EEG (Electroencephalogram) is a technique for identifying neurological disorders. There are various neurological disorders like Epilepsy, brain cancer, etc. Feature extraction and classification of electroencephalogram (EEGs) signals for (normal and epileptic) is a challenge for engineers and scientists. Various signal processing techniques have already been proposed for classification of non-linear and non stationary signals like EEG. In this work, neural network analysis (NNA) based classifier was employed to detect epileptic seizure activity from background electro encephalographs (EEGs). Two types of EEG signals (healthy subject with eye open condition, epileptic) were selected for the analysis. Signals were reprocessed, decomposed by using discrete wavelet transform DWT till 5th level of decomposition tree. Various features like mean. Standard deviation, median, entropy, kurtosis and skewness were computed and consequently used for classification of signals. The range of these features in non-epileptic and epileptic group of 80 subjects each from data set is analyzed for data available at the Department of Epileptology, University of Bonn, and the parameters with distinct non-overlapping zone are identified. The results show the promising classification accuracy of nearly 100% in detection of abnormal from normal EEG signals. The main purpose of this new approach is that the computation time of NNA classifier is less to provide better accuracy. This proposed classifier can be used to design expert system for epilepsy diagnosis purpose in various hospitals.