作者: Gleb Tcheslavski , A.A. (Louis) Beex
DOI: 10.1016/J.BSPC.2010.02.003
关键词:
摘要: This study aims at discrimination between various subject conditions and states on the basis of their electroencephalogram (EEG). For purpose such discrimination, phase synchrony (PS) coefficients were evaluated for two groups participants. Statistical tests – as two-factor ANOVA Kruskal–Wallis used to select sets EEG electrodes producing statistically different PS groups. The selected by Euclidean, weighted Mahalanobis distancebased classifiers, well classifier using a quadratic discriminant function, test suitability reliable discrimination. method above has been tested smokers non-smokers, high low schizotypy individuals, experimental eyes open closed. We have observed that average � 1 rhythm is higher non-smokers than also non-smokers. showed differences are significant 99% significance level number electrode pairs. all other participants On hand, individuals do not exceed within-group variations. These observations may support hypothesis nicotine self-medication in schizophrenia patients. closed condition, was be condition. Euclidean distance-based showed, average, better 80% correct classification while subset available pairs (i.e., masking). could useful, instance, automated vigilance monitoring.