Change search
ReferencesLink to record
Permanent link

Direct link
Comparing a supervised and an unsupervised classification method for burst detection in neonatal EEG
University of Borås.
Chalmers University of Technology.
Neoventa AB.
Department of Clinical Neurophysiology, Institute of Neuroscience and Physiology, Sahlgrenska University Hospital, Göteborg, Sweden.
Show others and affiliations
2008 (English)In: Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology", IEEE , 2008, Vol. 2008, 3836-3839 p.Conference paper (Refereed)
Abstract [en]

Hidden Markov Models (HMM) and Support Vector Machines (SVM) using unsupervised and supervised training, respectively, were compared with respect to their ability to correctly classify burst and suppression in neonatal EEG. Each classifier was fed five feature signals extracted from EEG signals from six full term infants who had suffered from perinatal asphyxia. Visual inspection of the EEG by an experienced electroencephalographer was used as the gold standard when training the SVM, and for evaluating the performance of both methods. The results are presented as receiver operating characteristic (ROC) curves and quantified by the area under the curve (AUC). Our study show that the SVM and the HMM exhibit similar performance, despite their fundamental differences.

Place, publisher, year, edition, pages
IEEE , 2008. Vol. 2008, 3836-3839 p.
, IEEE Engineering in Medicine and Biology Society. Conference Proceedings, ISSN 1557-170X
National Category
Medical Engineering
URN: urn:nbn:se:kth:diva-75340DOI: 10.1109/IEMBS.2008.4650046ISI: 000262404502155PubMedID: 19163549ISBN: 978-1-4244-1814-5OAI: diva2:490482
30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08; Vancouver, BC; 20 August 2008 through 25 August 2008
QC 20120222Available from: 2012-02-05 Created: 2012-02-05 Last updated: 2012-02-22Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textPubMed

Search in DiVA

By author/editor
Lindecrantz, Kaj
Medical Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 35 hits
ReferencesLink to record
Permanent link

Direct link