Connectivity optimization of artificial neural network with evolutionary computation algorithms

Merve Yilmaz; Mustafa Servet Kıran

doi:10.31127/tuje.1962552

Connectivity optimization of artificial neural network with evolutionary computation algorithms

Abstract

Human intelligence has historically produced various solutions to the challenges it has faced thanks to its cognitive abilities such as learning, remembering, comparing, and problem-solving. One of the most fundamental examples of artificial intelligence approaches that emerged by modeling these behaviors specific to intelligence is the artificial neural network (ANN), inspired by the biological nervous system. ANNs, with their similarity to biological nervous systems, present a highly complex system, and with technological advancements, the modeling and applicability of these systems are constantly increasing. In this study, a new ANN architecture inspired by the biological nervous system was designed. To improve the classification performance of the developed architecture, the connections in the network were treated as a binary optimization problem and optimized using the Binary Particle Swarm Optimization (BPSO) algorithm. Following the architecture design, the weights of the connections in the network were optimized using the Particle Swarm Optimization (PSO) algorithm which works with continuous values. As a result, a network architecture compatible with the biological nervous system, flexible in structure, and highly applicable to various problem types was created. The developed method was tested on Breast Cancer, Hepatitis, Mammographic Mass and Haberman’s Survival datasets. Additionally, proposed model compared with the Genetic Algorithm (GA), one of the most widely used evolutionary computation methods in the literature for connection optimization. Specifically, the proposed model reduces the input layer size from 5 to 2 in the Mammographic Mass domain by applying aggressive feature selection. It successfully reduces computational complexity by eliminating up to 12 hidden neurons in the Hepatitis dataset without sacrificing classification accuracy, thus providing significant structural pruning. Furthermore, it demonstrates high stability across all metrics with minimal standard deviation, proving that the synergy between binary and continuous swarm variants generates highly concise, lightweight, and efficient neural network topologies

Keywords

References

Yılmaz, M. (2022). Connectivity optimization of artificial neural network with evolutionary computation algorithms [Master's thesis, Konya Technical University].
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), https://doi.ieeecomputersociety.org/10.1109/CVPR.2016.90
Avola, D., Cinque, L., Fagioli, A., & Foresti, G. L. (2022). SIRe-Networks: Convolutional neural networks architectural extension for information preservation via skip/residual connections and interlaced auto-encoders. Neural Networks, 153, 386-398. https://doi.org/https://doi.org/10.1016/j.neunet.2022.06.030
Abbass, M. A. B. (2023). A comprehensive framework based on Bayesian optimization and skip connections artificial neural networks to predict buildings energy performance. Journal of Building Engineering, 77, 107523. https://doi.org/https://doi.org/10.1016/j.jobe.2023.107523
Chechik, G., Meilijson, I., & Ruppin, E. (1998). Synaptic Pruning in Development: A Computational Account. Neural Computation, 10, 1759-1777. https://doi.org/10.1162/089976698300017124
Han, S., Pool, J., Tran, J., & Dally, W. J. (2015). Learning both weights and connections for efficient neural networks Proceedings of the 29th International Conference on Neural Information Processing Systems - Volume 1, Montreal, Canada.
Atashgahi, Z., Pieterse, J., Liu, S., Mocanu, D., Veldhuis, R., & Pechenizkiy, M. (2022). A brain-inspired algorithm for training highly sparse neural networks. Machine Learning, 111, 1-42. https://doi.org/10.1007/s10994-022-06266-w
Wong, K., Dornberger, R., & Hanne, T. (2022). An analysis of weight initialization methods in connection with different activation functions for feedforward neural networks. Evolutionary Intelligence, 17. https://doi.org/10.1007/s12065-022-00795-y

