Please use this identifier to cite or link to this item: http://hdl.handle.net/11400/4769
Title: Cross-validation and neural network architecture selection for the classification of intracranial current sources
Authors: Βάσιος, Χρήστος
Ματσόπουλος, Γεώργιος Κ.
Βεντούρας, Ερρίκος Μ.
Νικήτα, Κωνσταντίνα Σ.
Ουζούνογλου, Νικόλαος Κ.
Item type: Conference publication
Conference Item Type: Full Paper
Keywords: VAR model;Bioelectric potentials;Αυτοπαλίνδρομες διαδικασίες;Βιοηλεκτρικό δυναμικό
Subjects: Medicine
Ιατρική
Νευρωνικά δίκτυα (Επιστήμη των υπολογιστών)
Neural computers
Issue Date: 26-Jan-2015
2004
Publisher: IEEE
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 backpropagation algorithm under "leave-one-out cross-validation". The ANN is a multilayer 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 event-related potentials (ERP) using an algebraic reconstruction technique. Results implementing the proposed methodology provide classification rates of up to 93%.
Description: Proceedings of the 7th Seminar on Neural Network Applications in Electrical Engineering (NEUREL-2004)
Language: English
Citation: Vasios, C., Matsopoulos, G., Ventouras, E., Nikita, K. and Uzunoglu, N. (2004). Cross-validation and neural network architecture selection for the classification of intracranial current sources. In the 7th Seminar on Neural Network Applications in Electrical Engineering. pp. 151-158. Belgrade, 23th-25th September2004.
Conference: Seminar on Neural Network Applications in Electrical Engineering
Access scheme: Embargo
License: Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες
URI: http://hdl.handle.net/11400/4769
Appears in Collections:Δημοσιεύσεις

Files in This Item:
File Description SizeFormat 
62 - 2004 - Neurel 2004 - Vasios et al - Cross-validation.pdf
  Restricted Access
656.46 kBAdobe PDFView/Open Request a copy


This item is licensed under a Creative Commons License Creative Commons