Detection of Epilepsy Disorder by EEG Using Discrete Wavelet Transforms

Abstract

EEG (Electroencephalogram) is a technique for identifying neurological disorders. There are various neurological disorders like Epilepsy, brain cancer, etc. Epilepsy is one of the common neurological disorders pertaining in approximately 1% of the people in the world. Objective detection efficiently is still a challenging task for many neurological disorders. This is highly related to the diversity of cases that occurs daily. Especially in the case of epilepsy, which is a complex disorder not well-explained at the biochemical and physiological levels, there is the need for investigations for novel features, which can be extracted and used for distinguishing epileptic EEG signals from normal EEG signals. This thesis discusses the design of system that detects the epileptic activity with efficacy. Decomposition of the EEG signal to various subbands by multi- level wavelet decomposition is followed to extract features from these sub-bands. The range of these features in non-epileptic and epileptic group of 50 subjects each from data set is analysed for data available at the Department of Epileptology, University of Bonn, and the parameters with distinct non-overlapping zone are identified [20]. These features are then classified using a scoring system that detects the EEG data for epilepsy. This system is finally validated for another two groups of non- epileptic and epileptic subjects, 50 each from the same data set. The validation process on a different group showed high detection rate.