Classification of EEG Signals in Depressed Patients

Abstract

Electroencephalography (EEG) are electrical signals that occur in every activity of the brain. Investigation of normal and abnormal changes that take place in the human brain using EEG signals is a widely used method in recent years. The World Health Organization (WHO) states that one of the most important health problems in today's society is depressive disorders. Nowadays, various scales are used in the diagnosis of depressive disorder in individuals. These scales are based on the declaration of the individual. In recent studies, EEG has been used as a biomarker for the diagnosis of depression. In this study, EEG signals from 30 patients with clinical depressive disorder have been recorded. EEG signals have been collected for 1 minute with eyes open and closed. The collected data have been divided into attributes by continuous wavelet transform which is used in many studies in processing non-stationary signals such as EEG. Obtained attributes have been classified with kNN classification method. As a result, it was observed that EEG signals, collected from subjects with depression while eyes are open and closed, can be classified with an accuracy of 91.30%.

Keywords

• EEG classification,depressive disorders,k-Nearest Neighbor (kNN) algorithm,Continuous Wavelet Transform

References

1. T. Erguzel, S. Ozekes, A. Bayram and N. Tarhan, "Classification of major depressive disorder subjects using Pre-rTMS electroencephalography data with support vector machine approach," 2014 Science and Information Conference, London, 2014, pp. 410-414.
2. S. A. Akar, S. Kara, S. Agambayev and V. Bilgiç, "Nonlinear analysis of EEG in major depression with fractal dimensions," 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, 2015, pp. 7410-7413.
3. W. Mumtaz, A. S. Malik, S. S. A. Ali and M. A. M. Yasin, "P300 intensities and latencies for major depressive disorder detection," 2015 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), Kuala Lumpur, 2015, pp. 542-545.
4. H. M. Mallikarjun and H. N. Suresh, "Depression level prediction using EEG signal processing," 2014 International Conference on Contemporary Computing and Informatics (IC3I), Mysore, 2014, pp. 928-933.
5. A. M. Al-Kaysi, A. Al-Ani, C. K. Loo, M. Breakspear and T. W. Boonstra, "Predicting brain stimulation treatment outcomes of depressed patients through the classification of EEG oscillations," 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, 2016, pp. 5266-5269.
6. Y. Mohan, S. S. Chee, D. K. P. Xin and L. P. Foong, "Artificial neural network for classification of depressive and normal in EEG," 2016 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES), Kuala Lumpur, 2016, pp. 286-290.
7. Holden, R. R., Mehta, K., Cunningham, E. J., & McLeod, L. D. (2001). “Development and preliminary validation of a scale of psychache”. Canadian Journal of Behavioural Science/Revue Canadienne Des Sciences Du Comportement, 33(4), 224.
8. Demirkol, M., Güleç, H., Çakmak, S., Namlı, Z., Güleç, M., Güçlü, N., & Tamam, L. (2018). “Reliability and validity study of the Turkish Version of the Psychache Scale”. Anatolian Journal of Psychiatry, 19(1),14–20.

9. Beck, A. T., & Steer, R. A. (1984).” Internal consistencies of the original and revised Beck Depression Inventory”. Journal of Clinical Psychology, 40(6), 1365–1367.
10. Qu , H. & Gotman, J. A, “Patient-Specific Algorithm for the Detection of Seizure Onset in Long-Term EEG Monitoring: Possible Use as a Warning Device”, IEEE Transactions on Biomedical Engineering, 44, 115-122p, 1997.
11. Oliveria, I., Grigori, O., Guimaraes, N., “EEG Signal Analysis for Silent Visual Reading Classification”, Internatıonal Journal Of Cırcuıts, Systems And Sıgnal Processıng, Issue 3, Volume 3, 2009:119-126p.
12. Murugappan, M., “Human emotion classification using wavelet transform and KNN”, Pattern Analysis and Intelligent Robotics (ICPAIR) International Conference on, (Volume:1 ), 28-29 June 2011, 148 – 153p.
13. Mitchell, T., 1997, “Machine Learning”, McGraw Hill, 1997.
14. Özer, Z.B., ve Amasyalı, M.F., “Meta Öğrenme ile KNN Parametre Seçimi”., 21. Sinyal İşleme Ve Uygulamaları Konferansı, 2013.