TABULAR ARTIFICIAL NEURAL NETWORK IMPLEMENTATION OF RADIAL BASIS FUNCTIONS FOR THE SAMPLES CLASSIFICATION
Abstract
The development and study of a new constructive algorithm for constructing models for sample classification using an artificial neural network with radial basis functions in a Microsoft Excel spreadsheet environment without VBA programming is presented in the subsequent work. The algorithm presented can be considered the most effective method for solving classification problems using artificial neural networks, since a model constructed in this manner is easily expanded and modified, which facilitates its application to solve many similar problems. Creating table models using this algorithm significantly expands the functionality of spreadsheets as a simple and efficient data modeling and visualization tool. The developed table model of an artificial neural network with radial basic functions and the general recommendations about her expansion, modification and application are provided in problems of classification. Results of classification by RBF network of unknown samples based on set educational a vector samples are shown. The tabular model, which is presented in the article, has multiple advantages including its exceptional visibility, which can be effectively used in the educational process for the purpose of studying algorithmic features of neural network operations. Table modeling technology developed for classification algorithms is highly useful for educational purposes, as it provides students with unlimited access to data structures and the algorithms necessary for their processing. Further, it visually displays the intermediate dynamic mode as well as output simulation results. The offered algorithm of creation of models can be also interesting to the experts in subject domain who aren't knowing programming languages.
References
[2] Adjemov S.S., Klenov N.V., Tereshonok M.V., Chirov D.S. The use of artificial neural networks for classification of signal sources in cognitive radio systems. Programming and Computer Software. 2016; 42(3):121-128. DOI: 10.1134/S0361768816030026
[3] Kurbatsky V.G., Sidorov D.N., Spiryaev V.A., Tomin N.V. Forecasting Nonstationary Time Series Based on Hilbert–Huang Transform and Machine Learning. Automation and Remote Control. 2014; 75(5):922-934. DOI: 10.1134/S0005117914050105
[4] Bogoslovskiy S.N. The scope of neural networks and the prospects for their development. Nauchnyy zhurnal KubGAU = Scientific journal of KubSAU. 2007; 27(3):1-11. (In Russian)
[5] Schegolev A.E., Klenov N.V., Soloviev I.I., Tereshonok M.V. Adiabatic superconducting cells for ultra-low-power artificial neural networks. Beilstein Journal of Nanotechnology. 2016; 7:1397-1403. DOI: 10.3762/bjnano.7.130
[6] Ignatenkov A.V., Ol'shanskij A.M. Application of an artificial neural network for scheduling processes on the example of the train schedule. Modern Information Technologies and IT-Education. 2015; 11(2):50-55. Available at: https://elibrary.ru/item.asp?id=26167466 (accessed 12.04.2018). (In Russian)
[7] Kipyatkova I.S., Karpov A.A. A study of neural network Russian language models for automatic continuous speech recognition systems. Automation and Remote Control. 2017; 78(5):858-867. DOI: 10.1134/S0005117917050083
[8] Kipjatkova I.C., Karpov A.A. Variants of deep artificial neural networks for speech recognition systems. Trudy SPIIRAN = SPIIRAS Proceedings. 2016; 6(49):80-103. (In Russian) DOI: 10.15622/sp.49.5
[9] Ryzhkov A.P., Katkov O.N., Morozov S.V. Neural network technologies in the decision of tasks of differentiation of access. Voprosy kiberbezopasnosti = Cybersecurity issues. 2016; 3(16):69-76. Available at: https://elibrary.ru/item.asp?id=26273593 (accessed 12.04.2018). (In Russian)
[10] Glazkova A.V. Automatic document classification on the basis of text audience age groups in e-learning systems. Modern Information Technology and IT-education. 2016; 12(3-2):50-54. Available at: https://elibrary.ru/item.asp?id=27705954 (accessed 12.04.2018).
