An SVM-based system and its performance for detection of seizures in neonates

Author

Temko, Andriy ; Thomas, Eoin ; Boylan, Geraldine ; Marnane, William ; Lightbody, Gordon

Author_Institution

Dept. of Electr. & Electron. Eng., Univ. Coll. Cork, Cork, Ireland

fYear

2009

fDate

3-6 Sept. 2009

Firstpage

2643

Lastpage

2646

Abstract

This work presents a multi-channel patient-independent neonatal seizure detection system based on the SVM classifier. Several post-processing steps are proposed to increase temporal precision and robustness of the system and their influence on performance is shown. The SVM-based system is evaluated on a large clinical dataset using several epoch-based and event based metrics and curves of performance are reported. Additionally, a new metric to measure the average duration of a false detection is proposed to accompany the event-based metrics.

Keywords

electroencephalography; neurophysiology; patient diagnosis; support vector machines; SVM classifier; event based metrics; neonatal seizure detection; robustness; support vector machine; temporal precision; Algorithms; Automation; Computer Simulation; Data Interpretation, Statistical; Electroencephalography; Equipment Design; Humans; Infant, Newborn; Neural Networks (Computer); Pattern Recognition, Automated; ROC Curve; Reproducibility of Results; Seizures; Sensitivity and Specificity; Signal Processing, Computer-Assisted;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE

Conference_Location

Minneapolis, MN

ISSN

1557-170X

Print_ISBN

978-1-4244-3296-7

Electronic_ISBN

1557-170X

Type

conf

DOI

10.1109/IEMBS.2009.5332807

Filename

5332807