Yu. I. Nechaev

Saint-Petersburg National Research University of Information Technologies, Mechanics and Optics (Saint-Petersburg, Russia); State Marine Technical University of St. Petersburg (Saint-Petersburg, Russia)

nechaev@mail.ifmo.ru

Conceptual solutions for constructing a hybrid simulation (HS) system for interpreting behavior of the marine dynamic objects (MDO) in an evolving medium are discussed. The analysis is carried out in the functional spaces of behavior and control of the modern catastrophe theory (MCT). The theoretical basis for the implementation of the multifunctional model of the interpretation of HS determines the principle of structural and parametric synthesis of neurodynamic models under conditions of uncertainty based on the hierarchical structure of the software package. The analysis of behavior MDO and the choice of a solution in a neurodynamic environment is carried out on the basis of ensemble forecast and a matrix of strategic decisions. The interpretation of MDO behavior in HS systems on the base neural-fuzzy and multi-agent environment (MMS) is carried out as part of the Big Data processing strategy for large volumes of data un the regime of urgent computing (UC).

Nechaev Yu.I. Hybrid simulation of evolution dynamics in the neural networks basis. Neurocomputers. 2021. V. 23. № 3. Р. 25−34. DOI: https://doi.org/10.18127/j19998554-202103-03 (in Russian).

1. Barsegyan A.A., Kupriyanov M.S., Stepanenko V.V., Kholod I.I. Metody i modeli analiza dannykh: OLAP i Data Mining. SPb.: BKhVPeterburg. 2004. 336 s (In Russian).
2. Nechayev Yu.I. Neyrokompyutery v intellektualnykh tekhnologiyakh KhKhI veka. M.: Radiotekhnika. 2011. 352 s (In Russian).
3. Nechayev Yu.I. Teoriya katastrof: sovremennyy podkhod pri prinyatii resheniy. SPb.: Art-Ekspress. 2011. 392 s (In Russian).
4. Nechayev Yu.I. Sovremennyye problemy informatiki i vychislitelnoy tekhniki. SPb.: Art-Ekspress. 2018. 315 s (In Russian).
5. Nechayev Yu.I., Turchak A.A. Evolyutsionnaya dinamika neyronnoy seti glubokogo obucheniya. Materialy XXII Mezhdunar. konf. po myagkim vychisleniyam i izmereniyam SCM-2018. 2018. S. 185–189 (In Russian).
6. Figueira G., Almada-Lobo B. Hybrid simulation–optimization methods: A taxonomy and discussion. Simulation Modelling Practice and Theory. 2014. V. 46. P. 118–134.
7. Foster I., Zhao Y., Raicu I., Lu S. Cloud Computing and Grid Computing 360-Degree Compared. Preprint arXiv:0901.0131, 2008 [Elektronnyy resurs]. – URL: http://arxiv.org/ftp/arxiv/papers/0901/0901.0131.pdf (data obrascheniya: 01.03.2021)
8. Hinton G.H., Osindero S., Teh Y.-W. A fast learning algorithm for deep belief nets. Neural Computation. 2006. V. 58. № 7. P. 1527–1554.
9. Lublinsky B. Defining SOA as an architectural style. 9 January 2007. [Elektronnyy resurs].  – URL: http://www.ibm.com/developerworks/architecture/library/ar–soastyle/ (data obrascheniya: 01.03.2021).
10. Szalay A. Extreme data-intensive scientific computing // Computing in Science & Engineering. 2011. V. 13. №. 6. P. 34-41.
11. Urgent Computing Workshop 2007. Argonne National Lab, University of Chicago. April 25-26. 2007. [Elektronnyy resurs]. – URL: <http://spruce.teragrid.org/workshop/urgent07.php>. (data obrascheniya: 01.03.2021).
12. Zadeh L. Fuzzy logic, neural networks and soft computing. Соmmutation on the ASM-1994. V. 37. № 3. P. 77–84.