Abstract
Epilepsy is a neurological disorder disease that affects more than 55 million people in the world. In this paper, we have proposed an efficient intelligent pattern recognition system for the classification of epileptic and non-epileptic electroencephalogram (EEG) signals. For this purpose, we used state-of-the-art machine learning technique, i.e., SVM (support vector machines) to classify epileptic and non-epileptic signals. Two (02) different classes of signals are used in this study, i.e., non-epileptic with open eyes and epileptic in seizure condition. One hundred (100) subjects from each class were employed for extraction of discriminatory features and classification purpose. After pre-processing of EEG signals, we use discrete wavelet transform (DWT) to decompose signals upto level 5. Then various features, i.e., energy, entropy and standard deviation are extracted from wavelet bands. Next, we use these features in the classification of signals. We achieved the classification accuracy of 100 % at delta band (0 to 3 Hz) and theta band (3 to 6 Hz). The comparisons with the previous studies show the significance of this system, which can be utilized in real-time as well as in offline clinical applications.