Support Vector Machine (SVM) as Post Classifier for Epilepsy Risk Level Classifications from Fuzzy based EEG Signal Parameters

Authors

A. Keerthi Vasan, M. Logesh Kumar

Bannari Amman Institute of Technology, Sathyamangalam

Abstract

In this paper, we propose an optimization of fuzzy outputs in the classification of epilepsy risk levels from EEG (Electroencephalogram) signals which are acquired through LABVIEW via DAC(Data Accusation Card). The fuzzy techniques are applied as a first level classifier to classify the risk levels of epilepsy. Support Vector machine (SVM) is identified as a post classifier on the classified data to obtain the optimized risk level that characterizes the patient’s epilepsy risk level. Epileptic seizures may go unnoticed, depending on their presentation, and some times may be confused with other events, such as a stroke, which can also cause falls or migraines. Twenty –five percent of the world’s 50 million people with epilepsy have seizures that cannot be controlled either by pharmaceutical therapy or surgical or combined by both methods. The bench parameters for validating the hybrid classifiers are Performance Index (PI) and Quality Value (QV) and are calculated. High PI such as 98.2 %, was obtained at QV’s of 22.2, for SVM optimization when compared to the value of 40% and 6.25 through fuzzy techniques respectively. We found that the SVM Method out performs Fuzzy Techniques in optimizing the epilepsy risk levels.