Arora, R. K. (2015). Optimization Algorithms and Applications. Taylor & Francis Group. 203-220.
Shojaei, I., & Rahami, H. (2022). A heuristic swarm-based optimization method using multi-variate normal distributions with self-adaptive variance matrices. Structures, 36, 372-391. https://doi.org/https://doi.org/10.1016/j.istruc.2021.12.027
Rardin, R. L., & Uzsoy, R. (2001). Experimental Evaluation of Heuristic Optimization Algorithms: A Tutorial. Journal of Heuristics, 7(3), 261-304. https://doi.org/10.1023/A:1011319115230
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533-536. https://doi.org/10.1038/323533a0
Khotanzad, A., Abaye, A., & Maratukulam, D. (1994, 28 June-2 July 1994). An adaptive recurrent neural network system for multi-step-ahead hourly prediction of power system loads. Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94),
Hongkang, W., Li, L., Yong, W., Fanjia, M., Haihua, W., & Sigrimis, N. A. (2018). Recurrent Neural Network Model for Prediction of Microclimate in Solar Greenhouse. IFAC-PapersOnLine, 51(17), 790-795. https://doi.org/https://doi.org/10.1016/j.ifacol.2018.08.099
Parra Hernández, R., Álvarez Gallegos, J., & Hernández Reyes, J. A. (1998). Simple recurrent neural network: A neural network structure for control systems1This work was supported in part by COSNET, CONACYT and by The Ministry of Education (SEP) México.1. Neurocomputing, 23(1), 277-289. https://doi.org/https://doi.org/10.1016/S0925-2312(98)00084-8
Jianhui, W., Qibing, J., & Shusheng, G. (1998). A Novel Recurrent Neural Network and its Algorithm. IFAC Proceedings Volumes, 31(25), 249-253. https://doi.org/https://doi.org/10.1016/S1474-6670(17)36395-4
Khalifa, Y., Mandic, D., & Sejdić, E. (2021). A review of Hidden Markov models and Recurrent Neural Networks for event detection and localization in biomedical signals. Information Fusion, 69, 52-72. https://doi.org/https://doi.org/10.1016/j.inffus.2020.11.008
Deng, M., Meng, T., Cao, J., Wang, S., Zhang, J., & Fan, H. (2020). Heart sound classification based on improved MFCC features and convolutional recurrent neural networks. Neural Networks, 130, 22-32. https://doi.org/https://doi.org/10.1016/j.neunet.2020.06.015
Kumar, R., & Srivastava, S. (2020). Externally Recurrent Neural Network based identification of dynamic systems using Lyapunov stability analysis. ISA Transactions, 98, 292-308. https://doi.org/https://doi.org/10.1016/j.isatra.2019.08.032
Ren, X., Gu, H., & Wei, W. (2021). Tree-RNN: Tree structural recurrent neural network for network traffic classification. Expert Systems with Applications, 167, 114363. https://doi.org/https://doi.org/10.1016/j.eswa.2020.114363
Elsken, T., Metzen, J. H., & Hutter, F. (2019). Neural architecture search: a survey. J. Mach. Learn. Res., 20(1), 1997–2017.
Ren, P., Xiao, Y., Chang, X., Huang, P.-y., Li, Z., Chen, X., & Wang, X. (2021). A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions. ACM Comput. Surv., 54(4), Article 76. https://doi.org/10.1145/3447582
Real, E., Aggarwal, A., Huang, Y., & Le, Q. V. (2019). Regularized evolution for image classifier architecture search Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, Honolulu, Hawaii, USA. https://doi.org/10.1609/aaai.v33i01.33014780
Liu, H., Simonyan, K., & Yang, Y. (2018). DARTS: Differentiable Architecture Search. ArXiv, abs/1806.09055.
Wistuba, M., Rawat, A., & Pedapati, T. (2019). A Survey on Neural Architecture Search. ArXiv, abs/1905.01392.
Yeoh, Y. J., Morie, T., & Tamukoh, H. (2021). An efficient hardware-oriented dropout algorithm. Neurocomputing, 427, 191-200. https://doi.org/https://doi.org/10.1016/j.neucom.2020.11.055
Wang, H., Yang, W., Zhao, Z., Luo, T., Wang, J., & Tang, Y. (2019). Rademacher dropout: An adaptive dropout for deep neural network via optimizing generalization gap. Neurocomputing, 357, 177-187. https://doi.org/https://doi.org/10.1016/j.neucom.2019.05.008
Chen, Y., & Yi, Z. (2021). Adaptive sparse dropout: Learning the certainty and uncertainty in deep neural networks. Neurocomputing, 450, 354-361. https://doi.org/https://doi.org/10.1016/j.neucom.2021.04.047
