Wavelet packet transform for feature extraction of EEG during mental tasks

Abstract

Wavelet packet transform (WPT) based feature extraction of the electroencephalogram (EEG) is introduced. Six-channel EEG data of four subjects were recorded while they performed three different mental tasks. Approximate one-second data segments were divided and transformed to multi-scale representations by dyadic wavelet packet decomposition channel by channel. Power values of different sub-spaces of six-channel EEG signals formed the feature vectors. A radial basis function (RBF) network was applied to classify the three task pairs. The average classification accuracy of four subjects over three task pairs is 85.3%. Compared with the two autoregressive (AR) model methods, wavelet packet transform would be a promising method to extract features from EEG signals.