Multivariate autoregressive modeling combined with simulated annealing optimization for classifying sources of event related potentials

dc.contributor.author	Βάσιος, Χρήστος	el
dc.contributor.author	Ματσόπουλος, Γεώργιος Κ.	el
dc.contributor.author	Βεντούρας, Ερρίκος Μ.	el
dc.contributor.author	Παπαγεωργίου, Χαράλαμπος	el
dc.contributor.author	Κονταξάκης, Βασίλειος Π.	el
dc.date.accessioned	2015-01-26T06:39:30Z
dc.date.issued	2015-01-26
dc.identifier.uri	http://hdl.handle.net/11400/4733
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.subject	Multivariate autoregression
dc.subject	Simulated annealing (Mathematics)
dc.subject	Πολυπαραγοντική αυτοπαλινδρόμηση
dc.subject	Προσομοιωμένη ανόπτηση
dc.title	Multivariate autoregressive modeling combined with simulated annealing optimization for classifying sources of event related potentials	en
heal.type	journalArticle
heal.generalDescription	Proceedings of the 5th International Conference on Bioelectromagnetism and 5th International Symposium on Non-invasive Functional Source Imaging within the Human Brain and Heart	en
heal.classification	Medicine
heal.classification	Medical technology
heal.classification	Ιατρική
heal.classification	Ιατρικά όργανα και εξοπλισμός
heal.classificationURI	http://id.loc.gov/authorities/subjects/sh00006614
heal.classificationURI	http://skos.um.es/unescothes/C02465
heal.classificationURI	N/A-Ιατρική
heal.classificationURI	N/A-Ιατρικά όργανα και εξοπλισμός
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh88004495
heal.contributorName	Νικήτα, Κωνσταντίνα Σ.	el
heal.contributorName	Ουζούνογλου, Νικόλαος Κ.	el
heal.identifier.secondary	ISSN: 1456-7865
heal.dateAvailable	10000-01-01
heal.language	en
heal.access	forever
heal.recordProvider	Τ.Ε.Ι. Αθήνας. Σχολή Τεχνολογικών Εφαρμογών. Τμήμα Μηχανικών Βιοϊατρικής Τεχνολογίας Τ.Ε.	el
heal.publicationDate	2005
heal.bibliographicCitation	Vasios, C., Matsopoulos, G., Ventouras, E., Papageorgiou, C., Kontaxakis, C., et al. (2005). Multivariate autoregressive modeling combined with simulated annealing optimization for classifying sources of event related potentials. International Journal of Bioelectromagnetism. vol. 7. pp. 78-81. International Society for Bioelectromagnetism: Minneapolis, 10th-12th May 2005.	en
heal.abstract	Event-Related Potentials (ERPs) provide non-invasive measurements of the electrical activity on the scalp that are linked to the presentation of stimuli and events. Brain mapping techniques are able to provide evidence for the solution of debatable issues in cognitive science. In this paper, a two-step signal classification approach is proposed, extending the use of the Low Resolution Brain Electrical Tomography (LORETA) inversion technique. The first step concerns the feature extraction module, which is based on the combination of the Multivariate Autoregressive model with the Simulated Annealing technique. The classification module, as the second step of the methodology, is implemented by means of an Artificial Neural Network (ANN) trained with the backpropagation algorithm under “leave-one-out crossvalidation”. 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 first episode schizophrenic patients and normal controls using as input signals the intracranial current sources obtained by the inversion of ERPs using the LORETA technique. Results by implementing the proposed methodology provide classification rates of up to 93.1%. Finally, the proposed methodology may be used for the design of more robust classifiers based on the head-surface measured potentials as well as on the intracranial source locations, which directly relate to cognitive mechanisms.	en
heal.publisher	International Society for Bioelectromagnetism	en
heal.journalName	International Journal of Bioelectromagnetism	en
heal.journalType	peer-reviewed
heal.fullTextAvailability	true