Aquila Optimization-Assisted Artificial Neural Network for Classification Problems
Source abstract
Abstract
Artificial Neural Networks (ANNs) are models that learn patterns in input-output data. Since traditional optimization methods often get trapped in local optima when determining weight and bias values, identifying optimal parameters and enhancing network performance remain significant research areas. Heuristic algorithms are also generally used in solving optimization problems and are used to train ANNs. In the study, the parameter optimization of the ANN model was carried out using the Aquila Optimizer (AO), a recent metaheuristic algorithm, and a hybrid Aquila Optimizer optimized ANN model (AOANN) was proposed. Hybridization of algorithms contributes to the improvement of optimization performance. In this study, the proposed model was assessed on empirical datasets, including Cancer, Iris, Glass, and Wine, and its performance was compared with that of well-established ANN models. The results of the evaluation revealed that the proposed AOANN, a soft computation model, demonstrated stability in solving classification problems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Metaheuristic Optimization Algorithms Research · Machine Learning and Data Classification · Neural Networks and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, Ondokuz Mayis University, Kurupelit, Samsun 55139, Türkiye
References (52)
Show source-provided references
1. Mazlan, A.U., Sahabudin, N.A.B., Remli, M.A., Ismail, N.S.N., Mohamad, M.S., and Warif, N.B.A. (2021, January 26). Supervised and Unsupervised Machine Learning for Cancer Classification: Recent Development. Proceedings of the 2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS), Shah Alam, Malaysia.10.1109/I2CACIS52118.2021.9495888 ↗
2. An efficient artificial neural network for damage detection in bridges and beam-like structures by improving training parameters using cuckoo search algorithm10.1016/j.engstruct.2019.109637 ↗
3. Theories of Error Back-Propagation in the Brain10.1016/j.tics.2018.12.005 ↗
4. Artificial Neural Network training using metaheuristics for medical data classification: An experimental study10.1016/j.eswa.2021.116423 ↗
5. Back Propogation Algorithm: An Artificial Neural Network Approach
6. A survey on metaheuristic optimization for random single-hidden layer feedforward neural network10.1016/j.neucom.2018.07.080 ↗
7. Nature-inspired algorithms for feed-forward neural network classifiers: A survey of one decade of research10.1016/j.asej.2020.01.007 ↗
8. Novel Pareto-Based Meta-Heuristics for Solving Multi-Objective Multi-Item Capacitated Lot-Sizing Problems10.1007/s00170-015-6993-6 ↗
9. Aquila Optimizer: A novel meta-heuristic optimization algorithm10.1016/j.cie.2021.107250 ↗
10. Modern meta-heuristics based on nonlinear physics processes: A review of models and design procedures10.1016/j.physrep.2016.08.001 ↗
11. Equilibrium optimizer: A novel optimization algorithm10.1016/j.knosys.2019.105190 ↗
12. Abualigah, L., Diabat, A., and Geem, Z.W. (2020). A Comprehensive Survey of the Harmony Search Algorithm in Clustering Applications. Appl. Sci., 10.10.3390/app10113827 ↗
13. Varshney, M., Kumar, P., Ali, M., and Gulzar, Y. (2024). Using the Grey Wolf Aquila Synergistic Algorithm for Design Problems in Structural Engineering. Biomimetics, 9.10.3390/biomimetics9010054 ↗
14. Kan, H., Xiao, Y., Gao, Z., and Zhang, X. (2025). Improved Multi-Strategy Aquila Optimizer for Engineering Optimization Problems. Biomimetics, 10.10.3390/biomimetics10090620 ↗
15. Gudise, V., and Venayagamoorthy, G. (2003, January 24–26). Comparison of particle swarm optimization and backpropagation as training algorithms for neural networks. Proceedings of the 2003 IEEE Swarm Intelligence Symposium, SIS’03 (Cat. No.03EX706), Indianapolis, IN, USA.
16. Blum, C., and Socha, K. (2005, January 6–9). Training feed-forward neural networks with ant colony optimization: An application to pattern classification. Proceedings of the Fifth International Conference on Hybrid Intelligent Systems, HIS 2005, Rio de Janeiro, Brazil.10.1109/ICHIS.2005.104 ↗
17. Karaboga, D., and Akay, B. (2007, January 11–13). Artificial Bee Colony (ABC) Algorithm on Training Artificial Neural Networks. Proceedings of the 2007 IEEE 15th Signal Processing and Communications Applications, Eskisehir, Turkey.10.1109/SIU.2007.4298679 ↗
18. A tabu search algorithm for the training of neural networks10.1057/palgrave.jors.2602535 ↗
19. Kattan, A., Abdullah, R., and Abdul Salam, R. (2010, January 27–29). Harmony Search Based Supervised Training of Artificial Neural Networks. Proceedings of the 2010 International Conference on Intelligent Systems, Modelling and Simulation, Liverpool, UK.10.1109/ISMS.2010.31 ↗
20. A Neurogenetic approach for the resource-constrained project scheduling problem10.1016/j.cor.2010.01.007 ↗
21. Artificial neural network, ANN-PSO and ANN-ICA for modelling the Stirling engine10.1080/01430750.2014.986289 ↗
22. Optimizing connection weights in neural networks using the whale optimization algorithm10.1007/s00500-016-2442-1 ↗
23. Apak, G. (2018). Çoklu Depolu araç Rotalama Probleminin Hibrid Algoritmalar Yöntemiyle çözülmesi/Solving Multi-Depot Vehicle Routing Problems via Hybrid Algorithms. [Master’s Thesis, Çukurova University, Institute of Social Sciences, Department of Management].
