A Comparison of Genetic Algorithm & Neural Network (MLP) In Patient Specific Classification of Epilepsy Risk Levels from EEG Signals

This paper is aimed to compare the performance of a Genetic Algorithm (GA) and MultiLayer Perceptron (MLP) Neural network in the classification of epilepsy risk level from Electroencephalogram (EEG) signal parameters. The epilepsy risk level is classified based on the extracted parameters like energy, variance, peaks, sharp and spike waves, duration, events and covariance from the EEG of the patient. A Binary Coded GA (BCGA) and MLP Neural network are applied on the code converter’s classified risk levels to optimize risk levels that characterize the patient. The Performance Index (PI) and Quality Value (QV) are calculated for these methods. A group of ten patients with known epilepsy findings are used in this study. High PI such as 93.33% and 95.83% for BGA and MLP are obtained at QV of 20.14 and 21.59.

[1]  M. Van Gils,et al.  Signal processing in prolonged EEG recordings during intensive care , 1997, IEEE Engineering in Medicine and Biology Magazine.

[2]  Tzung-Pei Hong,et al.  Integrating fuzzy knowledge by genetic algorithms , 1998, IEEE Trans. Evol. Comput..

[3]  N. Peric,et al.  Estimation of difficult-to-measure process variables using neural networks - a comparison of simple MLP and RBF neural network properties , 2004, Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.04CH37521).

[4]  Chang Wook Ahn,et al.  On the practical genetic algorithms , 2005, GECCO '05.

[5]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[6]  R. Harikumar,et al.  Fuzzy techniques for classification of epilepsy risk level from EEG signals , 2003, TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region.

[7]  L. Lin,et al.  An artificial-intelligence approach to ECG analysis. , 2000, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[8]  W.R. Fright,et al.  A multistage system to detect epileptiform activity in the EEG , 1993, IEEE Transactions on Biomedical Engineering.

[9]  L. Acosta,et al.  Brain maturation estimation using neural classifier , 1995, IEEE Transactions on Biomedical Engineering.

[10]  Russell C. Eberhart,et al.  Implementation of evolutionary fuzzy systems , 1999, IEEE Trans. Fuzzy Syst..

[11]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[12]  Sam Kwong,et al.  Genetic algorithms: concepts and applications [in engineering design] , 1996, IEEE Trans. Ind. Electron..

[13]  L. Tarassenko,et al.  Identification of inter-ictal spikes in the EEG using neural network analysis , 1998 .

[14]  Marco Russo,et al.  FuGeNeSys-a fuzzy genetic neural system for fuzzy modeling , 1998, IEEE Trans. Fuzzy Syst..

[15]  Kalyanmoy Deb,et al.  Long Path Problems , 1994, PPSN.

[16]  Nurettin Acir,et al.  Automatic detection of epileptiform events in EEG by a three-stage procedure based on artificial neural networks , 2005, IEEE Transactions on Biomedical Engineering.

[17]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[18]  Wei-Min Qi,et al.  Dynamic properties of Elman and modified Elman neural network , 2002, Proceedings. International Conference on Machine Learning and Cybernetics.