IMMUNE CLONAL ALGORITHM BASED FEATURE SELECTION FOR EPILEPTIC EEG SIGNAL CLASSIFICATION

Detecting epileptic EEG signal automatically and accurate-ly is significant in evaluating patients with epilepsy. In this study, the immune clonal algorithm (ICA) is employed to perform automatic feature selection, reducing the number of features the classifier deals with and improving the classifi-cation accuracy. In the experiment, EEG signal was decom-posed into five sub-band components by a discrete wavelet transform. Features were extracted as input to train three classifiers (NB, SVM, KNN and LDA) to judge whether the EEG signal was epileptic or not. Then, ICA was introduced to select a feature subset to train the classifiers. Experimen-tal results show that the classification accuracy based on s-elected features is significantly higher than that on original features. We also analyzed the relative importance of each feature. 1