Neural network system for selection of table tennis equipment
Abstract
The article examines the optimization of search processes and the relevance of the use of artificial neural networks for the selection of table tennis equipment. With the help of neural networks, it is possible to solve any task. The problem is only to make the right choice of architecture and structure of the neural network, the algorithm of its operation and to formalize the source data, the result and the corresponding transformation. The problem of clustering the table tennis equipment market is considered. The result of the research has become the creation of information-analytical system "Neuro TT" for the analysis of the table tennis equipment market and the possibility of selecting the optimal combination of rubbers and blade. The structure of such a neural network system has been developed. It consists of three information banks, which contain information about the properties of rubbers and blades, as well as known combinations of rubbers and blades. The use of such a system will allow to forecast the development trends of the table tennis equipment market, manufacturers to plan and change the structure of production, buyers (players) and sellers to fully meet the information needs
Keywords
neural network; optimization process; clustering; neural network system; algorithm
References
[1] V. A. Tazetdinov, "Automation of the process of selection of equipment for table tennis using neural network systems", Komputerno-intergrovani tekhnologii: osvita, nauka, vyrobnyztvo: sci. journ., no 32, pp. 81-84, 2018 [in Ukrainian].
[2] V. A. Tazetdinov, "Optimization of the process of selection of equipment for table tennis based on the construction of neural networks by the criteria of conformity", Naukovi Notatky: int. coll., no 63, pp. 209213, 2018 [in Ukrainian].
[3] А. N. Gorban, Neural network training. Moscow, Russia: ParaGraf, 1990 [in Russian].
[4] V. I. Landyk, Sports training methodology: table tennis. Donetsk, Ukraine: NordPress, 2005 [in Russian].
[5] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors", Nature (London), no. 323, pp. 533-536, 1986.
[6] B. Bundy, Optimization methods. Moscow, Russia: Radio i svyaz, 1988 [in Russian].
[7] M. Kiselev, and E. Solomatin, "Means of knowledge extraction in business and finance", Otkritiye Sistemi, no. 4, pp. 41-44, 1997 [in Russian].
[8] M. Shapot, "Data mining in decision support systems", Otkritiye Sistemi, no 1, pp. 30-35, 1998 [in Russian].
[9] M. M. Hlybovets, and O. V. Oletsky, Artificial intelligence. Kyiv, Ukraine: Academiya, 2002 [in Ukrainian].
[10] Rubber Reviews. [Online]. Available: https://revspin.net/rubber/. Accessed on: Jan. 28, 2021.
[11] Blade Reviews. [Online]. Available: https://revspin.net/blade/. Accessed on: Jan. 28, 2021.
[12] The database of table tennis blades compositions. [Online]. Available: https://stervinou.net/ttbdb/index.php/. Accessed on: Jan. 28, 2021.
[13] D. Dubois, and A. Prad, Theory of possibilities. Moscow, Russia: Radio i svyaz, 1990 [in Russian].
[14] A. A. Yezhov, and S. A. Shumsky, Neurocomputing and its applications in economics and business. Moscow, Russia: MIFI, 1998 [in Russian].
[15] O. P. Kutakh, "Research of dynamic situations and determination of their characteristics at different stages of the decision-making process", Systemni doslidzhennya ta informatsiyni tekhnolohiyi, no. 4, pp. 60-72, 2003 [in Ukrainian].