Öznitelik seçimi problemleri için ikili beyaz köpekbalığı optimizasyon algoritması

Öznitelik seçimi, makine öğrenmesi problemlerinde kabul edilebilir bir sınıflandırma doğruluğunu hedeflerken, aynı zamanda büyük ölçekli bir veri kümesinden gereksiz, alakasız ve gürültülü öznitelikleri elimine etme işlemidir. Aslında öznitelik seçimi de bir optimizasyon problemi olarak nitelendirilebilir. Literatürde metasezgisel optimizasyon algoritmalarının, optimum öznitelik alt kümelerinin bulunmasında başarılı performansa sahip olduğu çalışmalar mevcuttur. Bu çalışmada da beyaz köpek balığı optimizasyon algoritması (BKO), S, V ve U-şekilli transfer fonksiyonları ile ikili forma dönüştürülerek öznitelik seçimi için kullanılmıştır. Önerilen yöntemler UCI veri deposundaki sekiz farklı veri kümesi üzerinde uygulanmış ve sınıflandırma doğrulukları, uygunluk değerleri ve seçilen öznitelik sayıları yönünden incelenmiştir. Sınıflandırıcı olarak k-en yakın komşuluk sınıflandırıcısı kullanılmıştır. Daha sonra farklı metasezgisel algoritmalarla karşılaştırılarak Freidman sıralama testi uygulanmıştır. Deneysel sonuçlar önerilen metotların, öznitelik seçiminde başarılı olduğunu ve sınıflandırma başarısını artırdığını göstermektedir. Özellikle V ve U-şekilli versiyonların daha kararlı ve yüksek doğrulukla sonuçlar ürettiği yorumu yapılabilir.

Anahtar Kelimeler:

Beyaz köpek balığı optimizasyonu algoritması, Metasezgisel algoritmalar, Öznitelik seçimi, Sınıflandırma, Transfer fonksiyonu

Binary white shark optimization algorithm for feature selection problems

Feature selection is the process of eliminating redundant, irrelevant and noisy features from a large-scale dataset while aiming for acceptable classification accuracy in machine learning problems. In fact, feature selection can also be described as an optimization problem. In the literature, there are studies in which metaheuristic optimization algorithms have successful performance in finding optimal feature subsets. In this study, the white shark optimization algorithm (WSO) has been converted into binary form with S, V and U-shaped transfer functions and used for feature selection. The proposed methods have been applied on eight different datasets in the UCI data repository and examined in terms of classification accuracies, fitness values and selected feature numbers. The k-nearest neighbor classifier has been used as a classifier. Then, Freidman rank test has been applied by comparing with different metaheuristic algorithms. Experimental results show that the proposed methods are successful in feature selection and increase the classification success. It can be interpreted that especially the V and U-shaped versions produce more stable and high accuracy results.

Keywords:

White shark optimization algorithm Metaheuristic algorithms, Feature selection, Classification Transfer function, Classification, Transfer function,

