EEG Sinyallerinden Meta-Sezgisel Optimizasyon Algoritmalarına Dayalı Özellik Seçimi

Abstract

Özellik seçimi makine öğrenmesi alanında, sınıflandırma işlemlerinin öncesinde bulunan önemli bir aşamadır. Ayırt edici özelliklerin iyi belirlendiği durumlarda, sınıflandırma başarı performası artar ve daha az özellik değerlendirildiği için hesaplama maliyeti azalır. Elektroensefalografi (EEG) yöntemi ile beynin spontan elektrik aktiviteleri ölçülmektedir. EEG sinyallerinin analiz edilmesiyle, duygu durumu, hastalık teşhisi, anomali tespiti yapılabilmektedir. Bu çalışmada, EEG sinyallerinden epilepsi teşhisi amacıyla, sınıflandırmada kullanılan özelliklerin seçilmesine çalışılmıştır. Kullanılan verisetinde, epileptik ve sağlıklı bireylerden oluşan 2 sınıf mevcuttur. Verisetinde, EEG sinyallerinin alt bileşenlerinden 667 özellik vardır. Sınıflandırma için bu 667 özelikten meta-segisel optimizasyon algoritmaları ile ayırt edici özellikler seçilmiştir. Sınıflandırma için k en yakın komşuluk algoritması kullanılmıştır. EEG sinyallerinin alt bileşenlerinin tamamı ile yapılan sınıflandırmada, %60,05 doğruluk başarısı elde edilmiştir. Gri Kurt Optimizasyonu, Balina Optimizasyonu ve Harris Şahinler Optimizasyonu metasezgisel algoritmaları ile özellik seçimi sonucunda, sınıflandırma başarısı %80,16 olarak elde edilmiştir. Bu sınıflandırma başarısı 5-10 özellik kullanılarak elde edilebilmektedir. Sonuç olarak meta-sezgisel optimizasyon algoritmaları ile daha az özellik seçilerek doğruluk oranı artmış ve hesaplama maliyeti azalmıştır.

Keywords

• Balina optimizasyonu algoritması
• Elektroensefalografi
• Gri kurt optimizasyon algoritması
• Harris şahini optimizasyonu algoritması
• Özellik seçimi

Feature Selection Based On Meta-Heuristic Optimization Algorithms From EEG Signals

Abstract

Feature selection is an important stage in the field of machine learning before classification processes. In cases where distinguishing features are well determined, classification success performance increases. Another advantage is that the computational cost is reduced because fewer features are evaluated. Electroencephalography (EEG) is a method that measures spontaneous electrical activities of the brain. By analyzing EEG signals, emotional state, disease diagnosis and anomaly detection can be made. In this study, feature selection for classification in epilepsy diagnosis from EEG signals was attempted. The dataset used has two classes, consisting of epileptic and healthy individuals. There are 667 features in the dataset from subcomponents of EEG signals. For classification, distinctive features were selected from these 667 features with metaheuristic optimization algorithms. The k nearest neighbor algorithm was used for classification. In the classification made with all subcomponents of EEG signals, 60.05% accuracy was achieved. As a result of feature selection with Gray Wolf Optimization, Whale Optimization and Harris Hawks Optimization metaheuristic algorithms, the classification success was achieved as 80.16%. This classification success can be achieved by using 5-10 features. As a result, it is seen that the accuracy rate increases and the computational cost decreases by selecting fewer features with meta-heuristic optimization algorithms.

Keywords

• Whale optimization algorithm
• Electroencephalography
• Grey wolf optimization algorithm
• Harris hawks optimization algorithm
• Feature selection

References

1. Abdel-Basset M, Sallam KM, Mohamed R, Elgendi I, Munasinghe K, Elkomy OM. 2021. An improved binary grey-wolf optimizer with simulated annealing for feature selection. IEEE Access, 9: 139792-139822. https://doi.org/10.1109/ACCESS.2021.3117853.
2. Acharya UR, Sree SV, Swapna G, Martis RJ, Suri JS. 2013. Automated EEG analysis of epilepsy: A Review. Knowledge Based Syst, 45: 147-165. https://doi.org/10.1016/j.knosys.2013.02.014.
3. Aljarah I, Faris H, Mirjalili S. 2018. Optimizing connection weights in neural networks using the whale optimization algorithm. Soft Comput, 22(1): 1-15. https://doi.org/10.1007/s00500-016-2442-1.
4. Al-Tashi Q, Abdulkadir SJ, Rais HM, Mirjalili S, Alhussian H, Ragab MG, Alqushaibi A. 2020. Binary multi-objective grey wolf optimizer for feature selection in classification. IEEE Access, 8: 106247-106263. https://doi.org/10.1109/ACCESS.2020.3000040.
5. Al-Tashi Q, Kadir SJA, Rais HM, Mirjalili S, Alhussian H. 2019. Binary optimization using hybrid grey wolf optimization for feature selection. IEEE Access, 7: 39496-39508. https://doi.org/10.1109/ACCESS.2019.2906757.
6. Claassen J, Hirsch LJ, Mayer SA. 2003. Treatment of status epilepticus: a survey of neurologists. J Neurol Sci, 211(1-2): 37-41. https://doi.org/10.1016/s0022-510x(03)00036-4.
7. Das P, Das A. 2020. Adaptive gabor filtering using grey wolf optimization for enhancement of brain MRI. IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE), December 26-27, Naya Raipur, India, pp: 356-359. https://doi.org/10.1109/WIECON-ECE52138.2020.9397926.
8. Elgamal ZM, Yasin NBM, Tubishat M, Alswaitti M, Mirjalili S. 2020. An improved harris hawks optimization algorithm with simulated annealing for feature selection in the medical field. IEEE Access, 8: 186638-186652. https://doi.org/10.1109/ACCESS.2020.3029728.

