(IJIRSE) International Journal of Innovative Research in Science & Engineering ISSN (Online) 2347-3207 Performance Analysis of Epileptic EEG Expert System Using Scaled Conjugate Back Propagation Based ANN Classifier Ashish Raj 1 , Pankaj Gakhar 2 , Meenu Kumari 3 Sweta Tripathi 4 ashishraj1987@gmail.com 1 ,pankaj.gakhar@poornima.edu.in 2 ,meenu.kumari@poornima.edu.in 3 ,sweta.tripathi@poornima.edu.in 4 Abstract— Epilepsy is a neurological disorder with prevalence of about 1-2% of the world’s population. Epilepsy is a neurological condition in which is due to chronic abnormal bursts of electrical discharge in the brain. Monitoring brain activity through the electroencephalogram (EEG) has become an important tool in the diagnosis of epilepsy. The EEG recordings of patients suffering from epilepsy show two categories of abnormal activity: inter-ictal, abnormal signals recorded between epileptic seizures; and ictal, the activity recorded during an epileptic seizure. The term EEG refers that the brain activity emits the signal from head and being drawn. It is produced by bombardment of neurons within the brain. EEG signal provides valuable information of the brain function and neurobiological disorders as it provides a visual display of the recorded waveform and allows computer aided signal processing techniques to characterize them. This gives a prime motivation to apply the advanced digital signal processing techniques for analysis of EEG signals. The main objective of our research is to analyze the acquired EEG signals using signal processing tools such as wavelet transform and classify them into diff erent classes. The features from the EEG are extracted using statistical analysis of parameters obtained by wavelet transform and Auto-Regressive model. Total 300 EEG data subjects were analyzed. These data were grouped in three classes’ i.e, Normal patient class, Epileptic patient class and epileptic patient during non-seizure zone respectively. In order to achieve this we have applied a backpropgation based neural network classifier. After feature extraction secondary goal is to improve the accuracy of classi fication. 100 subjects from each set were analysed for feature extraction and classification and data were divided in training, testing and validation of proposed algorithm. Index Terms— EEG, Epilepsy, Wavelet transform; Feature Extraction, Neural network, Backpropogation Neural Network. I. INTRODUCTION Generally, the detection of epilepsy can be achieved by visual scanning of EEG recordings for inter-ictal and ictal activities by an experienced neurophysiologist. However, visual review of the vast amount of EEG data has serious drawbacks. Visual inspection is very time consuming and inefficient, especially in the case of long-term recordings. In addition, disagreement among the neurophysiologists on the same recording is possible due to the subjective nature of the analysis and due to the variety of inter-ictal spikes morphology. Moreover, the EEG patterns that characterize an epileptic seizure are similar to waves that are part of the background noise and to artifacts (especially in extra cranial recordings) such as eye blinks and other eye movements, muscle activity, electrocardiogram, electrode "pop" and electrical interference. For these reasons, methods for the automated detection of inter- ictal spikes and epileptic seizures can serve as valuable clinical tools for the scrutiny of EEG data in a more objective and computationally efficient manner.[1] 1.1 Wavelet Transform- The discrete wavelet transform (DWT) is quite an effective tool for Time-Frequency analysis of signals. Wavelet transform can be defined as a spectral estimation technique in which any general function can be expressed as a sum of an infinite series of wavelets. In DWT the time-scale representation of the signal can be achieved using digital filtering techniques. The approach for the multi-resolution decomposition of a signal x(n) is shown in Fig. 1.1. The DWT is computed by successive low pass and high pass filtering of the signal x (n). Each step consists of two digital filters and two down samplers by 2. The high pass filter g[] is the discrete mother wavelet and the low pass filter h[.] is its mirror version. At each level the down sampled outputs of the high pass filter produce the detail coefficients and that of low pass filter gives the approximation coefficients. The approximation coefficients are further decomposed and the procedure is continued as shown in figure.1.1. Figure 1.1. Computation process of DWT