PDF

___

Abdel-Basset, M., Abdel-Fatah, L., & Sangaiah, A. K. (2018). Metaheuristic algorithms: A comprehensive review. Computational intelligence for multimedia big data on the cloud with engineering applications, 185-231. doi:https://doi.org/10.1016/B978-0-12-813314-9.00010-4
Abualigah, L., Diabat, A., Mirjalili, S., Abd Elaziz, M., & Gandomi, A. H. (2021). The arithmetic optimization algorithm. Computer Methods in Applied Mechanics, 376, 113609. doi:https://doi.org/10.1016/j.cma.2020.113609
Arora, S., & Anand, P. (2019). Binary butterfly optimization approaches for feature selection. Expert Systems with Applications, 116, 147-160. doi:https://doi.org/10.1016/j.eswa.2018.08.051
Awadallah, M. A., Hammouri, A. I., Al-Betar, M. A., Braik, M. S., & Abd Elaziz, M. (2022). Binary Horse herd optimization algorithm with crossover operators for feature selection. Computers in Biology Medicine, 141, 105152. doi:https://doi.org/10.1016/j.compbiomed.2021.105152
Bäck, T., & Schwefel, H.-P. (1993). An overview of evolutionary algorithms for parameter optimization. Evolutionary computation, 1(1), 1-23. doi:https://doi.org/10.1162/evco.1993.1.1.1
Braik, M., Hammouri, A., Atwan, J., Al-Betar, M. A., & Awadallah, M. A. J. K.-B. S. (2022). White Shark Optimizer: A novel bio-inspired meta-heuristic algorithm for global optimization problems. 243, 108457. doi:https://doi.org/10.1016/j.knosys.2022.108457
Dash, M., & Liu, H. (1997). Feature selection for classification. Intelligent data analysis, 1(1-4), 131-156. doi:https://doi.org/10.1016/S1088-467X(97)00008-5
Dehghani, M., Montazeri, Z., Dehghani, A., Malik, O. P., Morales-Menendez, R., Dhiman, G., Nouri, N., Ehsanifar, A., Guerrero, J. M., & Ramirez-Mendoza, R. A. (2021). Binary spring search algorithm for solving various optimization problems. Applied Sciences, 11(3), 1286. doi:https://doi.org/10.3390/app11031286
Dhiman, G., & Kumar, V. (2019). Seagull optimization algorithm: Theory and its applications for large-scale industrial engineering problems. Knowledge-based systems, 165, 169-196. doi:https://doi.org/10.1016/j.knosys.2018.11.024
Duda, R. O., Hart, P. E., & Stork, D. G. (2001). Pattern Classification, Hoboken. In: NJ: Wiley.
Fan, Q., Chen, Z., & Xia, Z. (2020). A novel quasi-reflected Harris hawks optimization algorithm for global optimization problems. Soft Computing, 24(19), 14825-14843. doi:https://doi.org/10.1007/s00500-020-04834-7
Friedman, M. (1940). A comparison of alternative tests of significance for the problem of m rankings. The Annals of Mathematical Statistics, 11(1), 86-92. doi:https://doi.org/10.1214/aoms/1177731944
Grabczewski, K., & Jankowski, N. (2005). Feature selection with decision tree criterion. Fifth International Conference on Hybrid Intelligent Systems (HIS'05) (ss. 6 pp.).
Hichem, H., Elkamel, M., Rafik, M., Mesaaoud, M. T., & Ouahiba, C. (2019). A new binary grasshopper optimization algorithm for feature selection problem. Journal of King Saud University-Computer Information Sciences. doi:https://doi.org/10.1016/j.jksuci.2019.11.007
Houssein, E. H., Saad, M. R., Hashim, F. A., Shaban, H., & Hassaballah, M. (2020). Lévy flight distribution: A new metaheuristic algorithm for solving engineering optimization problems. Engineering Applications of Artificial Intelligence, 94, 103731. doi:https://doi.org/10.1016/j.engappai.2020.103731
Hussien, A. G., Hassanien, A. E., Houssein, E. H., Amin, M., & Azar, A. T. (2020). New binary whale optimization algorithm for discrete optimization problems. Engineering Optimization, 52(6), 945-959. doi:https://doi.org/10.1080/0305215X.2019.1624740
Jh, H. (1975). Adaptation in natural and artificial systems. Ann Arbor.
Karaboga, D., Gorkemli, B., Ozturk, C., & Karaboga, N. (2014). A comprehensive survey: artificial bee colony (ABC) algorithm and applications. Artificial Intelligence Review, 42(1), 21-57. doi:https://doi.org/10.1007/s10462-012-9328-0
Khanesar, M. A., Teshnehlab, M., & Shoorehdeli, M. A. (2007). A novel binary particle swarm optimization. 2007 Mediterranean conference on control & automation (ss. 1-6).
Kittler, J. (1978). Feature set search algorithms. Pattern recognition signal processing, 41-60.
Li, S., Chen, H., Wang, M., Heidari, A. A., & Mirjalili, S. (2020). Slime mould algorithm: A new method for stochastic optimization. Future Generation Computer Systems, 111, 300-323. doi:https://doi.org/doi.org/10.1016/j.future.2020.03.055
Li, Y., Zhu, X., & Liu, J. (2020). An improved moth-flame optimization algorithm for engineering problems. Symmetry, 12(8), 1234. doi:https://doi.org/10.3390/sym12081234
Long, W., & Xu, S. (2016). A novel grey wolf optimizer for global optimization problems. 2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) (ss. 1266-1270).
Luo, K., & Zhao, Q. (2019). A binary grey wolf optimizer for the multidimensional knapsack problem. Applied Soft Computing, 83, 105645. doi:https://doi.org/10.1016/j.asoc.2019.105645
Mirjalili, S. (2016). SCA: a sine cosine algorithm for solving optimization problems. Knowledge-based systems, 96, 120-133. doi:https://doi.org/10.1016/j.knosys.2015.12.022
Nadimi-Shahraki, M. H., Banaie-Dezfouli, M., Zamani, H., Taghian, S., & Mirjalili, S. (2021). B-MFO: a binary moth-flame optimization for feature selection from medical datasets. Computers in Biology, 10(11), 136.
Pal, M., & Foody, G. M. (2010). Feature selection for classification of hyperspectral data by SVM. EEE Transactions on Geoscience Remote Sensing
48(5), 2297-2307. doi:https://doi.org/10.1109/TGRS.2009.2039484
Poli, R., Kennedy, J., & Blackwell, T. (2007). Particle swarm optimization. Swarm intelligence, 1(1), 33-57. doi:https://doi.org/10.1007/s11721-007-0002-0
Quinlan, J. R. (1986). Induction of decision trees. Machine learning, 1(1), 81-106.
Robnik-Šikonja, M., & Kononenko, I. J. M. l. (2003). Theoretical and empirical analysis of ReliefF and RReliefF. 53(1), 23-69.
Saeys, Y., Inza, I., & Larranaga, P. J. b. (2007). A review of feature selection techniques in bioinformatics. 23(19), 2507-2517. doi:https://doi.org/10.1093/bioinformatics/btm344
Siedlecki, W., & Sklansky, J. (1993). On automatic feature selection. In Handbook of pattern recognition and computer vision (ss. 63-87): World Scientific.
Taghian, S., & Nadimi-Shahraki, M. H. (2019). Binary sine cosine algorithms for feature selection from medical data. Advanced Computing: An International Journal (ACIJ), 10. doi:https://doi.org/10.5121/acij.2019.10501
Thaher, T., Heidari, A. A., Mafarja, M., Dong, J. S., & Mirjalili, S. (2020). Binary Harris Hawks optimizer for high-dimensional, low sample size feature selection. In Evolutionary machine learning techniques (ss. 251-272): Springer.
Too, J., & Rahim Abdullah, A. (2020). Binary atom search optimisation approaches for feature selection. Connection Science, 32(4), 406-430. doi:https://doi.org/10.1080/09540091.2020.1741515