Epilepsi Tespitinde Gürbüz Yerel Ortalama Ayrışım ve Ampirik Kip Ayrışım Yöntemlerinin Performans Analizi

Abstract

Electroencephalography (EEG) data, which provides information about the electrical activity of the brain, are widely used in the diagnosis of neurological diseases, EEG signals also provide important information in the detection of epilepsy, which is one of the diseases affecting approximately 1% of the world’s population. In this study, it was aimed to detect the epileptic seizure before the seizure by using EEG signals. For this purpose, after preprocessing steps were performed by using EEG signals in different situations from epilepsy and healthy individuals, features were extracted from EEG signals from subband signals obtained by using Robust Local Mean Decomposition (RLMD) and Empirical Mode Decomposition (AKA) methods. Classification studies were carried out with the obtained features and Artificial Neural Networks (ANN). In line with the studies, the classification results of the different states of the EEG signals were revealed using the performance parameters of accuracy, sensitivity, specificity, precision and f1 score.