GLCM texture classification for EEG spectrogram image

Author

Mustafa, Mahfuzah ; Taib, Mohd Nasir ; Murat, Zunairah Hj ; Hamid, Noor Hayatee Abdul

Author_Institution

Fac. of Electr. & Electron. Eng., Univ. Malaysia Pahang, Kuantan, Malaysia

fYear

2010

fDate

Nov. 30 2010-Dec. 2 2010

Firstpage

373

Lastpage

376

Abstract

Over the past century, time based and frequency based is used for analyzing Electroencephalography (EEG) signals. EEG is a scientific tool for measure signal from human brain. This paper proposes a time-frequency approach or spectrogram image processing technique for analyzing EEG signals. Gray Level Co-occurrence Matrix (GLCM) texture feature were extracted from spectrogram image and then Principal components analysis (PCA) was employed to reduce the feature dimension. The purpose of this paper is to classify EEG spectrogram image using k-nearest neighbor algorithm (kNN) classifier. The result shows classification rate was 70.83% for EEG spectrogram image.

Keywords

electroencephalography; feature extraction; learning (artificial intelligence); medical signal processing; neurophysiology; principal component analysis; signal classification; time-frequency analysis; EEG spectrogram image processing technique; GLCM texture classification; electroencephalography signals; feature dimension; feature extraction; gray level co-occurrence matrix texture feature; human brain; k-nearest neighbor algorithm classifier; machine learning algorithm; principal component analysis; time-frequency approach; Accuracy; Electroencephalography; Feature extraction; Indexes; Principal component analysis; Spectrogram; Time frequency analysis; EEG; GLCM; PCA; kNN; spectrogram image; texture feature;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering and Sciences (IECBES), 2010 IEEE EMBS Conference on

Conference_Location

Kuala Lumpur

Print_ISBN

978-1-4244-7599-5

Type

conf

DOI

10.1109/IECBES.2010.5742264

Filename

5742264