A data-driven energy based estimator of EEG channel importance for improved patient-adaptive neonatal seizure detector

Research output: Chapter in Book/Report/Conference proceedingsChapterpeer-review

Abstract

A measure of channel importance is proposed for EEG-based detection of neonatal seizures. The channel weights are computed based on the integrated synchrony of classifier probabilistic outputs for the channels which share a common electrode. Those estimated weights are introduced within Bayesian probabilistic framework to provide a channel-specific and thus patient-adaptive seizure detection scheme. Results of validation on a clinical dataset of neonatal seizures confirm the utility of the proposed channel weighting for the SVM-based detection system recently developed in this research group. Exploiting the channel weighting, the ROC area can be drastically increased for the most difficult patients, with the average ROC area across 17 patients increased by 22% relative.

Original languageEnglish
Title of host publicationProceedings of the 18th IFAC World Congress
PublisherIFAC Secretariat
Pages13770-13775
Number of pages6
Edition1 PART 1
ISBN (Print)9783902661937
DOIs
Publication statusPublished - 2011

Publication series

NameIFAC Proceedings Volumes (IFAC-PapersOnline)
Number1 PART 1
Volume44
ISSN (Print)1474-6670

Keywords

  • Channel selection
  • Classification
  • EEG
  • Neonatal seizure detection
  • Probability
  • Weighting

Fingerprint

Dive into the research topics of 'A data-driven energy based estimator of EEG channel importance for improved patient-adaptive neonatal seizure detector'. Together they form a unique fingerprint.

Cite this