Fig. 8.

Results of common feature set analysis: a Number of selected features and average classification accuracy are shown for hemispheric asymmetry features (DATFPS17) with respect to different p value thresholds as DATFPS17 feature set yielded the best accuracy among all common feature sets. b Grouped sensitivity and specificity performance (in %) are shown in bar plots with error bars that indicate standard deviation (SE) along all subjects. c Presentation of occurrence count of dominant features. Band-wise dominant features for each subject is shown for DATFPS17 features type. Among five EEG frequency bands, maximum selected features belonged from alpha frequency band. d Temporal course of occurrence count of dominant features. Error bars indicate SEM along all subjects