Analysis and Classification of Eeg Signals for Detection of Epileptic Seizures

Abstract

Epilepsy is a persistent constantly recurring neurological brain disorder characterized by abnormal electrical activity in the brain. Epilepsy is not only a disorder but rather acts as a syndrome with divergent symptoms involving spasmodic abnormal electrical activities in the brain. Clinical data relevant to such abnormalities is complex context dependent and multidimensional and such data generates an amalgamation of computing research challenges. Electroencephalogram EEG is one of the most clinically and a scientifically utilized signal recorded from human brain and is powerful source of providing valuable insight of the brain dynamics. Accurate and careful analyses of these signals play a prominent role in diagnosis of brain diseases and many cognitive processes. newlineEEG technique has excellent temporal resolution noninvasiveness usability and low setup costs while capturing brain signals which makes it popular in this arena of research. The electroencephalogram recordings of epileptic subjects are visually inspected and analyzed by trained neurologists or radiologists for clinical diagnosis of epileptic seizures and possible treatment plans. However due to the complex time consuming high dimensional nature of the EEG event recordings visual inspections of EEG signals often result in errors. Therefore there is a need to develop automatic systems for classifying the recorded EEG signals. newline