HIERARCHICAL FUNCTIONS DECISION TREES AND MINIMUM RELATIVE ENTROPY IN THE DETECTION OF EPILEPSY RISK LEVELS FROM EEG SIGNALS

The goal of this paper is to analysis the performance of Hierarchical Soft (maxmin) decision trees and Minimum Relative Entropy (MRE) in optimization of Code Converter outputs in the detection of epilepsy risk levels from EEG (Electroencephalogram) signals. The Code Converter pre classifier is used to identify the risk levels of epilepsy based on extracted parameters like energy, variance, peaks, sharp and spike waves, duration, events and covariance from the patient's EEG signals. Hierarchical Soft decision tree (post classifiers with max-min criteria) four types and Minimum Relative Entropy are applied on the classified data to identify the optimized risk level (singleton) which characterizes the patient's risk level. The efficacy of the above methods is compared based on the bench mark parameters like Performance Index (PI), and Quality Value (QV).