Abstract:

Electroencephalography is the signals obtained by the measurement of the electrical flow in the brain. The classification of these signals is especially important because disorders related to brain signals contribute to the diagnosis, diagnosis and treatment. However, in order to obtain meaningful results from these signals, first and foremost data cleaning, authentication and authentication selection methods have been used. These methods were then compared in terms of their contribution to the success of classification. First, statistical characteristics were extracted from the filtered data with the Separate Wave Conversion method, then the differential evolution algorithm was selected with the subset of characteristics that gave the best classification result. The success of classification of the data set with selected properties has been tested with Support Vector Machines. Better results were obtained in the separation of some classes with the method used than similar studies.

Keywords: