Morphological operator based feature extraction technique along with suitable post classifiers for epilepsy risk level classification

Electroencephalogram (EEG) is a powerful tool for the diagnosis of neurological disorders. Since its discovery, the EEG has been used for the diagnosis of epilepsy, for trauma assessment, for sleep research, and for the analysis of higher brain functions. The EEG is highly dependent upon the availability of high quality instrumentation, and almost from the beginning, automated methods of signal processing have been applied. Recording the EEG during a seizure is particularly helpful in determining whether a patient has epilepsy or not, because seizures usually occur infrequently and unpredictably and obtaining such recording might require an EEG extending over several days. If the EEG recordings are too long, then the process is too much time consuming and hence spike detection methods which can perform automatically are needed. Morphological Filter (MF) is one such technique used for the automatic detection of spikes in epileptic EEG signals. This paper thus presents the performance analysis using morphological filtering technique along with Principal Component Analysis (PCA), Approximate Entropy (ApEn) and Sparse Representation Classifiers (SRC) as Post Classifiers for the Classification of Epilepsy Risk Levels from EEG Signals.