|Article title||THE CLASSIFICATION RESULTS OF THE NEURAL NETWORK TO FORM THE INPUT INFLUENCES THE PREDICTION OF FREE RESOURCES PROVIDER|
|Authors||R. Mamedov, A.B. Chernyshev|
|Section||SECTION II. COMPUTER ENGINEERING AND COMPUTER SCIENCE|
|Month, Year||07, 2015 @en|
|Abstract||This article contains the unique specificity of the results of neural networks research, and the results of the classification of the output of neural networks, facilitate the enforcement of intellectual autonomy in the learning process. The purpose of this article is developing a radically new method of contributing to the classification of the results of the neural network, and serves to simplify the procedure for filling the knowledge base and reducing the computational resources for processing large amounts of data. Research objectives consist in identifying and selecting the input actions of a neural network, as well as to identify the most promising and relevant methods of processing its results. The present study is based on neural networks in terms of constructing an intelligent system. The subject of investigation are the results of the classification neural network serving for the formation of input actions forecasting free resources provider. The proposed method of solving the identified problem is a method for autonomous learning intelligent system. Application of the results is expected in the systems of protection against attacks Class DDOS, in particular, promote the client overflow channel provider. On this basis, the relevance of the topic to date, due to the rapid increase in the number of attacks carried out in the Internet. A special feature of this study is to establish a system of training depending on its condition. The advantages of this method are as self-identification of the priority of events that must be recorded in the knowledge base. Thus, teacher"s percentage of participation the activities of the intellectual system is reduced by several times, that improves performance of intellectual system.|
|Keywords||DDOS attack; channel width; neural network; knowledge base.|
|References||1. Laboratoriya kasperskogo [Kaspersky lab]. Available at: https://securelist.ru/blog/issledovaniya/
25740/stastika-ddos-atak-s-ispolzovaniem-botnetov-v-pervom-kvartale-2015-goda (accessed 17 June 2015).
2. Mamedov R.A. Analiz primeneniya i posledstviya massirovannykh atak raspredelennogo otkaza v obsluzhivanii na server so srednestatisticheskoy moshchnost'yu [Analysis of the use and consequences of massive attacks distributed denial of service attack on the server with the average power], Nauchno-tekhnicheskiy vestnik Povolzh'ya [Scientific and Technical Volga
region Bulletin], 2014, No. 3, pp. 150-157.
3. Mamedov R.A. Sistemnyy analiz trafika provaydera na predmet vyyavleniya rasprede-lennoy ataki na otkaz obsluzhivaniya kanala [System analysis of traffic to detect attacks distributed denial of service channel], Sovremennaya nauka i innovatsii [Modern scientific researches and innovations], 2014, No. 1, pp. 24-31.
4. Babuska R. Construction of fuzzy systems-interplay between precission and transparency, Proc. of Europ Sympos on Intell Techn., Aachen (Germany), 2000, pp. 445-452.
5. Mandani E.H. A fuzzy rule-based method of controlling dynamic processes. Queen Mary College. London, 1981.
6. Finaev V.I., Glod O.D. Conceptual Model of an Adaptive Trained Control System by Before-hand Uncertain Situational Objects, Third European Congress on Intelligent Techniques and Soft Computing. Aachen, Germany, 1995.
7. Borisov A.N., Krumberg O.A., Fedorov I.P. Prinyatie resheniy na osnove nechetkikh modeley: Primery ispol'zovaniya [Decision making based on fuzzy models: Examples of usage]. Riga: Zinatne, 1990, 184 p.
8. Lei Wang, Dun-bing Tang. An improved adaptive genetic algorithm based on hormone modulation mechanism for job-shop scheduling problem, Expert Systems with Applications, 2011, Vol. 38, No. 6, pp. 7243-7250.
9. Enroth-Cugell C. and J.G. Robson. The Contrast Sensitivity of Retinal Ganglion Cells of the Cat., Journal of Physiology, 1966, No. 187, pp. 517-23.
