An Example of Classification Using a Neural Network Trained by the Zebra Optimization Algorithm

Abstract

Artificial intelligence techniques are a broad field of research with training, computation and prediction capabilities. Among these techniques, artificial neural networks (ANNs) are widely used as a predictive model. Learning algorithms in ANN classifiers have great importance on the success of ANN. The ANN model generally uses gradient-based learning models. However, due to the disadvantages of gradient-based learning models in local search, they have begun to be replaced by heuristic-based algorithms in recent years. Heuristic algorithms have attracted the attention of many researchers in recent years due to their success in problem solving. In this study, the Zebra Optimization Algorithm (ZOA), which has been proposed recently to train ANN networks, was examined. The main purpose of this study is to train the neural network using ZOA and increase the sensitivity of the perceptron neural network. In this study, a new ANN network integrated with ZOA is proposed. In this study, a detailed parameter analysis was carried out to show the effect of the population size and maximum generation number parameter settings, which form the basis for ZOA, on the ANN network. Then, a parameter analysis was carried out for the number of layers, number of neurons and epoch values, which are important for ANN networks. Such an ideal ANN network has been identified. This ideal ANN model was run on seven different data sets and was successful in predicting accurate data. In addition, three different heuristic algorithms (Gazelle Optimization Algorithm (GOA), Prairie Dogs Optimization (PDO), and Osprey Optimization Algorithm (OOA)) selected from the literature were integrated on the same ANN model and compared with the results of ANN integrated with ZOA operated under similar conditions. The results reveal that the proposed algorithm leads to greater convergence with the neural network coefficient compared to other algorithms. In addition, the proposed method caused the prediction error in the neural network to decrease.

Keywords

• ANN
• Zebra
• Layer
• Neuron
• Network
• Prediction

Zebra Optimizasyon Algoritması Tarafından Eğitilmiş Bir Sinir Ağının Kullanıldığı Sınıflandırma Örneği

Abstract

Yapay zeka teknikleri eğitim, hesaplama ve tahmin yeteneklerine sahip geniş bir araştırma alanıdır. Bu teknikler arasında yapay sinir ağları (YSA) tahmin modeli olarak yaygın olarak kullanılmaktadır. YSA sınıflandırıcılarındaki öğrenme algoritmaları YSA'nın başarısı üzerinde büyük önem taşımaktadır. YSA modeli genellikle gradyan tabanlı öğrenme modellerini kullanır. Ancak yerel aramada gradyan tabanlı öğrenme modellerinin dezavantajları nedeniyle son yıllarda yerini sezgisel tabanlı algoritmalar almaya başlamıştır. Sezgisel algoritmalar problem çözmedeki başarılarından dolayı son yıllarda birçok araştırmacının dikkatini çekmiştir. Bu çalışmada YSA ağlarının eğitimi için son dönemde önerilen Zebra Optimizasyon Algoritması (ZOA) incelenmiştir. Bu çalışmanın temel amacı sinir ağını ZOA kullanarak eğitmek ve algılayıcı sinir ağının duyarlılığını arttırmaktır. Bu çalışmada ZOA ile entegre yeni bir YSA ağı önerilmektedir. Bu çalışmada ZOA'ya temel oluşturan popülasyon büyüklüğü ve maksimum nesil sayısı parametre ayarlarının YSA ağı üzerindeki etkisini göstermek amacıyla detaylı bir parametre analizi yapılmıştır. Daha sonra YSA ağları için önemli olan katman sayısı, nöron sayısı ve çağ değerleri için parametre analizi yapılmıştır. Böyle ideal bir YSA ağı belirlendi. Bu ideal YSA modeli yedi farklı veri seti üzerinde çalıştırılmış ve doğru verileri tahmin etmede başarılı olmuştur. Ayrıca literatürden seçilen üç farklı sezgisel algoritma (Ceylan Optimizasyon Algoritması (GOA), Çayır Köpekleri Optimizasyonu (PDO), and Balıkkartalı Optimizasyon Algoritması (OOA)) aynı YSA modeli üzerine entegre edilmiş ve benzer koşullar altında çalışan ZOA ile entegre edilmiş YSA'nın sonuçları ile karşılaştırılmıştır. Sonuçlar, önerilen algoritmanın diğer algoritmalara göre sinir ağı katsayısı ile daha fazla yakınsamaya yol açtığını ortaya koymaktadır. Ayrıca önerilen yöntem sinir ağındaki tahmin hatasının azalmasına neden olmuştur.

