Peyman Vafadoost Sabzevar - Biomedical Engineering Department, Electrical andComputer Faculty, Hakim Sabzevari University,Sabzevar, Iran
Hamid Sadrian - Biomedical Engineering Department, Electrical andComputer Faculty, Hakim Sabzevari University,Sabzevar, Iran
Ahmad Hajipour - Faculty member of Department of Electrical and Computer Engineering, Hakim Sabzevari University,Sabzevar, Iran.

Epilepsy is one of the most common diseases of the human nervous system, affectingabout ۵۰ million people, according to the World Health Organization. When epilepticseizures occur, people experience unusual symptoms such as loss of consciousnessand seizures. Given that epilepsy is a neurological disorder in the human system, itsbehavior can be predicted by recording brain signals and processing them, andidentifying people with epilepsy to begin treatment. TheElectroencephalogram(EEG) signal is used as one of the human biological signals torecord and monitor the behavior of the brain. The method of recording EEG signalsis that the electrodes are first installed on the skull according to a predeterminedstandard, and these electrodes record the behavior of the brain based on the processestaking place. In this paper, first the EEG signal performance is examined and thenthe existing methods for feature extraction and classification are introduced. Finally,the research conducted by researchers in the field of epilepsy diagnosis is discussed.The results show that if the feature is properly extracted and valid classificationmethods are used, the EEG signal is a highly reliable signal in the diagnosis ofepilepsy.

EEG, Epilepsy, Signal processing, C lasification, Artificial intelligence