Performance analysis of SVD and Support Vector Machines for optimization of fuzzy outputs in classification of epilepsy risk level from EEG signals

In this paper, we compare the performances of Singular Value Decomposition (SVD) and Support Vector Machine (SVM) techniques in the optimization of fuzzy outputs towards the classification of epilepsy risk levels from EEG (Electroencephalogram) signals. The fuzzy techniques are applied as a first level classifier to classify the risk levels of epilepsy based on extracted parameters such as, energy, variance, peaks, sharp and spike waves, duration, events and covariance from the EEG signals. Support Vector machine (SVM) and SVD techniques are applied on the classified data to identify the optimized risk level (singleton) which characterizes the patient´s state. The efficacies of these methods are compared with the bench mark parameters such as Performance Index (PI), and Quality Value (QV). A group of twenty patients with known epilepsy findings are analyzed. High PI such as 98.2 % was obtained at QV´s of 21.99, for SVM optimization and PI such as 95.88 % was obtained at QV´s of 22.43 in the SVD model when compared to the value of 40% and 6.25 through fuzzy classifier respectively. It was identified that the SVM and SVD are good post classifiers in the optimization of epilepsy risk levels..