24. Training of the feed-forward artificial neural networks using butterfly optimization algorithm10.51354/mjen.917837 ↗
25. Improved ANN technique combined with Jaya algorithm for crack identification in plates using XIGA and experimental analysis10.1016/j.tafmec.2020.102554 ↗
26. Efficient Artificial neural networks based on a hybrid metaheuristic optimization algorithm for damage detection in laminated composite structures10.1016/j.compstruct.2020.113339 ↗
27. Hybrid meta-heuristic algorithm based deep neural network for face recognition10.1016/j.jocs.2021.101352 ↗
28. Training of Artificial Neural Network Using Metaheuristic Algorithm10.18201/ijisae.2017SpecialIssue31417 ↗
29. AlRassas, A.M., Al-qaness, M.A., Ewees, A.A., Ren, S., Abd Elaziz, M., Damaševičius, R., and Krilavičius, T. (2021). Optimized ANFIS model using Aquila Optimizer for oil production forecasting. Processes, 9.10.3390/pr9071194 ↗
30. Deep recurrent neural network-based Aquila optimization-based online shaming emotion analysis10.1002/cpe.6882 ↗
31. COOT optimization algorithm on training artificial neural networks10.1007/s10115-023-01859-w ↗
32. Hurtado-Mora, H.A., Herrera-Barajas, L.A., González-del Ángel, L.J., Pichardo-Ramírez, R., García-Ruiz, A.H., and Lira-García, K.E. (2025). Enhancing Neural Network Training Through Neuroevolutionary Models: A Hybrid Approach to Classification Optimization. Mathematics, 13.10.3390/math13071114 ↗
33. Kumar, M., Mohd, N., Shivam, G., Goyal, A., Parashar, D., and Khan, R. (2026). Hybrid Aquila optimizer–Harris Hawks optimization for CNN hyperparameter tuning in brain tumor classification. Sci. Rep.10.1038/s41598-026-43329-7 ↗
34. Blake, C., and Merz, C. (1998). UCI Repository of ML Databases, University of California.
35. Artificial neural networks for neuroscientists: A primer10.1016/j.neuron.2020.09.005 ↗
36. Mishra, S., Prusty, R., and Hota, P.K. (2015, January 17–19). Analysis of Levenberg-Marquardt and Scaled Conjugate gradient training algorithms for artificial neural network based LS and MMSE estimated channel equalizers. Proceedings of the 2015 International Conference on Man and Machine Interfacing (MAMI), Bhubaneswar, India.10.1109/MAMI.2015.7456617 ↗
37. Neural network architectures and learning algorithms10.1109/MIE.2009.934790 ↗
38. A scaled conjugate gradient algorithm for fast supervised learning10.1016/S0893-6080(05)80056-5 ↗
39. Sivasankari, K., Thanushkodi, K., and Kalaivanan, K. (2013, January 3). Automated seizure detection using multilayer feed forward network trained using scaled conjugate gradient method. Proceedings of the 2013 International Conference on Current Trends in Engineering and Technology (ICCTET), Coimbatore, India.10.1109/ICCTET.2013.6675944 ↗
40. Scaled conjugate gradient backpropagation algorithm for selection of industrial robots
41. Waheeb, W., Ghazali, R., and Deris, M.M. (2015, January 15–17). Content-based SMS spam filtering based on the scaled conjugate gradient backpropagation algorithm. Proceedings of the 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), Zhangjiajie, China.10.1109/FSKD.2015.7382023 ↗
42. Babani, L., Jadhav, S., and Chaudhari, B. (2016, January 16–18). Scaled conjugate gradient based adaptive ANN control for SVM-DTC induction motor drive. Proceedings of the 2th IFIP WG 12.5 International Conference and Workshops, AIAI 2016, Thessaloniki, Greece.
43. Wang, S., Jia, H., Abualigah, L., Liu, Q., and Zheng, R. (2021). An improved hybrid aquila optimizer and harris hawks algorithm for solving industrial engineering optimization problems. Processes, 9.10.3390/pr9091551 ↗
44. Network Intrusion Detection: An Analytical Assessment Using Deep Learning and State-of-the-Art Machine Learning Models10.1007/s44196-021-00047-4 ↗
45. Boosting Advanced Nasopharyngeal Carcinoma Stage Prediction Using a Two-Stage Classification Framework Based on Deep Learning10.1007/s44196-021-00026-9 ↗
46. Daily Activity Recognition and Tremor Quantification from Accelerometer Data for Patients with Essential Tremor Using Stacked Denoising Autoencoders10.1007/s44196-021-00052-7 ↗
47. Data mining approach to analyzing intrusion detection of wireless sensor network
48. A New Item-Based Collaborative Filtering Algorithm to Improve the Accuracy of Prediction in Sparse Data10.1007/s44196-022-00068-7 ↗
49. Prediction of Ship Heave Motion Using Regularized BP Neural Network with Cross Entropy Error Function10.1007/s44196-021-00043-8 ↗
50. An Intelligent Question Answering System of the Liao Dynasty Based on Knowledge Graph10.1007/s44196-021-00010-3 ↗
51. An introduction to ROC analysis10.1016/j.patrec.2005.10.010 ↗
52. Assessing landslide susceptibility using machine learning models: A comparison between ANN, ANFIS, and ANFIS-ICA10.1007/s12665-020-09294-8 ↗