A Comparison of Elman and Radial Basis Function (RBF) Neural Networks in Optimization of Fuzzy outputs for Epilepsy Risk Levels Classification fromEEG Signals
R. Harikumar1, T. Vijayakumar2
1Dr.R.Harikumar,Professor, ECE Department,.Bannari Amman Institute of Technology, Sathyamangalam India.
2T.Vijayakumar Assistant Professor, (Sr.Gr) Department of IT, Bannari Amman Institute of Technology, Sathyamangalam.
Manuscript received on January 01, 2013. | Revised Manuscript received on January 02, 2013. | Manuscript published on January 05, 2013. | PP: 295-303 | Volume-2, Issue-6, January 2013. | Retrieval Number: F1201112612/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper; we investigate the optimization of fuzzy outputs in the classification of epilepsy risk levels from EEG (Electroencephalogram) signals using two categories (Recurrent &Non Recurrent) of neural networks. The fuzzy techniques are applied as a first level classifier to classify the risk levels of epilepsy based on extracted parameters like energy, variance, peaks, sharp and spike waves, duration, events and covariance from the EEG signals of the patient. Elman neural network (with error Back propagation training) & Radial Basis Function (RBF) neural network are identified as post classifiers on the classified data to obtain the optimized risk level that characterizes the patient’s epilepsy risk level. The Performance Index (PI) and Quality Value (QV) are calculated for the above methods. A group of ten patients with known epilepsy findings are used in this study. High PI such as 97.87 %, and 98.92% was obtained at QV’s of 23.31, and 23.98 in Elman and RBF neural network optimization when compared to the value of 40% and 6.25 through fuzzy techniques respectively. We find that the RBF (Non Recurrent) neural network out performs Elman Network in optimizing the epilepsy risk levels.
Keywords: EEG Signals, Epilepsy Risk Levels,Fuzzy Logic, RBF, Elman Neural Networks, Back propagation.