Training of the Artificial Neural Networks using States of Matter Search Algorithm

Keywords: Artificial neural networks, training of artificial neural networks, states of matter search algorithm, optimization, feed-forward artificial neural networks

Abstract

In recent years, technology has been developing very rapidly in the field of artificial intelligence. In this development, Artificial neural networks (ANNs) have taken a huge place. The human brain has an excellent understanding structure. The brain makes this understanding through neuron cells. ANN aims to solve some complex problems by establishing the perception structure of human over neurons in the computer environment. ANN has the ability to learn using inputs and expected outputs. In order to do this, weight values in ANN are constantly updated according to the inputs and expected outputs. Thus, weight values are tried to be kept at an optimum level. Therefore, this problem is an optimization problem. In this study, the State of Matter Search meta-heuristic algorithm was used to optimize the weight values in ANN, called SMS-MLP. In the experiments, 5 classification datasets (xor, balloon, iris, breast cancer, heart) were used. The SMS-MLP algorithm was compared with the previous 6 algorithms in the literature. The experimental study shows that the SMS-MLP algorithm is more efficient than the other 6 algorithms.

Downloads

Download data is not yet available.

References

K. Öztürk, M.E. Şahin, Yapay Sinir Ağları ve Yapay Zekâ’ya Genel Bir Bakış, Takvim-i Vekayi, 6 25-36.

E. Madenci, Ş. Gülcü, Optimization of flexure stiffness of FGM beams via artificial neural networks by mixed FEM, Structural Engineering and Mechanics, 75 (2020) 633-642.

E. Kaya, A. Yasar, I. Saritas, Banknote classification using artificial neural network approach, International Journal of Intelligent Systems and Applications in Engineering, 4 (2016) 16-19.

A. Tümer, S. Edebali, Ş. Gülcü, Modeling of Removal of Chromium (VI) from Aqueous Solutions Using Artificial Neural Network, Iranian Journal of Chemistry and Chemical Engineering (IJCCE), 39 (2020) 163-175.

O. İnan, A.E. Tümer, S. Koçer, Ş. Gülcü, Diagnosis of lung cancer disease using artificial neural networks, in: 4th International conference on computational and experimental science and engineering (iccesen-2017), Antalya, Turkey, 2017.

D.-K. Bui, T.N. Nguyen, T.D. Ngo, H. Nguyen-Xuan, An artificial neural network (ANN) expert system enhanced with the electromagnetism-based firefly algorithm (EFA) for predicting the energy consumption in buildings, Energy, 190 (2020) 116370.

M. Kim, S. Jung, J.-w. Kang, Artificial Neural Network-Based Residential Energy Consumption Prediction Models Considering Residential Building Information and User Features in South Korea, Sustainability, 12 (2020) 109.

N.S. Jaddi, S. Abdullah, A.R. Hamdan, Optimization of neural network model using modified bat-inspired algorithm, Applied Soft Computing, 37 (2015) 71-86.

A. Askarzadeh, A. Rezazadeh, Artificial neural network training using a new efficient optimization algorithm, Applied Soft Computing, 13 (2013) 1206-1213.

A. Askarzadeh, Bird mating optimizer: an optimization algorithm inspired by bird mating strategies, Communications in Nonlinear Science and Numerical Simulation, 19 (2014) 1213-1228.

F. Erdoğan, Ş. Gülcü, Training of Artificial Neural Networks using Meta Heuristic Algorithms, in: The International Aluminium-Themed Engineering and Natural Sciences Conference (IATENS19), Konya, Turkey, 2019, pp. 124-128.

N.S. Jaddi, S. Abdullah, Optimization of neural network using kidney-inspired algorithm with control of filtration rate and chaotic map for real-world rainfall forecasting, Engineering Applications of Artificial Intelligence, 67 (2018) 246-259.

A.P. Piotrowski, M. Osuch, M.J. Napiorkowski, P.M. Rowinski, J.J. Napiorkowski, Comparing large number of metaheuristics for artificial neural networks training to predict water temperature in a natural river, Computers & Geosciences, 64 (2014) 136-151.

S. Mirjalili, How effective is the Grey Wolf optimizer in training multi-layer perceptrons, Applied Intelligence, 43 (2015) 150-161.

E. Cuevas, A. Echavarría, M.A. Ramírez-Ortegón, An optimization algorithm inspired by the States of Matter that improves the balance between exploration and exploitation, Applied intelligence, 40 (2014) 256-272.

O. Kaynar, S. Taştan, Zaman serisi analizinde mlp yapay sinir ağları ve arıma modelinin karşılaştırılması, Erciyes Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, (2009) 161-172.

A. Küçükyağlıoğlu, Ş. Gülcü, Training of Artificial Neural Network using Moth-Flame Optimization Algorithm, in: The International Aluminium-Themed Engineering and Natural Sciences Conference (IATENS19), Konya, Turkey, 2019, pp. 129-134.

M.F. Keskenler, E.F. Keskenler, Geçmişten günümüze yapay sinir ağları ve tarihçesi, Takvim-i Vekayi, 5 (2017) 8-18.

M.G. Ceruti, S.H. Rubin, Infodynamics: Analogical analysis of states of matter and information, Information Sciences, 177 (2007) 969-987.

D. Chowdhury, D. Stauffer, Principles of equilibrium statistical mechanics, Principles of Equilibrium Statistical Mechanics, by Debashish Chowdhury, Dietrich Stauffer, pp. 564. ISBN 3-527-40300-0. Wiley-VCH, September 2000., (2000) 564.

D.S. Betts, R.E. Turner, Introductory statistical mechanics, Addison-Wesley, 1992.

Y. Cengel, M. Boles, An Engineering Approach Thermodynamics, McGrow Hill, (2005).

D.L. García, À. Nebot, A. Vellido, Intelligent data analysis approaches to churn as a business problem: a survey, Knowledge and Information Systems, 51 (2017) 719-774.

T. Rong, H. Gong, W.W. Ng, Stochastic sensitivity oversampling technique for imbalanced data, International conference on machine learning and cybernetics, Springer, 2014, pp. 161-171.

Published
2020-09-28
How to Cite
[1]
Şaban Gulcu, “Training of the Artificial Neural Networks using States of Matter Search Algorithm”, IJISAE, vol. 8, no. 3, pp. 131-136, Sep. 2020.
Section
Research Article