Cross-validated classification of Intracranial Sources extracted by BET-ART method

Vasios, CE; Matsopoulos, GK; Ventouras, EM; Papageorgiou, C; Kontaxakis, VP; Nikita, KS; Uzunoglu, N

dc.contributor.author	Vasios, CE	en
dc.contributor.author	Matsopoulos, GK	en
dc.contributor.author	Ventouras, EM	en
dc.contributor.author	Papageorgiou, C	en
dc.contributor.author	Kontaxakis, VP	en
dc.contributor.author	Nikita, KS	en
dc.contributor.author	Uzunoglu, N	en
dc.date.accessioned	2014-03-01T02:43:11Z
dc.date.available	2014-03-01T02:43:11Z
dc.date.issued	2005	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31287
dc.subject	Algebraic Reconstruction Technique	en
dc.subject	Artificial Neural Network	en
dc.subject	Autoregressive Model	en
dc.subject	Back Propagation Algorithm	en
dc.subject	Cross Validation	en
dc.subject	Feature Extraction	en
dc.subject	Simulated Annealing	en
dc.subject	Leave One Out Cross Validation	en
dc.subject	Multi Layer Perceptron	en
dc.subject	Normal Control	en
dc.subject.other	Algebra	en
dc.subject.other	Classification (of information)	en
dc.subject.other	Feature extraction	en
dc.subject.other	Mathematical models	en
dc.subject.other	Regression analysis	en
dc.subject.other	Simulated annealing	en
dc.subject.other	Artificial Neural Network (ANN)	en
dc.subject.other	Back-propagation algorithm	en
dc.subject.other	Multivariate Autoregressive model	en
dc.subject.other	Schizophrenic patients	en
dc.subject.other	Patient treatment	en
dc.title	Cross-validated classification of Intracranial Sources extracted by BET-ART method	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/CNE.2005.1419573	en
heal.identifier.secondary	http://dx.doi.org/10.1109/CNE.2005.1419573	en
heal.identifier.secondary	1419573	en
heal.publicationDate	2005	en
heal.abstract	In the present paper, a new methodological approach, for the classification of first episode schizophrenic patients (FES) against normal controls, is proposed. The first step of the methodology applied is the feature extraction, which is based on the combination of the Multivariate Autoregressive model with the Simulated Annealing technique, in order to extract optimum features, in terms of classification rate. The classification, as the second step of the methodology, is implemented by means of an Artificial Neural Network (ANN) trained with the back-propagation algorithm under ""leave-one-out cross-validation"". The ANN is a multi-layer perceptron, the architecture of which, is selected after a detailed search. The proposed methodology has been applied for the classification of FES patients and normal controls using as input signals the intracranial current sources obtained by the inversion of ERPs using an Algebraic Reconstruction Technique. Results by implementing the proposed methodology provide classification rates of up to 93.1%. © 2005 IEEE.	en
heal.journalName	2nd International IEEE EMBS Conference on Neural Engineering	en
dc.identifier.doi	10.1109/CNE.2005.1419573	en
dc.identifier.volume	2005	en
dc.identifier.spage	140	en
dc.identifier.epage	143	en