Genetic Algorithm for Classification of Epilepsy Risk Levels from EEG Signals

This paper introduces a genetic algorithm (GA) based epilepsy risk level classifier from EEG signal parameters. The risk level of epilepsy is classified based on the extracted parameters like energy, variance, peaks, sharp and spike waves, duration, events and covariance obtained from the EEG of the patient. A binary coded GA (BCGA) is then applied on the code converter's classified risk levels to obtain the optimized risk level that characterizes the patient. The performance index (PI) and quality value (QV) and receiver operating characteristics are calculated for this method. A group of eight patients with known epilepsy findings are used for this study. High PI such as 92% for BGA was obtained at a QV of 80%.