Mae, Y., Kumagai, W., & Kanamori, T. (2021). Uncertainty propagation for dropout-based Bayesian neural networks. Neural Networks, 144, 394-406. https://doi.org/https://doi.org/10.1016/j.neunet.2021.09.005
Jo, H. S., Koo, Y. D., Park, J. H., Oh, S. W., Kim, C.-H., & Na, M. G. (2021). Prediction of golden time for recovering SISs using deep fuzzy neural networks with rule-dropout. Nuclear Engineering and Technology, 53(12), 4014-4021. https://doi.org/https://doi.org/10.1016/j.net.2021.06.017
Das, G., Pattnaik, P. K., & Padhy, S. K. (2014). Artificial Neural Network trained by Particle Swarm Optimization for non-linear channel equalization. Expert Systems with Applications, 41(7), 3491-3496. https://doi.org/https://doi.org/10.1016/j.eswa.2013.10.053
Quarto, M., D'Urso, G., & Giardini, C. (2022). Micro-EDM optimization through particle swarm algorithm and artificial neural network. Precision Engineering, 73, 63-70. https://doi.org/https://doi.org/10.1016/j.precisioneng.2021.08.018
Moayedi, H., Mehrabi, M., Mosallanezhad, M., Rashid, A. S. A., & Pradhan, B. (2019). Modification of landslide susceptibility mapping using optimized PSO-ANN technique. Engineering with Computers, 35(3), 967-984. https://doi.org/10.1007/s00366-018-0644-0
Asadnia, M., Chua, L. H. C., Qin, X. S., & Talei, A. (2014). Improved Particle Swarm Optimization–Based Artificial Neural Network for Rainfall-Runoff Modeling. Journal of Hydrologic Engineering, 19(7), 1320-1329. https://doi.org/doi:10.1061/(ASCE)HE.1943-5584.0000927
Khajeh, M., & Dastafkan, K. (2014). Removal of molybdenum using silver nanoparticles from water samples: Particle swarm optimization–artificial neural network. Journal of Industrial and Engineering Chemistry, 20(5), 3014-3018. https://doi.org/https://doi.org/10.1016/j.jiec.2013.11.036
Chai, R., Ling, S. H., Hunter, G. P., Tran, Y., & Nguyen, H. T. (2014). Brain–Computer Interface Classifier for Wheelchair Commands Using Neural Network With Fuzzy Particle Swarm Optimization. IEEE Journal of Biomedical and Health Informatics, 18(5), 1614-1624. https://doi.org/10.1109/JBHI.2013.2295006
Bai, B., Zhang, J., Wu, X., wei Zhu, G., & Li, X. (2021). Reliability prediction-based improved dynamic weight particle swarm optimization and back propagation neural network in engineering systems. Expert Systems with Applications, 177, 114952. https://doi.org/https://doi.org/10.1016/j.eswa.2021.114952
Nasimi, R., & Irani, R. (2014). Identification and Modeling of a Yeast Fermentation Bioreactor Using Hybrid Particle Swarm Optimization-Artificial Neural Networks. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 36(14), 1604-1611. https://doi.org/10.1080/15567036.2011.592903
Kennedy, J., & Eberhart, R. C. (1997, 12-15 Oct. 1997). A discrete binary version of the particle swarm algorithm. 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation,
40. Sarath, K. N. V. D., & Ravi, V. (2013). Association rule mining using binary particle swarm optimization. Engineering Applications of Artificial Intelligence, 26(8), 1832-1840. https://doi.org/https://doi.org/10.1016/j.engappai.2013.06.003
Zhai, T., & He, Z. (2013). Instance selection for time series classification based on immune binary particle swarm optimization. Knowledge-Based Systems, 49, 106-115. https://doi.org/https://doi.org/10.1016/j.knosys.2013.04.021
Ravi Ganesh, M., Krishna, R., Manikantan, K., & Ramachandran, S. (2014). Entropy based Binary Particle Swarm Optimization and classification for ear detection. Engineering Applications of Artificial Intelligence, 27, 115-128. https://doi.org/https://doi.org/10.1016/j.engappai.2013.07.022
Xiong, B., Li, Y., Huang, M., Shi, W., Du, M., & Yang, Y. (2019). Feature Selection of Input Variables for Intelligence Joint Moment Prediction Based on Binary Particle Swarm Optimization. IEEE Access, 7, 182289-182295. https://doi.org/10.1109/ACCESS.2019.2959064
