International Journal of Nonlinear Analysis and Applications

A hybrid technique for EEG signals evaluation and classification as a step towards to neurological and cerebral disorders diagnosis

Document Type : Research Paper

Authors

1 College of Computer Science and Information Technology, University of Anbar, Iraq

2 Department of Computer Science, Science College, Mustansiriyah University, Baghdad, Iraq.

3 Department of Oil and gas economics, college of administration sciences and financial, Imam Ja’afar Al-sadiq university, Baghdad, Iraq

4 Faculty of Computer Science and Mathematics, University of Kufa, Iraq.

Abstract

Electroencephalography (EEG) signals are commonly used to identify and diagnose brain disorders. Each EEG normal waveform consists of the following waveforms: Gamma(γ) wave, Beta (β) wave, Alpha (α), Theta (θ), and Delta (δ). The term Neurological Diseases ” NurDis ” is used to describe a variety of conditions that affect the nervous Epilepsy, neuro infections (bacterial and viral), brain tumors, cerebrovascular diseases, Alzheimer’s disease, and various dementias are all examples of neurological disorders. Encephalitis is one of the illnesses that affects the brain. The EEG signals used in this paper were from the CHB-MIT Scalp EEG database. The discrete wavelet transform (DWT) was utilized to extract characteristics from the filtered EEG data. Finally, classifiers such as K Nearest Neighbor (KNN) and Support vector machine (SVM) were used to categorize the EEG signals into normal and pathological signal classes using all of the computed characteristics. In order to categorize the signal in a normal and anomalous group, the KNN and SVM classifiers are employed. For both classifiers, performance assessments (accuracy, sensitivity and specificity) are determined. KNN classifier accuracy is 71.88%, whereas SVM classifier accuracy is 81.23%. The sensitivity of KNN and SVM are 80.14% and 77.31%, respectively. The KNN classification specificity is 69.62% and the SVM classification specificity is 98%. Both classifiers performance is evaluated using the confusion matrix.

