Grading brain injury in neonatal EEG using SVM and supervector kernel

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

Abstract

Brain injury at the time of birth could lead to severe neurological dysfunction at an older age. Grading the brain injury in the early hours after birth could help doctors determine a prompt and reliable treatment. This work presents an automated neonatal EEG grading system based on a cross-disciplinary method of using Support Vector Machine and supervectors, initially developed for speaker identification. The EEG is classified into one of the four grades of neonatal brain injury. The preliminary results show promising performance and are an improvement on the previously published results.

Original languageEnglish
Title of host publication2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5894-5898
Number of pages5
ISBN (Print)9781479928927
DOIs
Publication statusPublished - 2014
Event2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 - Florence, Italy
Duration: 4 May 20149 May 2014

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Conference

Conference2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
Country/TerritoryItaly
CityFlorence
Period4/05/149/05/14

Fingerprint

Dive into the research topics of 'Grading brain injury in neonatal EEG using SVM and supervector kernel'. Together they form a unique fingerprint.

Cite this