Modeling for System Optimization with Small Dataset Using Neural Network

Document Type: Research Paper


Department of Image Processing and Data Mining Lab, Shahrood University of Technology, Semnan, Iran


The shortage of data is one of the most important problems in system modeling and optimization in industrial applications. Typical modeling techniques are unable to properly model a system with a limited dataset. In this paper, a modeling method for optimization of these systems is proposed. The proposed method has two main steps. In the first step, the model is employed to generate data using neural network. This model determines the correspondence input of each output. In the second step, optimization of the generated model is performed using genetic algorithm. Inputs leading to the specified output can be estimated using the proposed system. Optimality of the system can be explained by an evaluation function. The proposed method was evaluated in two different experiments on a time series and a real data. Results of the experiments were analyzed using mean square error. The experimental results show the capability of the proposed method in system modeling and optimization.


Main Subjects

1.         K. A. Ugwa and Agwu, A. (2012)."Mathematical Modeling As A Tool For Sustainable Development In Nigeria" , International Journal of Academic Research in Progressive Education and Development, vol. 1, No. 2, pp. 251-258.

[2]       P. D. Cha., Dym C. L., and J. J. Rosenberg, (2000)."Fundamentals of modeling and analysing engineering systems," ed,

[3]       T. Berger, R. et al., (2013). "A survey of variability modeling in industrial practice", in Proceedings of the Seventh International Workshop on Variability Modelling of Software-intensive Systems, 2013.

[4]       D.-C. Li and C.-W. Liu, "A neural network weight determination model designed uniquely for small data set learning," Expert Systems with Applications, vol. 36, pp. 9853-9858, 2009.

[5]       S. Ingrassia and I. Morlini, "Neural network modeling for small datasets," Technometrics, vol. 47, pp. 297-311, 2005.

[6]       A. Gosavi, 2015"Simulation-Based Optimization: An Overview", in Simulation-Based Optimization. vol. 55, ed: Springer US, , pp. 29-35.

[7]       R. H. Myers, D. C. Montgomery, and C. M. Anderson-Cook, Response surface methodology: process and product optimization using designed experiments vol. 705: John Wiley & Sons, 2009.

[8]       K. Hornik, M. Stinchcombe, and H. White, "Multilayer feedforward networks are universal approximators," Neural Networks, vol. 2, pp. 359-366, 1989.

[9]       A. Gosavi, "Parametric Optimization: Response Surfaces and Neural Networks," in Simulation-Based Optimization. vol. 55, ed: Springer US, 2015, pp. 37-69.

[10]     Gholipoor, M. et al., (2012)."The optimization of root nutrient content for increased sugar beet productivity using an artificial neural network", International Journal of Plant Production, Vol. 6, No. 4, pp. 429-442.

[11]     Khazaii, J. (2016). "Genetic Algorithm Optimization", in Advanced Decision Making for HVAC Engineers, ed: Springer, pp. 87-97.

[12]     Ali M. Z., et al., (2017). "An improved رده of Real-Coded Genetic Algorithms for Numerical Optimization", Neurocomputing,

[13]     Bakirtzis A., and Kazarlis, S. (2016). "Genetic algorithms," Advanced Solutions in Power Systems: HVDC, FACTS, and Artificial Intelligence: HVDC, FACTS, and Artificial Intelligence, pp. 845-902.

[14]     J. Tang, C. Deng, and G.-B. Huang, (2016). "Extreme learning machine for multilayer perceptron", IEEE transactions on neural networks and learning systems, vol. 27, No. 4, pp. 809-821.

[15]     Abo-Hammour, Z. e., et al., (2013)."A Genetic Algorithm Approach for Prediction of Linear Dynamical Systems", Mathematical Problems in Engineering, Vol. 2013, p. 12.

[16]     A. L. E. Will, (2016). "Improvement of a Hybrid Evolutionary Model of Genetic Algorithms and Artificial Neural Networks", Boletín Técnico, ISSN: 0376-723X, Vol. 54,

[17]     I. Cruz-Vega, C. A. R. et al., (2016). "Genetic algorithms based on a granular surrogate model and fuzzy aptitude functions", in Evolutionary Computation (CEC), IEEE Congress on, pp. 2122-2128.

[18]     Grégoire, G. (2014)."Multiple linear regression", European Astronomical Society Publications Series, Vol. 66, pp, NO 45-72, 2014.