Determining Appropriate Window Size and Window Function for Epileptic Seizure Forecasting

Abstract

The aim of this study is to determine the appropriate window size and windowing function for studies related to epileptic seizure forecasting. Firstly, in order to accomplish this aim, a suitable data set is obtained. Afterwards, tests are performed for 12 different window durations and the most suitable windowing time is determined. Determined window duration, windowing functions of 5 different properties are applied and performance rates are examined. As a result of the findings obtained in future studies, it is aimed to increase the success rate by conducting test operations with different features and classifiers.