Epileptic seizure classification using statistical features of EEG signal

Epilepsy detection is enough time consuming and requires thorough observation to determine epilepsy type and locate the responsible area of the cerebral cortex. This paper proposes an effortless epilepsy classification method for straightforward epilepsy detection and investigates the classification accuracy of multiclass EEG signal during epilepsy. To accomplish our research work we exploit DWT MATLAB toolbox to obtain responsible features to accumulate feature vectors. Afterwards feature vectors are given in the input layer of the NN classifiers to differentiate normal, interictal and ictal EEG periods. Accuracy rate is calculated based on the confusion matrix. Proposed method can be utilized to monitor and detect epilepsy type incorporating with alarm system.