Classification of seizure and seizure-free EEG signals using local binary patterns. (January 2015)

• Record Type: Journal Article
• Authors: Kumar, T. Sunil; Kanhangad, Vivek; Pachori, Ram Bilas
• Is Part Of: Biomedical signal processing and control. Volume 15(2015)
• Page Start: 33
• Page End: 40
• Publication Date: 2015-01
• Subjects: 1D-Local binary pattern -- Epilepsy -- Electroencephalogram (EEG) signals -- Seizure and seizure-free EEG signals -- Gabor filter bank -- EEG signal classification; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2014.08.014
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A novel method using 1D-LBPs and 1-NN classifier for classification of seizure and seizure-free EEG signals. Bank of Gabor filters for decomposing EEG signal. Three different schemes have been investigated for fusion of information. Approach achieves the best 10-fold classification accuracy of 98.33%. Abstract: Local binary pattern (LBP) is a texture descriptor that has been proven to be quite effective for various image analysis tasks in image processing. In this paper one-dimensional local binary pattern (1D-LBP) based features are used for classification of seizure and seizure-free electroencephalogram (EEG) signals. The proposed method employs a bank of Gabor filters for processing the EEG signals. The processed EEG signal is divided into smaller segments and histograms of 1D-LBPs of these segments are computed. Nearest neighbor classifier utilizes the histogram matching scores to determine whether the acquired EEG signal belongs to seizure or seizure-free category. Experimental results on publicly available database suggest that the proposed features effectively characterize local variations and are useful for classification of seizure and seizure-free EEG signals with a classification accuracy of 98.33%. This result demonstrates the superiority of our approach for classification of seizure and seizure-free EEG signals over recently proposed approaches in the literature.