Keywords

• ANN
• Zebra
• Katman
• Nöron
• Ağ
• Tahmin

References

1. McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics, 5(4), 115-133. https://doi.org/10.1007/BF02478259
2. Feng, Z. K., & Niu, W. J. (2021). Hybrid artificial neural network and cooperation search algorithm for nonlinear river flow time series forecasting in humid and semi-humid regions. Knowledge-Based Systems, 211, 106580. https://doi.org/10.1016/j.knosys.2020.106580
3. Fuqua, D., & Razzaghi, T. (2020). A cost-sensitive convolution neural network learning for control chart pattern recognition. Expert Systems with Applications, 150, 113275. https://doi.org/10.1016/j.eswa.2020.113275
4. Chatterjee, S., Sarkar, S., Hore, S. Dey, N., Ashour, A. S., & Balas, V. E. (2017). Particle swarm optimization trained neural network for structural failure prediction of multistoried RC buildings. Neural Computing and Applications, 28, 2005-2016. https://doi.org/10.1007/s00521-016-2190-2
5. Ulas, M., Altay, O., Gurgenc, T., & Ozel, C. (2020). A new approach for prediction of the wear loss of PTA surface coatings using artificial neural network and basic, kernel-based, and weighted extreme learning machine. Friction, 8, 1102-1116. https://doi.org/ 10.1007/s40544-017-0340-0
6. Vosniakos, G. C., & Benardos, P. G. (2007). Optimizing feedforward artifcial neural network architecture. Engineering Applications of Artificial İntelligence, 20(3), 365-382. https://doi.org/10.1016/j.engappai.2006.06.005
7. Mosavi, M. R., Khishe, M., & Ghamgosar, A. (2016). Classification of sonar data set using neural network trained by gray wolf optimization. Neural Network World, 26(4), 393-415. https://doi.org/ 10.14311/NNW.2016.26.023
8. Mosavi, M. R., Khishe, M., Parvizi, G. R., Naseri, M. J., & Ayat, M. (2019). Training multi-layer perceptron utilizing adaptive best-mass gravitational search algorithm to classify sonar dataset. Archives of Acoustics, 44(1), 137-51. https://doi.org/10.24425/aoa.2019.126360

