A time-frequency approach for newborn seizure detection

QSpace/Manakin Repository

A time-frequency approach for newborn seizure detection

Show simple item record


dc.contributor.author Boashash, Boualem
dc.contributor.author Mesbah, Mostefa
dc.date.accessioned 2011-04-28T14:17:34Z
dc.date.available 2011-04-28T14:17:34Z
dc.date.issued 2001-09
dc.identifier.citation IEEE Engineering in Medicine and Biology Magazine, Vol. 20, No. 5, pp 30-38 en_US
dc.identifier.issn 0739-5175
dc.identifier.uri http://hdl.handle.net/10576/10673
dc.description A time-frequency approach to newborn EEG seizure detection shows that seizures can be modeled as piece-wise linear FM signals. en_US
dc.description.abstract Techniques previously designed for seizure detection in newborns using the electroencephalogram (EEG) have been relatively inefficient due to their assumption of local stationarity of the EEG. To overcome the problem raised by the nonstationarity of the EEG signal, current methods are extended to a time-frequency approach. This allows the analysis and characterization of the different newborn EEG patterns that are intended to be the first step toward an automatic time-frequency seizure detection and classification. An in-depth analysis of both the autocorrelation and spectrum seizure detection techniques identified the detection criteria that can be extended to the time-frequency domain. The selected method uses a high-resolution reduced interference time-frequency distribution referred to as the B-distribution (BD). Here, the authors present the various patterns of observed time-frequency seizure signals and relate them to current knowledge of seizures. In particular, initial results indicate that a quasilinear instantaneous frequency (IF) can be used as a critical feature of the EEG seizure characteristics. en_US
dc.description.sponsorship IEEE Engineering in Medicine and Biology Society en_US
dc.language.iso en en_US
dc.publisher IEEE en_US
dc.subject EEG seizure detection and classification en_US
dc.subject newborn en_US
dc.subject time-frequency analysis en_US
dc.subject multicomponent signals en_US
dc.subject B distribution en_US
dc.subject piece-wise linear FM signal en_US
dc.subject EEG background en_US
dc.subject burst suppression en_US
dc.title A time-frequency approach for newborn seizure detection en_US
dc.type Article en_US

Files in this item

Files Size Format View
Boashash-Mesbah ... born seizure detection.pdf 12.30Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search QSpace


Advanced Search

Browse

My Account