Abstract
As one of the most popular artificial neural networks, multi-layer perceptron (MLP) has been employed to solve classification problems in many applications. The main challenge in MLP application is finding the ideal set of network connection weights and biases in the training process, which minimizes the error of MLP in processing datasets. To efficiently address this challenge, numerous swarm intelligence (SI) algorithms with powerful search capabilities have been adopted for training MLP classifiers. However, these existing algorithms often suffer from problems of local optima stagnation, premature convergence, and inefficient search. In this study, a novel floating flame moth-flame optimization (FMFO) algorithm with remarkable exploitation and exploration search capabilities is proposed, offering an advantageous option for training MLP classifiers. To verify the performance of the proposed FMFO in training MLP classifiers, the FMFO-based MLP training approach (FMFO-MLP) is evaluated on eleven classification datasets that represent a wide range of the variable dimension scale. In addition, some recently developed well-known and state-of-the-art SI algorithms are applied to compare with the proposed FMFO. Experimental results demonstrate that the proposed FMFO outperforms the other competing algorithms in terms of approximating the optimal objective function value and achieving classification accuracy. Moreover, the proposed FMFO achieves a competitive computational efficiency in the experiment, confirming that it is an efficient optimizer for training MLP classifiers in practical applications.
Similar content being viewed by others
References
Agrawal U, Arora J, Singh R, Gupta D, Khanna A, Khamparia A (2020) Hybrid wolf-bat algorithm for optimization of connection weights in multi-layer perceptron. ACM Trans Multimed Comput Commun Appl (TOMM) 16(1s):1–20
Mirjalili S, Mirjalili SM, Lewis A (2014) Let a biogeography-based optimizer train your multi-layer perceptron. Inf Sci 269:188–209
Zhang J-R, Zhang Jun, Lok T-M, Lyu MR (2007) A hybrid particle swarm optimization–back-propagation algorithm for feedforward neural network training. Appl Math Comput 185(2):1026–1037
Yang J, Hu Y, Zhang K, Wu Y (2021) An improved evolution algorithm using population competition genetic algorithm and self-correction bp neural network based on fitness landscape. Soft Comput 25 (3):1751–1776
Xu Y, Chen H, Luo J, Zhang Q, Jiao S, Zhang X (2019) Enhanced moth-flame optimizer with mutation strategy for global optimization. Inf Sci 492:181–203
Pelusi D, Mascella R, Tallini L, Nayak J, Naik B, Deng Y (2020) An improved moth-flame optimization algorithm with hybrid search phase. Knowl-Based Syst 191:105277
Ghorbani MA, Kazempour R, Chau K-W, Shamshirband S, Ghazvinei PT (2018) Forecasting pan evaporation with an integrated artificial neural network quantum-behaved particle swarm optimization model: a case study in talesh, northern iran. Eng Appl Comput Fluid Mech 12(1):724–737
Mirjalili S (2015) How effective is the grey wolf optimizer in training multi-layer perceptrons. Appl Intell 43(1):150–161
Gupta S, Deep K, Mirjalili S, Kim JH (2020) A modified sine cosine algorithm with novel transition parameter and mutation operator for global optimization. Expert Syst Appl 154:113395
Mousavirad SJ, Schaefer G, Korovin I, Oliva D (2021) Rde-op: A region-based differential evolution algorithm incorporation opposition-based learning for optimising the learning process of multi-layer neural networks. In: International Conference on the Applications of Evolutionary Computation (Part of EvoStar). Springer, pp 407–420
Mirjalili S (2015) Moth-flame optimization algorithm: A novel nature-inspired heuristic paradigm. Knowl-Based Syst 89:228–249
Shehab M, Abualigah L, Hamad HA, Alabool H, Alshinwan M, Khasawneh AM (2020) Moth–flame optimization algorithm: variants and applications. Neural Comput Appl 32(14):9859–9884
Ma L, Wang C, Xie N-g, Shi M, Ye Y, Lu W (2021) Moth-flame optimization algorithm based on diversity and mutation strategy. Appl Intell 51(8):5836–5872
Lin G-Q, Li L-L, Tseng M-L, Liu H-M, Yuan D-D, Tan RR (2020) An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation. J Clean Prod 119966:253
Hongwei L, Jianyong L, Liang C, Jingbo B, Yangyang S, Kai L (2019) Chaos-enhanced moth-flame optimization algorithm for global optimization. J Syst Eng Electron 30(6):1144–1159
Anfal M, Abdelhafid H (2017) Optimal placement of pmus in algerian network using a hybrid particle swarm–moth flame optimizer (pso-mfo). Electroteh Electron Autom 65(3):191– 196
Elaziz MA, Ewees AA, Ibrahim RA, Lu S (2020) Opposition-based moth-flame optimization improved by differential evolution for feature selection. Math Comput Simul 168:48–75
