Pattern Classification of Epileptic Electroencephalograms Signal Based on Improved Feature Extraction Method

Since pattern classification for Epileptic Electroencephalograms signals (EEG signals) still have remark uncertainty, this study analysis the method of feature extraction and pattern classification. Epileptic Electroencephalograms signals (EEG signals) depict the electrical activities of neurons and consist of some physiological and pathological information. EEG is one of the non-invasive methods for monitoring and diagnosing epileptic behavior. Classification of epileptic electroencephalograms signal has important medical diagnostic significance. In this study, a novel method is proposed to extract features from P300 component. A method of optimizing parameters on classing EEG signals is presented. In this study, the proposed method is compared with the empirical parameters and the grid search in the sense of training accuracy and training time. The proposed classifier has more advantage than the empirical parameters and the grid search for training this got sample in the sense of the average training accuracy and training time. Our experimental results also demonstrated the effectiveness of the proposed classification method.