9. Hassine OB. 2024a. Epilepsy Detection Using EEG Signals, Datasets. URL: https://www.kaggle.com/datasets/oussamabenhassine/epilepsy-detection-using-eeg-signals (erişim tarihi: Nisan, 25, 2024).
10. Hassine OB. 2024b. Epilepsy Detection Using EEG Signals, Project. URL: https://github.com/oussamabenhassine/Epilepsy-Dectection-using-EEG-signlas/ (erişim tarihi: Nisan, 25, 2024).
11. Heidari AA, Mirjalili S, Faris H, Aljarah I, Mafarja M, Chen H. 2019. Harris hawks optimization: Algorithm and applications. Future generation computer systems, 97: 849-872. https://doi.org/10.1016/j.future.2019.02.028.
12. Hussien AG, Hassanien AE, Houssein EH, Bhattacharyya S, Amin M. 2019. S-shaped binary whale optimization algorithm for feature selection. In: Recent Trends in Signal and Image Processing. Advances in Intelligent Systems and Computing, vol 727. Springer, May 10, Singapore. https://doi.org/10.1007/978-981-10-8863-6_9.
13. Hussien AG, Oliva D, Houssein EH, Juan AA, Yu X. 2020. Binary whale optimization algorithm for dimensionality reduction. Mathematics, 8(10): 1-24. https://doi.org/10.3390/math8101821.
14. Iasemidis LD, Shiau DS, Chaovalitwongse W, Sackellares JC, Pardalos PM, Principe JC, Carney PR, Prasad A, Veeram B. 2003. Adaptive epileptic seizure prediction system. IEEE Transact Biomedic Eng, 50(5): 616-627. https://doi.org/10.1109/TBME.2003.810689.
15. Kumar SJ, Bhuvaneswari P. 2012. Analysis of Electroencephalography (EEG) Signals and Its Categorization. Procedia Eng, 38: 2525-2536. https://doi.org/10.1016/j.proeng.2012.06.298.
16. Mirjalili S, Lewis A. 2016. The whale optimization algorithm. Adv Eng Software, 95: 51-67. https://doi.org/10.1016/j.advengsoft.2016.01.008.
17. Mirjalili S, Mirjalili SM, Lewis A. 2014. Grey wolf optimizer. Adv Eng Software, 69: 46-61. https://doi.org/10.1016/j.advengsoft.2013.12.007.
18. Nadimi-Shahraki MH, Zamani H, Mirjalili S. 2022. Enhanced whale optimization algorithm for medical feature selection: A COVID-19 case study. Comput Biol Medic, 148: 105858. https://doi.org/10.1016/j.compbiomed.2022.105858.
19. Sayed GI, Darwish A, Hassanien AE. 2020. Binary whale optimization algorithm and binary moth flame optimization with clustering algorithms for clinical breast cancer diagnoses. J Classification, 37(1): 66-96. https://doi.org/0.1007/s00357-018-9297-3.
20. Thaher T, Heidari AA, Mafarja M, Dong JS, Mirjalili S. 2020. Binary Harris Hawks optimizer for high-dimensional, low sample size feature selection. In Evolutionary machine learning techniques. Springer, Singapore, pp: 251-272. https://doi.org/10.1007/978-981-32-9990-0_12.
21. Vijayanand R, Devaraj D. 2020. A novel feature selection method using whale optimization algorithm and genetic operators for intrusion detection system in wireless mesh network. IEEE Access, 8: 56847-56854. https://doi.org/10.1109/ACCESS.2020.2978035.
22. Wang JS, Li SX. 2019. An improved grey wolf optimizer based on differential evolution and elimination mechanism. Sci Rep, 9(1): 1-21. https://doi.org/10.1038/s41598-019-43546-3.
23. Zhang Y, Liu R, Wang X, Chen H, Li C. 2021. Boosted binary Harris hawks optimizer and feature selection. Eng Comput, 37(4): 3741-3770. https://doi.org/10.1007/s00366-020-01028-5.