Main Article Content
Brain is the crucial organ which performs various functions of body. Electroencephalogram (EEG) is an efficient modality which helps to acquire brain signals from scalp. Analysis of EEG signals helps in diagnosis and treatment of brain diseases like epilepsy seizure, and various problems associated with brain disorders. These signals are contaminated with unwanted artifacts and complicate to analyze. The diagnosis requires flawless analysis of EEG signals. Different methods are proposed to examine with high accuracy. In this paper, Discrete Wavelet Transform is used to pre-process the EEG signal and decompose into five frequency bands and then, the features like mean, standard deviation, RMS, entropy, energy and relative energy are computed. These features are evaluated by machine learning classifier such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Naive Bayes (NB). The results demonstrate the highest classification accuracy (99.5%), Specificity (100%), Sensitivity(100%) by SVM for normal versus epileptic subjects.