Statistical Wavelet Features, Pca, And Svm Based Approach For Eeg Signals Classification

Abstract

The study of the electrical signals produced by neural<br> activities of human brain is called Electroencephalography. In this<br> paper, we propose an automatic and efficient EEG signal<br> classification approach. The proposed approach is used to classify the<br> EEG signal into two classes: epileptic seizure or not. In the proposed<br> approach, we start with extracting the features by applying Discrete<br> Wavelet Transform (DWT) in order to decompose the EEG signals<br> into sub-bands. These features, extracted from details and<br> approximation coefficients of DWT sub-bands, are used as input to<br> Principal Component Analysis (PCA). The classification is based on<br> reducing the feature dimension using PCA and deriving the supportvectors<br> using Support Vector Machine (SVM). The experimental are<br> performed on real and standard dataset. A very high level of<br> classification accuracy is obtained in the result of classification.