ANALYSIS OF EEG SIGNALS BY USING CLASSIFICATION AND CLUSTERING METHODS

Abstract

In this study, normal and epileptic EEG signals are analyzed by using different preprocessing, classification/clustering methods and results are compared. Mean Absolute values and parametric models such as Yule-Walker AR and Covariance methods are used fort he feature extraction. For the classification of EEG signals Linear Discriminant Analysis, Support Vector Machine (SVM) methods are used. Clustering techniques such as K-means and Fuzzy C-means are also used for the analysis of the EEG signals. The comparative results confirmed that the proposed methods achieved high classification rates.

Keywords

• EEG, Epilepsy, LDA, SVM, K-Means,

EEG Y?ARETLERYNYN SINIFLANDIRMA VE KÜMELEME TEKNYKLERY YLE ANALYZY

Öz

Bu çaly?mada, sa?lykly ve epilepsi hastasy olan ki?ilerden alynan EEG i?aretleri farkly öni?leme ve synyflandyrma yöntemleri kullanylarak analiz edilmi? ve bu yöntemlerin ba?ary oranlary kar?yla?tyrylmy?tyr. EEG i?aretlerinin synyflandyrylmasy veya öbekle?tirilmesi için öznitelik çykarym (Ortalama Mutlak De?er (OMD), Yule-Walker AR ve Kovaryans AR), öbekle?tirme (K-Ortalama, Bulanyk C-Ortalama (BCO) ) ve synyflandyrma (Destek Vektör Analizi ve Lineer Diskriminant Analizi) metotlary kullanylmy?tyr. Elde edilen yüksek synyflandyrma basarym sonuçlary kar?yla?tyrmaly olarak verilmi?tir.

Anahtar Kelimeler

• EEG, Epilepsi, LDA, LDA, K-Ortalama,