McDonnell, J. R., & Waagen, D. (1993, 28 March-1 April 1993). Evolving neural network connectivity. IEEE International Conference on Neural Networks,
Pujol, J. C. F., & Poli, R. (1998). Evolving the Topology and the Weights of Neural Networks Using a Dual Representation. Applied Intelligence, 8(1), 73-84. https://doi.org/10.1023/A:1008272615525
Yong, L., & Xin, Y. (2001, 27-30 May 2001). Evolving neural networks for Hang Seng stock index forecast. Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546),
Whitley, D., Starkweather, T., & Bogart, C. (1990). Genetic algorithms and neural networks: optimizing connections and connectivity. Parallel Computing, 14(3), 347-361. https://doi.org/https://doi.org/10.1016/0167-8191(90)90086-O
Grefenstette, J. J. (1986). Optimization of Control Parameters for Genetic Algorithms. IEEE Transactions on Systems, Man, and Cybernetics, 16(1), 122-128. https://doi.org/10.1109/TSMC.1986.289288
Lin, W.-Y., Lee, W.-Y., & Hong, T.-P. (2003). Adapting Crossover and Mutation Rates in Genetic Algorithms. J. Inf. Sci. Eng., 19, 889-903.
Hassanat, A., Almohammadi, K., Alkafaween, E. a., Abunawas, E., Hammouri, A. M., & Prasath, V. B. S. (2019). Choosing Mutation and Crossover Ratios for Genetic Algorithms - A Review with a New Dynamic Approach. Inf., 10, 390.
Sade, J. (2025). Predicting fetal health using ANFIS: A comparative study with machine learning models. Turkish Journal of Engineering, 10(1), 187-196. https://doi.org/10.31127/tuje.1711661
Bozkurt, F., Yucel Altay, S., & Yaganoglu, M. (2015). Yapay Sinir Ağları İle Ankara İlinde Hava Kalitesi Sağlık İndeksi Tahmini.
Kıran, M. S. (2014). Novel approaches based on artificial bee colony algorithm to solve optimization problems [Doctoral dissertation, Konya Technical University].
Kennedy, J., & Eberhart, R. (1995, 27 Nov.-1 Dec. 1995). Particle swarm optimization. Proceedings of ICNN'95 - International Conference on Neural Networks,
Lokman, G., & Iscan, S. (2026). Enhancing Optimal Power Flow Using Grey Wolf Intelligence-Integrated Particle Swarm Optimization. Turkish Journal of Engineering, 10(2), 661-675. https://doi.org/10.31127/tuje.1838822
Mojtaba Ahmadieh, K., Mohammad, T., & Mahdi Aliyari, S. (2007, 27-29 June 2007). A novel binary particle swarm optimization. 2007 Mediterranean Conference on Control & Automation,
Nguyen, B. H., Xue, B., Andreae, P., & Zhang, M. (2021). A New Binary Particle Swarm Optimization Approach: Momentum and Dynamic Balance Between Exploration and Exploitation. IEEE Transactions on Cybernetics, 51(2), 589-603. https://doi.org/10.1109/TCYB.2019.2944141
Mohammed, A. H., Prasad, M. A., & N.r, D. M. (2025). Application of Evolutionary Techniques to Minimize Torsion for Plan Irregular Re-entrant Corner Buildings. Turkish Journal of Engineering, 9(2), 272-280. https://doi.org/10.31127/tuje.1552068
Thengade, A., & Dondal, R. (2012). Genetic Algorithm – Survey Paper. IJCA Proc National Conference on Recent Trends in Computing, NCRTC, 5.
Shukla, A., Pandey, H. M., & Mehrotra, D. (2015, 25-27 Feb. 2015). Comparative review of selection techniques in genetic algorithm. 2015 International Conference on Futuristic Trends on Computational Analysis and Knowledge Management (ABLAZE),
Kruisselbrink, J. W., Li, R., Reehuis, E., Eggermont, J., & Bäck, T. (2011). On the log-normal self-adaptation of the mutation rate in binary search spaces Proceedings of the 13th annual conference on Genetic and evolutionary computation, Dublin, Ireland. https://doi.org/10.1145/2001576.2001699
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. J. Artif. Int. Res., 16(1), 321–357.
Soygazi, F., & Alp, G. (2025). Enhancing Crop Recommendation with SMOTE-Augmented Machine Learning Algorithms. Turkish Journal of Engineering, 9(4), 612-620. https://dergipark.org.tr/en/pub/tuje/article/1682299
Sinap, V. (2024). Comparative analysis of machine learning techniques for credit card fraud detection: Dealing with imbalanced datasets. Turkish Journal of Engineering, 8(2), 196-208. https://doi.org/10.31127/tuje.1386127

