A computer-aided detection of EEG seizures in infants: A singular-spectrum approach and performance comparison

Celka, P and Colditz, P (2002) A computer-aided detection of EEG seizures in infants: A singular-spectrum approach and performance comparison. Ieee Transactions On Biomedical Engineering, 49 5: 455-462.


Author Celka, P
Colditz, P
Title A computer-aided detection of EEG seizures in infants: A singular-spectrum approach and performance comparison
Journal name Ieee Transactions On Biomedical Engineering   Check publisher's open access policy
ISSN 0018-9294
Publication date 2002
Sub-type Article (original research)
DOI 10.1109/10.995684
Volume 49
Issue 5
Start page 455
End page 462
Total pages 8
Place of publication New York
Publisher Ieee-inst Electrical Electronics Engineers Inc
Language eng
Abstract This paper presents a scalp electroencephalogram (EEG) seizure detection scheme based on singular spectrum analysis (SSA) and Rissanen minimum description length (MDL) model-order selection (SSA-MDL). Preprocessing of the signals allows for the drastic reduction of the number of false alarms. Statistical performance comparison with seizure detection schemes of Gotman et al. and Liu et al. is performed on both synthetic data and real EEG seizures. Monte Carlo simulations based on synthetic infant EEG seizure data reveals some detection drawbacks on a large variety of seizure waveforms. Detection using both Monte Carlo and four real infant scalp EEG signals shows the superiority of the SSA-MDL method with an average good detection rate of > 93 % and false detection rate < 4 %.
Keyword Engineering, Biomedical
detection
EEG seizure
infant
MDL
newborn
singular spectrum analysis
Temporal-lobe Epilepsy
Value Decomposition
Newborn Eeg
Electroencephalogram
Dimension
Dynamics
Signals
Term
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Unknown

Document type: Journal Article
Sub-type: Article (original research)
Collections: Excellence in Research Australia (ERA) - Collection
School of Medicine Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 56 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 69 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Access Statistics: 123 Abstract Views  -  Detailed Statistics
Created: Wed, 17 Oct 2007, 11:11:29 EST