Independent component analysis applied to the P600 component of event-related potentials

Ventouras, E; Moatsos, M; Papageorgiou, C; Rabavilas, A; Uzunoglu, N

dc.contributor.author	Ventouras, E	en
dc.contributor.author	Moatsos, M	en
dc.contributor.author	Papageorgiou, C	en
dc.contributor.author	Rabavilas, A	en
dc.contributor.author	Uzunoglu, N	en
dc.date.accessioned	2014-03-01T02:42:48Z
dc.date.available	2014-03-01T02:42:48Z
dc.date.issued	2004	en
dc.identifier.issn	05891019	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31091
dc.subject	Blind Source Separation (BSS)	en
dc.subject	Event-related Potentials (ERPs)	en
dc.subject	Independent Component Analysis (ICA)	en
dc.subject	P600 component	en
dc.subject.other	Algorithms	en
dc.subject.other	Blind source separation	en
dc.subject.other	Data processing	en
dc.subject.other	Linear systems	en
dc.subject.other	Patient monitoring	en
dc.subject.other	Biomedical signals	en
dc.subject.other	Event-related potentials (ERP)	en
dc.subject.other	P600 components	en
dc.subject.other	Independent component analysis	en
dc.title	Independent component analysis applied to the P600 component of event-related potentials	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IEMBS.2004.1403095	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IEMBS.2004.1403095	en
heal.publicationDate	2004	en
heal.abstract	The analysis of the P600 component of Event-related Potentials (ERPs) has attracted attention due to its relation to covert cognitive mechanisms, in connection to memory processes. The component may often be low-amplitude, compared to other components such as the P300. Independent Component Analysis (ICA) techniques have been successfully applied in ERP processing, in the framework of Blind Source Separation (BSS) for unmixing recorded potentials into a sum of temporally independent and spatially fixed components. In the present work ICA was used for reconstructing averaged ERPs in the time window of the P600 component, selecting a subset of independent components' projections to the original electrode recording positions. The selection is based on two empirical criteria, selecting the projection that reconstructs a P600 nearest temporally to the original P600, or selecting the projection combination - up to a preselected maximum number of combined projections - providing maximum reconstructed P600 amplitude. The techniques are tested on ERPs recorded from healthy subjects and psychiatric patients, notably improving the differentiation of the two groups, based on either the amplitude or the latency of the reconstructed P600 component, in comparison to results achieved using the original ERPs.	en
heal.journalName	Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings	en
dc.identifier.doi	10.1109/IEMBS.2004.1403095	en
dc.identifier.volume	26 I	en
dc.identifier.spage	80	en
dc.identifier.epage	83	en