Title: Classification of Epileptic and Normal EEG Signals Using Power Spectrum of Sub-bands

Abstract: 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.

Keywords: LabVIEW; epilepsy; machine learning

Başlık: Epileptik ve Normal EEG Sinyallerinin Alt Bant Güç Spektrumu Kullanılarak Sınıflandırılması

Özet: Dünya genelinde birçok insanın hayatını etkileyen epilepsinin erken teşhisi, hastaların hayatlarına verimli devam edebilmesi için uygulanacak tedavinin ilk adımıdır. Uzmanlar, bu teşhisin en kısa sürede ve en doğru şekilde yapılması için çok fazla zaman ve enerji harcamak zorunda kalmaktadır. Bu çalışmanın amacı, nöbetleri otomatik olarak teşhis edebilen bir sistem geliştirmek için makine öğrenmesi algoritmalarının epileptik ve normal sinyalleri ayırt etme kapasitesini araştırmaktır. LabVIEW, hem epileptik hem normal kayıtlar için bir öznitelik olarak kullanılan EEG alt bant güçlerinin toplamını bulmak için kullanılmıştır. Bu öznitelikler Matlab kullanılarak farklı sınıflandırıcılar ile sınıflandırılmış ve sınıflandırma sonucunda alt bant güç toplamının epileptik ve normal EEG sinyallerinin sınıflandırılmasında anlamlı bir öznitelik olarak kullanılabileceği sonucuna varılmıştır.

Anahtar kelimeler: LabVIEW; epilepsi; makine öğrenmesi

• Teplan M. Fundamentals of EEG measurement. Measurement Science Review 2002; 2(2): 1-11.
• World Health Organization, International Bureau for Epilepsy, International League against Epilepsy. Atlas: Epilepsy Care in the World. 2005, Geneva, Italy.
• Acharya UR, Sree SV, Swapna G, Martis RJ, Suri JS. Automated EEG analysis of epilepsy: A review. Knowledge Based Systems 2013; 45: 147-165.
• Chua KC, Chandran V, Acharya R, Lim CM. Automatic identification of epilepsy by HOS and power spectrum parameters using EEG signals: A comparative study. In 2008 IEEE 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, August 20-25, 2008, Vancouver, BC, Canada, pp. 3824-3827.
• Andrzejak RG, Lehnertz K, Mormann F, Rieke C, David P, Elger CE. Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state. Physical Review E: Statistical, Nonlinear, and Soft Matter Physics 2001; 64(6): 061907.
• Tsipouras MG. Spectral information of EEG signals with respect to epilepsy classification. EURASIP Journal on Advances in Signal Processing 2019; 2019(10): 1-17.
• Kotsiantis SB, Zaharakis I, Pintelas P. Supervised machine learning: A review of classification techniques. Emerging Artificial Intelligence Applications in Computer Engineering 2007; 160: 3-24.
• Subasi A, Ercelebi E. Classification of EEG signals using neural network and logistic regression. Computer Methods and Programs in Biomedicine 2005; 78(2): 87-99.
• Tessy E, Shanir PM, Manafuddin S. Time domain analysis of epileptic EEG for seizure detection. In 2016 IEEE International Conference on Next Generation Intelligent Systems (ICNGIS), September 1-3, 2016, Kottayam, India, pp. 1-4.
• Zhu W, Zeng N, Wang N. Sensitivity, specificity, accuracy, associated confidence interval and ROC analysis with practical SAS implementations. In NESUG Proceedings: Health Care and Life Sciences, January 2010, Baltimore, Maryland, pp. 1-9.
• Subasi A. EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Systems with Applications 2007; 32(4): 1084-1093.