10. Bonavear F., Dorigo M. Swarm Intelligence: from Natural to Artificial Systems. Oxford university Press, 1999.
11. Iskusstvennye immunnye sistemy i ikh primenenie [Artificial immune systems and their applications], By ed. D. Dasgupty: Translation from English, By ed. A.A. Romanyukhi. Moscow: Fizmatlit, 2006, 344 p.
12. Mamedov R.A. Sistemnyy analiz staticheskogo predostavleniya provayderom uslugi dostupa v internet [Analysis of the static system of granting the service provider access to the Internet] Materialy III Vserossiyskoy nauchno-prakticheskoy konferentsii: molodezh' nauka innovatsii
[Proceedings of the III all-Russian scientific-practical conference: youth science innovation]. Grozny, 2014, Vol. 1, pp. 32-37.
13. Rodzin S.I. Vychislitel'nyy intellekt: nemonotonnye logiki i graficheskoe predstavlenie znaniy [Computational intelligence: nonmonotonic logic and graphic representation of knowledge] Programmnye produkty i sistemy [Programmnye Produkty i Sistemy], 2002, No. 1, pp. 20-22.
14. Konysheva L.K. Osnovy teorii nechetkikh mnozhestv [Fundamentals of the theory of fuzzy sets]. St. Petersburg: Piter, 2011, 192 p.
15. Tselykh A.N., Dikarev S.B., Gura V.V. Nekotorye podkhody k proektirovaniyu adaptivnykh sistem [Some approaches to the design of adaptive systems], Vestnik komp'yuternykh i informatsionnykh tekhnologiy [Herald of Computer and Information Technologies], 2006, No. 5, pp. 37-41.
16. Chernukhin Yu.V., Pisarenko S.N., Priemko A.A. Neyrosetevaya sistema navigatsionnoy bezopasnosti transportnykh ob"ektov v nazemnoy, podvodnoy, nadvodnoy i vozdushnoy sredakh [Neural-network-based system of navigational safety of transport objects in the ground, underwater, surface and air environments], Iskusstvennyy intellekt. Nauchno-teoreticheskiy zhurnal NAN Ukrainy [Artificial intelligence. Scientific-theoretical journal of the national Academy of Sciences of Ukraine], 2006, No. 3, pp. 331-339.
17. Bershteyn L.S., Bozhenyuk A.V. Otsenka stepeni izomorfizma na osnove nechetkikh mnozhestv vnutrenney ustoychivosti i klik nechetkikh grafov [Assessment of the degree of isomorphism based on the fuzzy sets of the internal stability of fuzzy graphs and cliques], Programmnye produkty i sistemy [Programmnye Produkty i Sistemy], 2002, No. 1, pp. 12-15.
18. Zadeh L.A. Is there a need for fuzzy logic?, Information Sciences, Elsevier, 2008, No. 178, pp. 2751-2779.
19. Polkovnikova N.A. Proektirovanie gibridnoy ekspertnoy sistemy podderzhki prinyatiya resheniy [Design of a hybrid expert system for decision support], Sb. tez. dokl. II Vserossiyskogo kongressa molodykh uchenykh [The collection of theses of reports II all-Russian Congress of young scientists]. St. Petersburg: NIU ITMO, 2013. Issue I, pp. 46-48.
20. Pegat A. Nechetkoe modelirovanie i upravlenie [Fuzzy modeling and control]: Translation from English. Moscow: BINOM. Laboratoriya znaniy, 2009, 798 p.
21. Tselykh A.N., Dikarev S.B., Gura V.V. Nekotorye podkhody k proektirovaniyu adaptivnykh system [Some approaches to the design of adaptive systems], Vestnik komp'yuternykh i informatsionnykh tekhnologiy [Herald of Computer and Information Technologies], 2006, No. 5, pp. 37-41.