Elaziz MA, Yousri D, Mirjalili S (2021) A hybrid harris hawks-moth-flame optimization algorithm including fractional-order chaos maps and evolutionary population dynamics. Adv Eng Softw 154:102973
Sayed GI, Hassanien AE (2018) A hybrid sa-mfo algorithm for function optimization and engineering design problems. Compl Intell Syst 4(3):195–212
Xu Y, Chen H, Heidari AA, Luo J, Zhang Q, Zhao X, Li C (2019) An efficient chaotic mutative moth-flame-inspired optimizer for global optimization tasks. Expert Syst Appl 129:135–155
Khalilpourazari S, Khalilpourazary S (2019) An efficient hybrid algorithm based on water cycle and moth-flame optimization algorithms for solving numerical and constrained engineering optimization problems. Soft Comput 23(5):1699–1722
Yu X, Wang Y, Liang J, Slowik A (2021) A self-adaptive mutation neural architecture search algorithm based on blocks. IEEE Comput Intell Mag 16(3):67–78
O’Neill D, Xue B, Zhang M (2021) Evolutionary neural architecture search for high-dimensional skip-connection structures on densenet style networks. IEEE Transactions on Evolutionary Computation
Yu X, Tang T, Liu AX (2019) Large-scale feedforward neural network optimization by a self-adaptive strategy and parameter based particle swarm optimization. IEEE Access 7:52473–52483
Heidari AA, Faris H, Aljarah I, Mirjalili S (2019) An efficient hybrid multilayer perceptron neural network with grasshopper optimization. Soft Comput 23(17):7941–7958
Mohammadi B, Guan Y, Moazenzadeh R, Safari MJS (2021) Implementation of hybrid particle swarm optimization-differential evolution algorithms coupled with multi-layer perceptron for suspended sediment load estimation. Catena 198:105024
Yamany W, Fawzy M, Tharwat A, Hassanien AE (2015) Moth-flame optimization for training multi-layer perceptrons. In: 2015 11th International computer engineering Conference (ICENCO). IEEE, pp 267–272
Gupta S, Deep K (2020) A novel hybrid sine cosine algorithm for global optimization and its application to train multilayer perceptrons. Appl Intell 50(4):993–1026
Zhao R, Wang Y, Hu P, Jelodar H, Yuan C, Li Y, Masood I, Rabbani M (2019) Selfish herds optimization algorithm with orthogonal design and information update for training multi-layer perceptron neural network. Appl Intell 49(6):2339–2381
Ghanem WAHM, Jantan A (2018) A cognitively inspired hybridization of artificial bee colony and dragonfly algorithms for training multi-layer perceptrons. Cogn Comput 10(6):1096–1134
Bansal P, Kumar S, Pasrija S, Singh S (2020) A hybrid grasshopper and new cat swarm optimization algorithm for feature selection and optimization of multi-layer perceptron. Soft Comput 24(20):15463–15489
Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of ICNN’95-international conference on neural networks, vol 4. IEEE, pp 1942–1948
Clerc M, Kennedy J (2002) The particle swarm-explosion, stability, and convergence in a multidimensional complex space. IEEE Trans Evol Comput 6(1):58–73
Yang Z, Shi K, Wu A, Qiu M, Hu Y (2019) A hybird method based on particle swarm optimization and moth-flame optimization. In: Proceedings of the 2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), vol 2. IEEE, pp 207–210
Li C, Zhang N, Lai X, Zhou J, Xu Y (2017) Design of a fractional-order pid controller for a pumped storage unit using a gravitational search algorithm based on the cauchy and gaussian mutation. Inf Sci 396:162–181
Mirjalili S, Lewis A (2016) The whale optimization algorithm. Adv Eng Softw 95:51–67
Storn R, Price K (1997) Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces. J Glob Optim 11(4):341–359
Saremi S, Mirjalili S, Lewis A (2017) Grasshopper optimisation algorithm: theory and application. Adv Eng Softw 105:30–47
David A, Patrick M, Christopher M, Eamonn K, Cathy B, Seth H, David N (2021) Uci machine learning repository. Website. http://archive.ics.uci.edu/ml/index.php
Wilcoxon F (1945) Individual comparisons by ranking methods. biometrics bulletin. Int Biometr Soc 1(6):80–83
Friedman M (1940) A comparison of alternative tests of significance for the problem of m rankings. Ann Math Stat 11(1):86–92
Yang Z, Wu A (2020) A non-revisiting quantum-behaved particle swarm optimization based multilevel thresholding for image segmentation. Neural Comput Appl 32(16):12011–12031
Acknowledgements
This study was funded by the Guangzhou Municipal Science and Technology Bureau of China (Research Grant no. 202002030133), the Guangzhou Municipal Education Bureau of China (Research Grant no. 201831785), the Department of Education of Guangdong Province of China (Research Grant no. 2019GKTSCX069), and the Guangzhou Panyu Polytechnic (Research Grant no. 2011Y05PY).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yang, Z. FMFO: Floating flame moth-flame optimization algorithm for training multi-layer perceptron classifier. Appl Intell 53, 251–271 (2023). https://doi.org/10.1007/s10489-022-03484-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03484-6