Please use this identifier to cite or link to this item:
|Title:||SVM-based discrimination of one-month abstinent alcoholics from healthy controls using the P600 component of ERP signals|
Βεντούρας, Ερρίκος Μ.
Λιάππας, Ιωάννης Α.
Ραμπαβίλας, Ανδρέας Ν.
Κάβουρας, Διονύσης Α.
|Item type:||Conference publication|
|Conference Item Type:||Full Paper|
|Keywords:||Alcoholics;Pattern recognition;Αλκοολικοί;Αναγνώριση προτύπων|
|Abstract:||The aim of this study was to design a computer-based classification system capable of distinguishing one-month abstinent alcoholics from normal controls by Event-related potential (ERP) signals using the P600 component. Clinical material comprised twenty one-month abstinent alcoholics and an equal number of gender and aged-matched healthy controls. All subjects were evaluated by a computerized version of the digit span Wechsler test. EEG activity was recorded and digitized from 15 scalp electrodes (leads). A dedicated computer software was developed and it was used to read the ERP signals and to calculate features related to the P600 component (500-800 ms) of the ERP signal. Nineteen features were generated and were employed in the design of an optimum SVM-classifier at each lead. The outcomes of those SVM-classifiers were selected by a majority-vote engine (MVE), which assigned each subject to either the normal or alcoholic classes. MVE-classification accuracy was 97.5% when using all leads and 92.5% or 77.5% when using only the right or left scalp leads respectively. These findings provide evidence of right hemisphere dysfunction in alcoholics affecting the processing of information that assigns a specific response to a specific stimulus, as those mechanisms are reflected by the P600 component of ERPs.|
|Description:||Proceedings of the 1st International Conference “From Scientific Computing to Computational Engineering” (1ST IC-SCCE) (CD-ROM).|
|Citation:||Kalatzis, I., Piliouras, N., Ventouras, E., Papageorgiou, C., Liappas, I., et al. (2004). SVM-based discrimination of one-month abstinent alcoholics from healthy controls using the P600 component of ERP signals. In the 1st International Conference “From Scientific Computing to Computational Engineering. University of Patras: Athens, 8th-10th September 2004.|
|Conference:||International Conference From Scientific Computing to Computational Engineering|
|License:||Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες|
|Appears in Collections:||Δημοσιεύσεις|
Files in This Item:
|61 - 2004 - 1st IC-SCCE - Kalatzis.pdf|
|392.84 kB||Adobe PDF||View/Open Request a copy|
This item is licensed under a Creative Commons License