Details

Primary Language

English

Subjects

Computer Software, Software Quality, Processes and Metrics, Software Testing, Verification and Validation, Software Engineering (Other)

Journal Section

Research Article

Authors

Merve Yilmaz ^*
0000-0002-1551-7980
Türkiye

Mustafa Servet Kıran
0000-0002-5896-7180
Türkiye

Publication Date

October 16, 2026

Submission Date

June 3, 2026

Acceptance Date

July 20, 2026

Published in Issue

Year 2026 Volume: 10 Number: 4

DOI

https://doi.org/10.31127/tuje.1962552

IZ

https://izlik.org/JA26SR79TF

Cite

RIS / Bibtex

APA

Yilmaz, M., & Kıran, M. S. (2026). Connectivity optimization of artificial neural network with evolutionary computation algorithms. Turkish Journal of Engineering, 10(4), 1237-1250. https://doi.org/10.31127/tuje.1962552

AMA

1.Yilmaz M, Kıran MS. Connectivity optimization of artificial neural network with evolutionary computation algorithms. TUJE. 2026;10(4):1237-1250. doi:10.31127/tuje.1962552

Chicago

Yilmaz, Merve, and Mustafa Servet Kıran. 2026. “Connectivity Optimization of Artificial Neural Network With Evolutionary Computation Algorithms”. Turkish Journal of Engineering 10 (4): 1237-50. https://doi.org/10.31127/tuje.1962552.

EndNote

Yilmaz M, Kıran MS (October 1, 2026) Connectivity optimization of artificial neural network with evolutionary computation algorithms. Turkish Journal of Engineering 10 4 1237–1250.

IEEE

[1]M. Yilmaz and M. S. Kıran, “Connectivity optimization of artificial neural network with evolutionary computation algorithms”, TUJE, vol. 10, no. 4, pp. 1237–1250, Oct. 2026, doi: 10.31127/tuje.1962552.

ISNAD

Yilmaz, Merve - Kıran, Mustafa Servet. “Connectivity Optimization of Artificial Neural Network With Evolutionary Computation Algorithms”. Turkish Journal of Engineering 10/4 (October 1, 2026): 1237-1250. https://doi.org/10.31127/tuje.1962552.

JAMA

1.Yilmaz M, Kıran MS. Connectivity optimization of artificial neural network with evolutionary computation algorithms. TUJE. 2026;10:1237–1250.

MLA

Yilmaz, Merve, and Mustafa Servet Kıran. “Connectivity Optimization of Artificial Neural Network With Evolutionary Computation Algorithms”. Turkish Journal of Engineering, vol. 10, no. 4, Oct. 2026, pp. 1237-50, doi:10.31127/tuje.1962552.

Vancouver

1.Merve Yilmaz, Mustafa Servet Kıran. Connectivity optimization of artificial neural network with evolutionary computation algorithms. TUJE. 2026 Oct. 1;10(4):1237-50. doi:10.31127/tuje.1962552