Detection of Epileptic Seizures with Support Vector Machine Algorithm

The complex and non-periodic signs obtained by EEG (electroencephalography) are used in the detection of a large number of diseases. Epilepsy, which is one of them, is a neurological disorder that affects a large number of people around the world and has a risk of causing injury of the patient in various ways. Instant monitoring of EEG signals is vital for the patient by providing notification of crisis detection in moments of vehicle / machine use. In this paper, a support vector machine based algorithm is used for the detection of epileptic attacks. In the study, EEG data sets corresponding to 23 non-crisis and crisis moments have been used. During the process of the EEG signals, wavelet transform, fourier transform, feature extraction and classification have been applied, respectively. Based on the implementation steps used and classification method selected the epileptic attacks have been determined with 97% accuracy.