EEG Signals Classification Based on Wavelet Transform and a New Statistical Feature

In this paper, we use a new set of statistic feature for the Electroencephalogram (EEG) signals classification. The EEG signals are decomposed into the frequency sub-bands using discrete wavelet transform (DWT). A set of statistical features is extracted from each sub-band to represent the distribution of wavelet coefficients. We propose three new statistical features, Fourth moment, betwixt maximum and minimum and zero-crossing. These features cause to improve Correct Classification rate (CCR). Next, we use a linear discriminant analysis (LDA) and Principal component analysis (PCA) for decrease the dimension of features. Then these features are classified by multilayer perceptron (MLP) with three discrete outputs: healthy volunteers, epilepsy patients during seizure-free interval and epilepsy patients during seizure. Experimental results on a set of EEG signals from Andrzejak et al (2001) data base show a good performance achieved by the proposed method in comparison with some recent methods

Keywords:

EEG signal , DWT , LDA , PCA , and MLP