9. Mosavi, M. R., & Khishe, M. (2017). Training a feed-forward neural network using particle swarm optimizer with autonomous groups for sonar target classification. J. Circuits. Journal of Circuits, Systems and Computers, 26(11), 1-20. https://doi.org/10.1142/S0218126617501857
10. Yaghini, M., Khoshraftar, M. M., & Fallahi, M. (2011). HIOPGA: a new hybrid metaheuristic algorithm to train feedforward neural networks for prediction [Conference presentation]. In Proceedings of the International Conference on Data Science (ICDATA). The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp). Las Vegas, NV, USA. http://world-comp.org
11. Kiranyaz, S., Ince, T., Yildirim, A., & Gabbouj, M. (2009). Evolutionary artifcial neural networks by multi-dimensional particle swarm optimization. Neural Networks, 22(10), 1448-1462. https://doi.org/10.1016/j.neunet.2009.05.013
12. Khishe, M., & Mosavi, M. R. (2020). Classification of underwater acoustical dataset using neural network trained by Chimp Optimization Algorithm. Applied Acoustics, 157, 107005. https://doi.org/10.1016/j.apacoust.2019.107005
13. Afrakhteh, S., Mosavi, M., Khishe, M., & Ayatollahi, A. (2020). Accurate classification of EEG signals using neural networks trained by hybrid population-physic-based algorithm. International Journal of Automation and Computing, 17, 108-122. https://doi.org/10.1007/s11633-018-1158-3
14. Khishe, M., Mosavi, M. R., & Kaveh, M. (2017). Improved migration models of biogeography based optimization for sonar data set classification using neural network. Applied Acoustics, 118, 15-29. https://doi.org/10.1016/j.apacoust.2016.11.012
15. Khishe, M., Mosavi, M. R., & Moridi, A. (2018). Chaotic fractal walk trainer for sonar data set classification using multi-layer perceptron neural network and its hardware implementation. Applied Acoustics, 137, 121-39. https://doi.org/10.1016/j.apacoust.2018.03.012
16. Ravakhah, S., Khishe, M., Aghababaee, M., & Hashemzadeh, E. (2017). Sonar false alarm rate suppression using classification methods based on interior search algorithm. International Journal of Computer Science and Network Security, 17(7), 58-65.
17. Mosavi, M. R., Khishe, M., & Akbarisani, M. (2017). Neural network trained by biogeographybased optimizer with chaos for sonar data set classification. Wireless Personal Communications, 95(4), 4623-4642. https://doi.org/10.1007/s11277-017-4110-x
18. Kaveh, M., Khishe, M., & Mosavi, M. R. (2019). Design and implementation of a neighborhood search biogeography-based optimization trainer for classifying sonar dataset using multi-layer perceptron neural network. Analog Integrated Circuits Signal Process, 100, 405-428. https://doi.org/10.1007/s10470-018-1366-3
19. Mosavi, M. R., Khishe, M., Hatam Khani, Y., & Shabani, M. (2017). Training radial basis function neural network using stochastic fractal search algorithm to classify sonar dataset. Iranian Journal of Electrical & Electronic Engineering, 13(1), 100-111.
20. Dangare, C. S., & Apte, S. S. (2012). Improved study of heart disease prediction system using data mining classifcation techniques. International Journal of Computer Applications, 47(10), 44-48.
21. Movassagh, A. A., Alzubi, J. A., Gheisari, M., Rahimi, M., Mohan, S., Abbasi, A. A., & Nabipour, N. (2023). Artificial neural networks training algorithm integrating invasive weed optimization with differential evolutionary model. Journal of Ambient Intelligence and Humanized Computing, 14, 6017-6025. https://doi.org/10.1007/s12652-020-02623-6
22. Dang, N. M., Tran Anh, D., & Dang, T. D. (2021). ANN optimized by PSO and Firefly algorithms for predicting scour depths around bridge piers. Engineering with Computers, 37, 293-303. https://doi.org/10.1007/s00366-019-00824-y
23. Jamali, B., Rasekh, M., Jamadi, F., Gandomkar, R., & Makiabadi, F. (2019). Using PSO-GA algorithm for training artificial neural network to forecast solar space heating system parameters. Applied Thermal Engineering, 147, 647-660. https://doi.org/10.1016/j.applthermaleng.2018.10.070
24. Khatir, S., Tiachacht, S., Le Thanh, C., Ghandourah, E., Mirjalili, S., & Wahab, M. A. (2021). An improved Artificial Neural Network using Arithmetic Optimization Algorithm for damage assessment in FGM composite plates. Composite Structures, 273, 114287. https://doi.org/10.1016/j.compstruct.2021.114287
