NEW METHODS OF SOFT COMPUTING IN REGIONAL DEVELOPMENT STRATEGY FORMATION

Yaroslav Vyklyuk, Valeriy Yevdokymenko

Abstract


An urgent necessity in socio-economic regional development strategy specification is being substantiated for the purpose of reconstructing and adjusting the TEA (Types of Economic Activity) structure, which is able to speed up the development of GRP (Gross Regional Product), GS (Gross Surplus) per person and steadily grade current interregional differentiation and asymmetry. To reach the target a special algorithm for Soft Computing has been created. On the example of the selected region it was proved that the present economic system is not self-organized and it requires an efficient public management. If the regional management strategy is not optimally chosen then in the system some uncontrolled fluctuations can be observed, that may lead to an economic crisis and the "collapse" of the economy system. Mathematical models of optimization of strategies building of 3 types have been constructed and their effectiveness has been quantitatively researched. It is proved, that the dynamic management strategy with the maximizing of the objective function at the end of the period under investigation, turned out to be the most effective. It is established that public administration which is based on a scientifically grounded quantitative approach, using advanced mathematical models of Soft Computing, allows building a strong economic foundation, which will be the basis for a further rapid growth of the regional economy.

Keywords


soft computing, economic modeling, neural networks, regional development strategy

Full Text:

PDF

References


Akbari, R., & Ziarati, K. (17 05 2011 г.). Multi Level Evolutionary Algorithm for Optimizing Numerical Functions, IJIEC, 2, . International Journal of Industrial Engineering Computations, 419-430. doi:10.5267/j.ijiec.2010.03.002

Atencia, M., Joya, G., & Sandoval, F. (04 2005 г.). Hopfield Neural Networks for Parametric Identification of Dynamical Systems. Neural Processing Letters, 21(2), 143-152. doi:10.1007/s11063-004-3424-3

Cohen, M., & Grossberg, S. (1983). Absolute Stability of Global Pattern Formation and Parallel Memory Storage by Compatitive Neural Networks. IEEE Transactionson Systems, Manand Cybernetics, 13:8, , 815-826.

Hopfield J.J. (1982). Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proceedings of the National Academy of Sciences of the USA, 79(8), 2554-2558.

Katsikatsou, M., Moustaki, I., Yang-Wallentin, F., & Joreskog, K. (12 2012 г.). Pairwise Likelihood Estimation for factor analysis models with ordinal data. Computational Statistics and Data Analysis, 56(12), 4243-4258.

Maksimov, Y. A., & Filippovskaya, Y. A. (1982). Algoritmy resheniya zadach nelineynogo programmirovaniya. Moskva: MIFI.

Moore, J., & Weatherford, L. (2001). Decision Modeling with Microsoft Excel. New Jersey: Prentice Hall.

Zhang, J., Chung, H.-H., & Lo, W.-L. (2007). Clustering-Based Adaptive Crossover and Mutation Probabilities for Genetic Algorithms. IEEE Transactions on Evolutionary Computation, 11(3), 326-335. doi:10.1109/TEVC.2006.880727


Refbacks

  • There are currently no refbacks.