DefinePK

Abstract

Epilepsy causes rapid and revertible changes in the functions of the brain due to the constant occurrence of recurrent seizures. For the epileptic detection and classification, Electroencephalography (EEG) signals are used as this can relate the functions related to the activities of the brain. This paper presents the performance analysis of Approximate Entropy (ApEn) as a Feature Extraction Technique and Fuzzy Mutual Information (FMI), Linear Graph Embedding (LGE) as Dimensionality Reduction Techniques followed by the Application of Principal Component Analysis (PCA) as a Post Classifier for the Classification of Epilepsy Risk Levels from EEG signals. The benchmark parameters used for the analysis here are Performance Index (PI), Quality Values (QV), Specificity, Sensitivity, Time Delay and Accuracy.