25. Gurgenc, E, Altay, O, & Altay, E. V. (2024). AOSMA-MLP: A novel method for hybrid metaheuristics artificial neural networks and a new approach for prediction of geothermal reservoir temperature. Applied Sciences, 14(8), 3534. https://doi.org/10.3390/app14083534
26. Altay, O., & Altay, E. V. (2023). A novel hybrid multilayer perceptron neural network with improved grey wolf optimizer. Neural Computing and Applications, 35, 529–556. https://doi.org/10.1007/s00521-022-07775-4
27. Altay, E. V., Gurgenc, E., Altay, O., & Dikici, A. (2022). Hybrid artificial neural network based on a metaheuristic optimization algorithm for the prediction of reservoir temperature using hydrogeochemical data of different geothermal areas in Anatolia (Turkey). Geothermics, 104, 102476. https://doi.org/10.1016/j.geothermics.2022.102476
28. Altay, O., & Gurgenc, T. (2024). GJO-MLP: a novel method for hybrid metaheuristics multi-layer perceptron and a new approach for prediction of wear loss of AZ91D magnesium alloy worn at dry, oil, and H-BN nanoadditive oil. Surface Review and Letters (SRL), 31, 06, 1-16. https://doi.org/10.1142/S0218625X24500483
29. Cinar, A. C. (2020). Training feed-forward multi-layer perceptron artificial neural networks with a tree-seed algorithm. Arabian Journal for Science and Engineering, 45, 10915–10938. https://doi.org/10.1007/s13369-020- 04872-1
30. Trojovská, E., Dehghani, M., & Trojovský, P. (2022). Zebra optimization algorithm: A new bio-inspired optimization algorithm for solving optimization algorithm. IEEE Access, 10, 49445-49473. https://doi.org/10.1109/ACCESS.2022.3172789
31. Agushaka, J. O., Ezugwu, A. E. & Abualigah, L. (2023). Gazelle optimization algorithm: a novel nature-inspired metaheuristic optimizer. Neural Computing and Applications, 35, 4099–4131. https://doi.org/10.1007/s00521-022-07854-6
32. Ezugwu, A. E., Agushaka, J. O., Abualigah, L., Mirjalili, S., & Gandomi, A. H. (2022). Prairie dog optimization algorithm. Neural Computing and Applications, 34, 20017–20065. https://doi.org/10.1007/s00521-022-07530-9
33. Dehghani, M., & Trojovský, P. (2023). Osprey optimization algorithm: A new bio-inspired metaheuristic algorithm for solving engineering optimization problems. Frontiers in Mechanical Engineering, 8, 1126450. https://doi.org/10.3389/fmech.2022.1126450
34. Yang, J., & Ma, J. (2019). Feed-forward neural network training using sparse representation. Expert Systems with Applications, 116, 255–264. https://doi.org/10.1016/j.eswa.2018.08.038
35. Siemon, H. P., & Ultsch, A. (1990, July 9–13). Kohonen networks on transputers: implementation and animation [Conference presentation]. In: International Neural Network Conference (INNC), Springer, Dordrecht. https://doi.org/10.1007/978-94-009-0643-3_31
36. Orr, M. (1996). Introduction to radial basis function networks. Technical Report, center for cognitive science. The University of Edinburgh.
37. Kousik, N., Natarajan, Y., Raja, R. A., Kallam, S., Patan, R., Gandomi, A. H. (2021). Improved salient object detection using hybrid convolution recurrent neural network. Expert Systems with Applications, 166, 114064. https://doi.org/10.1016/j.eswa.2020.114064
38. Winoto, A. S., Kristianus, M., & Premachandra, C. (2020). Small and slim deep convolutional neural network for mobile device. IEEE Access, 8, 125210-125222. https://doi.org/10.1109/ACCESS. 2020.3005161
39. Ghosh-Dastidar, S., & Adeli, H. (2009). Spiking neural networks. International journal of neural systems, 19, 295-308. https://doi.org/10.1142/ S0129065709002002
40. Fekri-Ershad, S. (2020). Bark texture classification using improved local ternary patterns and multilayer neural network. Expert Systems with Applications, 158, 113509. https://doi.org/10.1016/j.eswa.2020.113509
41. Ren, H., Ma, Z., Lin, W., Wang, S., & Li, W. (2019). Optimal design and size of a desiccant cooling system with onsite energy generation and thermal storage using a multilayer perceptron neural network and a genetic algorithm. Energy Conversion and Management, 180, 598-608. https://doi.org/10.1016/j.enconman.2018.11.020
42. Aljarah, I., Faris, H., & Mirjalili, S. (2018). Optimizing connection weights in neural networks using the whale optimization algorithm. Soft Computing, 22(1), 1-15. https://doi.org/10.1007/s00500-016-2442-1
43. Bache, K., & Lichman, M. (2024, December 5). UCI Machine learning repository. http:// archive.ics.uci.edu/ml.