Skip to main content

Advertisement

TableĀ 7 Comparison of the classification accuracy between the existing models and the best combination of features that produced by AMSKF technique on eye event-related EEG data

From: Feature selection using angle modulated simulated Kalman filter for peak classification of EEG signals

Peak model Feature subset length Selected features Training accuracy (%) Testing accuracy (%)
Dumpala 4 f 1, f 6, f 13, f 14 80.9 51.5
Acir 6 f 1, f 2, f 7, f 8, f 13, f 14 76.3 52.2
Liu 11 f 1, f 2, f 3, f 4, f 6, f 9, f 12, f 13, f 14, f 15, f 16 77.2 48.2
Dingle 4 f 5, f 6, f 13, f 14 71.4 40.1
AMSKF (proposed work) 11 f 1, f 2, f 7, f 8, f 9, f 10, f 11, f 12, f 13, f 14, f 15 91.8 72.7