Comparison of Harmony Search Variants on EEG Noise Removal Problem

Abstract

Electro-encephalogram (EEG) scan is a medical imaging system that measures the electrical activities in the brain and gives information about whether the brain is functioning successfully. These scanning signals, which are made by placing electrodes on the human skull, are exposed to noise due to other activities in the person's body and external factors. The harmony search (HS) algorithm is a semi-heuristic algorithm inspired by the composing process when creating musical works. In this study, the problem of removing noise from EEG signals with the HS algorithm and its variants developed afterwards was tried to be optimized and the performances of the variants on this problem, which is a big data optimization problem, were compared. The examined results reveal that the subsequently developed HS variants demonstrate superior performance compared to the initial version of the HS algorithm in big data optimization problems.

Keywords

• Big data optimization
• harmony search algorithm
• EEG

Harmoni Arama Varyantlarının EEG Gürültü Temizleme Problemi Üzerinden Kıyaslanması

Öz

Elektro-ensefalogram (EEG) taraması, beyinde oluşan elektriksel aktiviteleri ölçümleyerek beynin fonksiyonlarını başarılı şekilde yerine getirip getirmediği hakkında bilgi veren bir tıbbi görüntüleme sistemidir. İnsan kafatasına elektrotlar yerleştirilerek yapılan bu tarama sinyalleri kişinin vücudundaki diğer aktivitelerden ve dış faktörlerden dolayı gürültüye maruz kalmaktadır. Harmoni arama (HS) algoritması, müzik eserleri oluşturulurken gerçekleştirilen besteleme sürecinden esinlenen bir yarı-sezgisel algoritmadır. Bu çalışmada HS algoritması ve sonrasında geliştirilen varyantları ile EEG sinyallerinin gürültülerden temizlenmesi problemi optimize edilmeye çalışılmış ve varyantların bir büyük veri optimizasyon problemi olan bu problem üzerindeki başarımları kıyaslanmıştır. İncelenen sonuçlar, büyük veri optimizasyon problemleri üzerinde sonradan geliştirilen HS varyantlarının, HS algoritmasının ilk versiyonundan daha üstün performans gösterme kabiliyetine sahip olduğunu ortaya koymaktadır.

Anahtar Kelimeler

• Büyük veri optimizasyonu
• harmoni arama algoritması
• EEG

Kaynakça

1. [1] C.-W. Tsai, C.-F. Lai, H.-C. Chao, and A. V. Vasilakos. Big data analytics: a survey. Journal of Big data, 2(1):21, 2015.
2. [2] V. N. Gudivada, R. Baeza-Yates, and V. V. Raghavan. Big data: Promises and problems. Computer, 48(3):20–23, 2015.–
3. [3] H. A. Abbass. Calibrating independent component analysis with laplacian reference for real-time eeg artifact removal. In International Conference on Neural Information Processing, pages 68–75, 2014.
4. [4] S. Elsayed and R. Sarker. An adaptive configuration of differential evolution algorithms for big data. In IEEE Congress on Evolutionary Computation (CEC). IEEE, pages 695–702, 2015.
5. [5] S. Elsayed and R. Sarker. Differential evolution framework for big data optimization. Memetic Computing, 8(1):17–33, 2016.
6. [6] M. A. El Majdouli, S. Bougrine, I. Rbouh, and A. A. El Imrani. A fireworks algorithm for single objective big optimization of signals. In 2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA), pages 1–7. IEEE, 2016.
7. [7] M. A. Meselhi, S. M. Elsayed, D. L. Essam, and R. A. Sarker. Fast differential evolution for big optimization. In 2017 11th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), pages 1–6. IEEE, 2017.
8. [8] H. Wang, W. Wang, L. Cui, H. Sun, J. Zhao, Y. Wang, and Y. Xue. A hybrid multiobjective firefly algorithm for big data optimization. Applied Soft Computing, 69:806–815, 2018.

9. [9] S. Aslan. An Artificial Bee Colony-Guided Approach for Electro-Encephalography Signal Decomposition-Based Big Data Optimization. International Journal of Information Technology & Decision Making, 19(02), 561-600, 2020.
10. [10] Aslan, S., & Karaboga, D. (2020). A genetic Artificial Bee Colony algorithm for signal reconstruction based big data optimization. Applied Soft Computing, 88, 106053.
11. [11] İleri, S. C. , Aslan, S. & Demirci, S. (2022). Büyük Veri Optimizasyonu için Kaynak-Bağlantılı Harmoni Arama Algoritmasının Performans Analizi . Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, 15 (2) , 151-160 . DOI: 10.54525/tbbmd.1090787.
12. [12] Shi, B., Wang, Q., Yin, S., Yue, Z., Huai, Y., & Wang, J. (2021). A binary harmony search algorithm as channel selection method for motor imagery-based BCI. Neurocomputing, 443, 12-25. https://doi.org/10.1016/j.neucom.2021.02.051.
13. [13] Nakra, A., Duhan, M. Deep neural network with harmony search based optimal feature selection of EEG signals for motor imagery classification. Int. j. inf. tecnol. 15, 611–625 (2023). https://doi.org/10.1007/s41870-021-00857-x.
14. [14] S. K. Goh, H. A. Abbass, K. C. Tan, and A. Al Mamun. Artifact removal from eeg using a multi-objective independent component analysis model. In International Conference on Neural Information Processing, pages 570–577, 2014.
15. [15] S. K. Goh, K. C. Tan, A. Al-Mamun, and H. A. Abbass. Evolutionary big optimization (bigopt) of signals. In 2015 IEEE Congress on Evolutionary Computation (CEC), pages 3332–3339. IEEE, 2015.
16. [16] Geem, Z. W., Kim, J. H., & Loganathan, G. V. (2001). A new heuristic optimization algorithm: harmony search. simulation, 76(2), 60-68.
17. [17] Dubey, M., Kumar, V., Kaur, M., & Dao, T. P. (2021). A systematic review on harmony search algorithm: theory, literature, and applications. Mathematical Problems in Engineering, 2021, 1-22.
18. [18] Qin, F., Zain, A. M., & Zhou, K. Q. (2022). Harmony search algorithm and related variants: A systematic review. Swarm and Evolutionary Computation, 101126.
19. [19] Mahdavi, M., Fesanghary, M., & Damangir, E. (2007). An improved harmony search algorithm for solving optimization problems. Applied mathematics and computation, 188(2), 1567-1579.
20. [20] Omran, M. G., & Mahdavi, M. (2008). Global-best harmony search. Applied mathematics and computation, 198(2), 643-656.
21. [21] Cheng, Y. M., Li, L., Lansivaara, T., Chi, S. C., & Sun, Y. J. (2008). An improved harmony search minimization algorithm using different slip surface generation methods for slope stability analysis. Engineering Optimization, 40(2), 95-115.
22. [22] Zou, D., Gao, L., Wu, J., Li, S., & Li, Y. (2010). A novel global harmony search algorithm for reliability problems. Computers & Industrial Engineering, 58(2), 307-316.
23. [23] Ouyang, H. B., Gao, L. Q., Li, S., Kong, X. Y., Wang, Q., & Zou, D. X. (2017). Improved harmony search algorithm: LHS. Applied Soft Computing, 53, 133-167.
24. [24] BigOpt. (2015). http://www.husseinabbass.net/BigOpt.html. (Erişim Tarihi:08 Ekim 2024)