[11] Basalin P.D., Kumagina E.A., Nejmark E.A., Timofeev A.E., Fomina I.A., Chernyshova N.N. IT education with an intelligent learning environment. Modern Information Technologies and IT-Education. 2017; 13(4):105-111. (In Russian) DOI: 10.25559/SITITO.2017.4.384
[12] Mikhailov A.S., Staroverov B.A. Visualization of training sample creation process for artificial neural network. Nauchnaja vizualizacija = Scientific Visualization. 2016; 8(2):85-97. Available at: https://elibrary.ru/item.asp?id=26460835 (accessed 12.04.2018). (In Russian)
[13] Voevoda A.A., Romannikov D.O. Synthesis of neural network for solving logical-arithmetic problems. Trudy SPIIRAN = SPIIRAS Proceedings. 2017; 5(54):205–223. (In Russian) DOI: 10.15622/sp.54.9
[14] Burdinskiy S.A., Kistenev V.K., Panteleyev V.I., Toropov A.S. 2007. Neural network modeling of non-tidal electricity consumption of railways. Proceedings of the Second All-Russian Scientific and Technical Conference with international participation “Problems of electrical engineering, power engineering and electrotechnology”. Togliatti: TSU. 372 p. (In Russian)
[15] Uskov A.A., Kuzmin AV. Intelligent control technologies. Artificial neural networks and fuzzy logic. M.: Goryachaya liniya – Telekom, 2004. 143 p. (In Russian)
[16] Gorshenin A.K. Pattern-based analysis of probabilistic and statistical characteristics of extreme precipitation. Informatics and Applications. 2017; 4:38-46. (In Russian) DOI: 10.14357/19922264170405
[17] Boltunov E.V. Neural network method of expanding the dynamic range of an analog-to-digital converter. Prospects for the development of information technologies. 2011; 4:79-83. Available at: https://elibrary.ru/item.asp?id=21017746 (accessed 12.04.2018). (In Russian)
[18] Nikolaeva I.V. Application of artificial neural networks for forecasting the dynamics of economic indicators. Sfera uslug: innovatsii i kachestvo = Services: innovation and quality. 2012; 8:22. Available at: https://elibrary.ru/item.asp?id=25679701 (accessed 12.04.2018). (In Russian)
[19] Shumskikh I.Yu., Piganov M.N. The use of a neuroimitator for predicting the reliability of space equipment. Regional scientific and practical conference dedicated to the 50th anniversary of the first manned flight into space. Samara, April 14-15, 2011. Samara: Publishing house of the Samara State Aerospace University, 2011. Pp. 205-207. (In Russian)
[20] Zhukov V.G., Bukhtoyarov V.V. On the application of artificial neural networks with radial basis functions in the problems of detecting anomalies in network traffic. Reshetnevskiye chteniya = Reshetnevsky readings. 2013; 2(17):285-286. Available at: https://elibrary.ru/item.asp?id=21802174 (accessed 12.04.2018). (In Russian)
[21] Amosov O.S., Magola D.S., Malashevskaya E.A. Estimation of Random Sequences Using Fuzzy Systems and Clustering. Informatika i sistemy upravleniya = Informatics and Control Systems. 2012; 1(31):146-155. Available at: https://elibrary.ru/item.asp?id=17637581 (accessed 12.04.2018). (In Russian)
[22] Bessonov A.A. A generalized learning algorithm for an evolving radial-basis network. Sistemi obrobki ínformatsíí̈ = Information processing systems. 2015; 10:163-166. Available at: http://www.hups.mil.gov.ua/periodic-app/article/13422 (accessed 12.04.2018). (In Russian)
[23] Dorofeyeva L.I. Modeling and Optimization of Separation Processes: Textbook. Tomsk: Publishing house of Tomsk Polytechnic University, 2008. 128 p. (In Russian)
[24] Abu Suek A.R.M. Prospects for the use of neural networks for assessing the quality of crude oil. REDS: Telekommunikatsionnyye ustroystva i sistemy = REDS: Telecommunication devices and systems. 2014; 4(4):376-378. Available at: https://elibrary.ru/item.asp?id=25663619 (accessed 12.04.2018). (In Russian)
[25] Rechnov A.V. Application of neural networks for classification analysis. Vestnik Rossiyskogo universiteta kooperatsii = Bulletin of the Russian University of Cooperation. 2013; 4(14):141-144. Available at: https://elibrary.ru/item.asp?id=21608691 (accessed 12.04.2018). (In Russian)
[26] Yudin D.A., Magergut V.Z. Application of the method of extreme training of the neural network for the classification of image areas. Nauchnyye vedomosti BelGU. Seriya: Istoriya. Politologiya. Ekonomika. Informatika = Scientific Bulletin of BelGU. Series: History. Political science. Economy. Computer science. 2013; 26/1:95-103. Available at: https://www.bsu.edu.ru/upload/iblock/a33/%E2%84%968%20(151)%20%D0%B2%D1%8B%D0%BF%2026_1.pdf (accessed 12.04.2018). (In Russian)
[27] Vinogradova E.Yu. Methodology for designing neural networks to support the adoption of managerial decisions. Izvestiya IGEA = News IGEA. 2011; 4:182-186. Available at: https://elibrary.ru/item.asp?id=16519395 (accessed 12.04.2018). (In Russian)
[28] Network of radial basis functions. MachineLearning.ru. Available at: http://www.machinelearning.ru/wiki/index.php?title=RBF (accessed 12.04.2018). (In Russian)
[29] Lyubivaya T.G. Table simulation of artificial intelligence algorithms in MS Excel. NovaInfo.Ru. 2016; 4(56):251-256. (In Russian)
[30] Anikin V.I., Karmanova A.A. Training of the artificial neural network of Kohonen by a cellular automaton. Informatsionnyye tekhnologii = Information technologies. 2014; 11:73-80. (In Russian)
[31] Solozhentsev E.D. Scenario logic-probabilistic risk management in business and technology. SPb.: Publishing house "Business Press", 2004. 432 p. (In Russian)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Publication policy of the journal is based on traditional ethical principles of the Russian scientific periodicals and is built in terms of ethical norms of editors and publishers work stated in Code of Conduct and Best Practice Guidelines for Journal Editors and Code of Conduct for Journal Publishers, developed by the Committee on Publication Ethics (COPE). In the course of publishing editorial board of the journal is led by international rules for copyright protection, statutory regulations of the Russian Federation as well as international standards of publishing.
Authors publishing articles in this journal agree to the following: They retain copyright and grant the journal right of first publication of the work, which is automatically licensed under the Creative Commons Attribution License (CC BY license). Users can use, reuse and build upon the material published in this journal provided that such uses are fully attributed.