Keywords

[1] A.S. Abdulbaqi, et al., Recruitment Internet Of Things For Medical Condition Assessment: Electrocardiogram Signal Surveillance), Special Issue, AUS Journal, Institute of Architecture and Urbanism, University of Austral de Chile, (2019) 434-440.
[2] A.S. Abdulbaqi, I. Y. Panessai, Efficient EEG Data Compression and Transmission Algorithm for Telemedicine, Journal of Theoretical and Applied Information Technology (JATIT), 97 (4) (2019).
[3] A.S. Abdulbaqi, et al., Robust multichannel EEG Signals Compression Model Based on Hybridization Technique, International Journal of Engineering & Technology, 7 (4) (2018) 3402-3405.
[4] A. S. Easa, and W. Arabo, A Normalization Methods for Backpropagation: A Comparative Study, Science Journal of University of Zakho, 5 (4)(2017) 319-3237.
[5] P. Ekman, Basic emotions, Handbook of cognition and emotion, (1999) 45-60.
[6] L. Fonseca, The Impact of data normalization on unsupervised continuous classification of landforms, International Geoscience and Remote Sensing Symposium, 2003.
[7] A. Harinder, and R.K. Sherma, DWT-based epileptic seizure detection from EEG signal using k-NN classifier, International Conference on Trends in Electronics and Informatics, 2017.
[8] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques. San Mateo, CA, USA: Morgan Kaufmann, 2006.
[9] C. W. Hsu, C. C. Chang, and C. J. Lin, A practical guide to support vector classification, Tech. Rep., 2003.
[10] N. Jatupaiboon, S. Pangum, and P. Israsena, Emotion classification using minimal EEG channels and frequency bands, 10th International Joint Conference on Computer Science and Software Engineering, (2013) 21-24.
[11] T. Jayalaklashmi, and A. Santhakumaran, Statistical normalization and back[12] R. Jenke, A. Peer, M. Buss, Feature extraction and selection for emotion recognition from EEG, IEEE Transactions on Affective Computing, 5 (3) (2014) 327-339.
[13] M. Kociolek, M. Strlecki, and S. Szymajda, On the influence of the image normalization scheme on texture classification accuracy, Signal Processing: Algorithms, Architectures, Arrangements, and Applications, 2018.
[14] S. Koelstra, et al., DEAP: A Database for Emotion Analysis; Using Physiological Signals, IEEE Transactions on Affecting Computing, 3 (1) (2012) 18-312.
[15] S. Kul, P. O. Durdu, and O. Akbulut, Performance Comparison of EEG Channels in Emotion Recognition, 27th Signal Processing and Communications Applications Conference (SIU), 2019.
[16] K. P. Kuntal, and K. S. Sudeep, Preprocessing for image classification by convolutional neural networks, IEEE International Conference on Recent Trends in Electronics Information Communication Technology, 2016.
[17] J. W. C. Medithe, and U. R. Nelakuditi, Study of normal and abnormal EEG, International Conference on Advanced Computing and Communication Systems, 2016.
[18] M. Mikhail, K. El Ayat, J. A. Coan, J. J. Allen, Using minimal number of electrodes for emotion recognition using brain signals produced from a new elicitation technique, International Journal of Autonomous and Adaptive Comm. System, 6 (1) (2013)80-97.
[19] G. W. Milligan and M. C. Cooper, A study of standardization of variables in cluster analysis, Journal of Classification, 5 (1988) 181–204.
[20] B. Mohamad, and D. Usman, Standardization and its effects on K-Means clustering algorithm, Research Journal of Applied Sciences, Engineering and Technology, 6 (17) (2013) 3299-3303.
[21] V. R. Patil, and R. G. Mihta, Impact of outlier removal and normalization approach in modified k-Means clustering algorithm, International Journal of Computer Science Issues, 8 (5) (2011) 331-336.
[22] Propagation for classification,” International Journal of Computer Theory and Engineering, 3 (1) (2011) 89-93.
[23] J. A., Russell, A circumplex model of affect, Journal of Personality and Social Psychology, 39 (6) (1980) 1161-1178.
[24] B. K. Singh, K. Verma, and A. S. Thoke, Investigations on impact of feature normalization techniques on classifier’s performance in breast tumor, International Journal of Computer Applications, vol. 116 (19) (2015) 2015.
[25] L. A. Shalabe, and Z. Shaban, Normalization as a preprocessing engine for data mining and the approach of preference matrix, International Conference on Dependability of Computer Systems, 2006.
[26] M. C. P. Souto, D. S. A. Araujo, I. G. Costa, R. G. F. Soarez, T. B. Ludermir, and A. Schliep, Comparative study on normalization procedures for cluster analysis of gene expression datasets,” IEEE International Joint Conference on Neural Networks, 2008.
[27] E. K. St Louis, and L. C. Frey (Eds), Electroencephalography (EEG): An Introductory Text and Atlas of Normal and Abnormal Findings in Adults, Children, and Infants, Chicago, IL: American Epilepsy Society, 2016.
[28] S. Theodoridis, and K. Koutroumbas, Pattern Recognition, 4th Edition, Academic Press, 2008.
[29] L. Xie, Q. Tian, and B. Zoang, Feature normalization for part-based image classification, IEEE International Conference on Image Processing, 2013.
[30] H. Zhang, H. Lin, and Y. Li, Impacts of feature normalization on optical and SAR data fusion for land use/land cover classification, IEEE Geoscience and Remote Sensing Letters, 12 (5) (2015) 1061-1065.
[31] J. Zhang, M. Chen, S. Zhao, S. Hu, Z. Shi, and Y. Cao, Relief F-based EEG sensor selection methods for emotion recognition, Sensors, 16 (10) (2016).
International Journal of Nonlinear Analysis and Applications
Volume 13, Issue 1
March 2022
Pages 773-781
  • Receive Date: 30 June 2021
  • Accept Date: 24 September 2021