Performance Comparison of Fuzzy Mutual Information as Dimensionality Reduction Techniques and SRC, SVD and Approximate Entropy as Post Classifiers for the Classification of Epilepsy Risk Levels from EEG Signals

One of the most commonly occurring disorder in the brain is epilepsy and it is characterized by the sudden onset of recurrent seizures. When the electrical discharge in the brain bursts suddenly in an abnormal fashion it leads to epilepsy. Epilepsy is a neurological disorder of the Central Nervous System (CNS) and causes great trouble to mankind because of the recurrence of the seizures. The EEG provides a significant tool for exploring the neural activities in the network of the brain which is widely associated with the synchronous changes happening in the membrane potentials of neighbouring neurons. This paper provides a performance comparison when Fuzzy Mutual Information (FMI) acts as a dimensionality reduction technique followed by the Sparse Representation Classifier (SRC), Singular Value Decomposition (SVD), Approximate Entropy (ApEn) as Post Classifiers for the Classification of Epilepsy Risk Levels from EEG Signals. The bench mark parameters considered here are Performance Index (PI), Quality Value (QV), Specificity, Sensitivity, Time Delay and Accuracy.