Open AccessClassification of Epileptic and Normal EEG Signals Using Power Spectrum of Sub-bands
Author(s) -
Sude Pehlivan,
Savaş Şahin
Publication year - 2020
Publication title -
akıllı sistemler ve uygulamaları dergisi
Language(s) - English
Resource type - Journals
ISSN - 2667-6893
DOI - 10.54856/jiswa.202005095
Subject(s) - electroencephalography , epilepsy , computer science , matlab , artificial intelligence , pattern recognition (psychology) , spectral density , power (physics) , energy (signal processing) , machine learning , speech recognition , psychology , mathematics , statistics , neuroscience , telecommunications , physics , quantum mechanics , operating system
The early diagnosis of epilepsy, which affects the lives of many people worldwide, is the first step of treatment to help patients to continue their lives efficiently. Experts have to spend a lot of time and energy to make this diagnosis as quickly and accuratelyaspossible.The aimofthisstudywasto investigatethe capacity of machine learning algorithms to distinguish epileptic and normal signals to develop a system that can automatically diagnose seizures. LabVIEW was used to obtain the sum of EEG sub-band powers which were used as an attribute for both epileptic and normal records. These attributes were classified with different classifiers using Matlab and as a result of the classification, it was concluded that the sub-band power sum can be used as a meaningful attribute in the classification of epileptic and normal EEG signals.