Exploring temporal information in neonatal seizures using a dynamic time warping based SVM kernel.

Journal: Computers in biology and medicine
Published Date: Mar 1, 2017

Abstract

Seizure events in newborns change in frequency, morphology, and propagation. This contextual information is explored at the classifier level in the proposed patient-independent neonatal seizure detection system. The system is based on the combination of a static and a sequential SVM classifier. A Gaussian dynamic time warping based kernel is used in the sequential classifier. The system is validated on a large dataset of EEG recordings from 17 neonates. The obtained results show an increase in the detection rate at very low false detections per hour, particularly achieving a 12% improvement in the detection of short seizure events over the static RBF kernel based system.

Authors

  • Rehan Ahmed
    Neonatal Brain Research Group, Irish Centre for Fetal and Neonatal Translational Research (INFANT), Ireland; Department of Electrical and Electronics Engineering, University College Cork, Ireland. Electronic address: rehan@eleceng.ucc.ie.
  • Andriy Temko
    Neonatal Brain Research Group, Irish Centre for Fetal and Neonatal Translational Research (INFANT), Ireland; Department of Electrical and Electronics Engineering, University College Cork, Ireland.
  • William P Marnane
    Irish Centre for Fetal and Neonatal Translational Research (INFANT), Ireland; Department of Electrical and Electronic Engineering, University College Cork, Ireland.
  • Geraldine Boylan
    Neonatal Brain Research Group, Irish Centre for Fetal and Neonatal Translational Research (INFANT), Ireland; Department of Pediatrics and Child Health, University College Cork, Ireland.
  • Gordon Lightbody
    Neonatal Brain Research Group, Irish Centre for Fetal and Neonatal Translational Research (INFANT), Ireland; Department of Electrical and Electronics Engineering, University College Cork, Ireland.

Keywords

External Resources

Popular Topics
Recent Journals