Epilepsy is one of the most common disorders of the brain. Now a days, identification and diagnosis of epilepsy is accomplished manually by skilled neurologists, who are very rare. We propose a technique for developing intelligent decision support system for the diagnosis of epilepsy from recorded of EEG signals of patients, which results into automatic detection of normal, interictal and ictal conditions. We used three-level Db2 discrete wavelet transform for decomposition followed by statistical features extraction. The classifiers based on Generalized Feed Forward Neural Network (GFFNN), Multilayer Perceptron (MLP) and Support Vector Machine (SVM) are used for the diagnosis of epilepsy. Sensitivity analysis is used for dimensionality reduction of the input features space. The performance of the proposed system is evaluated in terms of classification accuracy, sensitivity, specificity and overall accuracy on cross-validation as well as testing datasets. Following invention is described in detail with the help of figure 2 of sheet 1 showing the detailed working of proposed ANN based classifier
