Analysis of PSO and Hybrid PSO in Calculation of Epileptic Risk Level in EEG
R. Harikumar1, T. Vijayakumar2, R. Kasthuri3
1Dr.R.Harikumar,ECE, Bannari Amman Institute of Technology, Sathy, Erode, India.
2T.Vijayakumar, IT, Bannari Amman Institute of Technology, Sathy, Erode, India.
3R.Kasthuri, ECE, Bannari Amman Institute of Technology, Sathy, Erode, India.
Manuscript received on February 04, 2013. | Revised Manuscript received on February 24, 2013. | Manuscript published on March 05, 2013. | PP: 154-159 | Volume-3 Issue-1, March 2013. | Retrieval Number: A1331033113/2013©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: The main aim of this paper is to compare and analyze the performance of the PSO algorithm and the hybrid PSO output in determining the epileptic risk level for the given Electroencephalogram signal inputs. Various parameters like energy, variance, peaks, sharp and spike waves, duration, events and covariance are calculated from the EEG signals. The two optimization technique has been used for classifying the risk level of the given inputs and the efficacy of the above two methods have been analyzed and compared using mean square error and quality value. 20 patients input are taken for analysis in both methods in calculation of risk level. Comparing to PSO output hybrid PSO method is efficient based on performance index and quality value.
Keywords: Electroencephalogram signals, Epileptic risk level, Particle swarm optimization (PSO), Hybrid PSO optimization, mean square error, quality value.