automated neonatal seizure detection mimicking a human observer reading EEGClinical Neurophysiology, 2008
- A multistage knowledge-based system for EEG seizure detection in newborn infantsClinical Neurophysiology, 2007
- Characterization of neonatal seizures by conventional EEG and single-channel EEGClinical Neurophysiology, 2007
- Treatment of neonatal seizuresArchives of Disease in Childhood - Fetal and Neonatal Edition, 2007
- Seizure detection algorithm for neonates based on wave-sequence analysisClinical Neurophysiology, 2006
- Automated neonatal seizure detection: A multistage classification system through feature selection based on relevance and redundancy analysisClinical Neurophysiology, 2006
- An evaluation of automated neonatal seizure detection methodsClinical Neurophysiology, 2005
- A system to detect the onset of epileptic seizures in scalp EEGClinical Neurophysiology, 2005
- Speaker Verification Using Adapted Gaussian Mixture ModelsDigital Signal Processing, 2000