A.A. Petrov1, O.V. Druzhinina2, O.N. Masina3

1–3 Bunin Yelets State University (Yelets, Russia)

2 FRС «Computer Science and Control» of Russian Academy of Sciences (Moscow, Russia)

1 xeal91@yandex.ru, 2 ovdruzh@mail.ru, 3 olga121@inbox.ru

Modeling radio wave propagation in complex nonlinear environments is a pressing scientific challenge. Developing effective tools for predicting Wi-Fi signal characteristics, taking into account the complex geometric characteristics of enclosing structures, is essential. The development of neural network algorithms based on synthetic data aims to overcome the limitations associated with the labor-intensive nature of in-kind measurements. This paper aims to develop algorithmic and software tools for modeling electromagnetic wave propagation using neural networks, analyze the results of computational experiments, and evaluate the effectiveness of intelligent algorithms based on standard metrics. A simulation model with procedural floor plan generation functionality is developed to create a representative synthetic dataset. A specialized MLP–Wi-Fi RW (Multilayer Perceptron – Wi-Fi Radio Waves) neural network architecture is proposed and implemented. A variant of this neural network is trained using the generated data, and the effectiveness of the developed algorithms is evaluated using the cross-validation method. Problem-oriented software is developed in Python and Julia, and the obtained results are interpreted. The results can be applied to solving problems of constructing digital twins applicable to the analysis of physical propagation environments for shortwave radio signals. This modeling approach is aimed at improving digital communication systems and developing intelligent methods for analyzing electromagnetic wave characteristics.

Petrov A.A., Druzhinina O.V., Masina O.N. Development and implementation of a neural network algorithm for modeling the propagation of electromagnetic waves // Electromagnetic waves and electronic systems. 2026. V. 31. № 4. P. 94−103. DOI: https://doi.org/10.18127/j15604128-202604-08

1. Hata M. Empirical formula for propagation loss in land mobile radio services. IEEE Transactions on Vehicular Technology. 1980. V. 29. № 3. P. 317–325. DOI 10.1109/T-VT.1980.23859.
2. Panchenko V.E., Erokhin G.A., Gainutdinov T.A., Kocherzhevsky V.G., Shorin O.A. Combination of statistical and deterministic methods for calculating the radio field in urban conditions. Elektrosvyaz. 1998. № 4. P. 31–33. (in Russian)
3. Milyutin E.R., Vasilenko G.O., Sivers M.A., Volkov A.N., Pevtsov N.V. Methods for calculating the field in UHF communication systems. St. Petersburg: Triada. 2003. 159 p. (in Russian)
4. Perez Fontan F., Mariño Espiñeira P. Modeling the wireless propagation channel: a simulation approach with MATLAB. Wiley. 2008. 268 p. DOI 10.1002/9780470751749.
5. Utz V.A. Study of signal propagation losses in cellular communication based on statistical models. Bulletin of the Immanuel Kant Baltic Federal University. 2011. № 4. P. 44–49. (in Russian)
6. Molchanov S.V., Zakharov A.I. Applying artificial neural networks for prediction of radiowave propagation features. bulletin of the Immanuel Kant Baltic Federal University. 2014. № 4. P. 100–105. (in Russian)
7. Grishko A.K., Goryachev N.V., Trusov V.A., Podsyakin A.S., Proshin A.A. Analysis of mathematical models for calculating the parameters of radio transmission lines. Proceedings of the International Symposium "Reliability and Quality". 2018. V. 2. P. 361–363. (in Russian)
8. Wilson H. Artificial intelligence. Grey House Publishing. 2018. 200 p.
9. Nikolenko S.I., Kadurin A.A., Arkhangelskaya E.V. Deep Learning. St. Petersburg: Piter. 2018. 480 p. (in Russian)
10. Kazmin O.Yu., Simonina O.A. Solving the problem of optimizing the electromagnetic environment in radio access networks using neural networks. Proceedings of Educational Institutions of Communications. 2021. V. 7. № 3. P. 25–37. DOI 10.31854/1813-324X-2021-7-3-25-37. (in Russian)
11. Barkhatov N.A., Revunov S.E., Uryadov V.P. Artificial neural network technique for predicting the critical frequency of the ionospheric F2 layer. Radiophysics and Quantum Electronics. 2005. V. 48. № 1. P. 1–13. DOI 10.1007/s11141-005-0043-4.
12. Romashchenko M.A., Vasilchenko D.V., Beletskaya S.Yu. Use of artificial neural networks to assess the impact of electromagnetic interference. Radiotekhnika. 2023. V. 87. № 8. P. 21−27. DOI 10.18127/j00338486-202308-04. (in Russian)
13. Adjemov S.S., Klenov N.V., Tereshonok M.V., Chirov D.S. A neural-network method for the synthesis of informative features for the classification of signal sources in cognitive radio systems. Moscow University Physics Bulletin. 2016. V. 71. № 2. P. 174–179. DOI 10.3103/S0027134916020028.
14. Adzhemov S.S., Tereshonok M.V., Chirov D.S. Type recognition of the digital modulation of radio signals using neural networks. Moscow University Physics Bulletin. 2015. V. 70. № 1. P. 22–27. DOI 10.3103/S0027134915010026.
15. Petrov A.A. The structure of the software package for modeling of technical systems in conditions of switching functioning modes. Electromagnetic Waves and Electronic Systems. 2018. V. 23. № 4. P. 61–64. (in Russian)
16. Petrov A.A., Druzhinina O.V., Masina O.N. Development of algorithmic support for modeling nonlinear control switching systems. Nonlinear World. 2022. V. 20. № 1. P. 5–13. DOI 10.18127/j20700970-202201-01 (in Russian)
17. Chernomordov S.V., Druzhinina O.V., Masina O.N., Petrov A.A. Application of machine learning methods in problems of neural network modeling of controlled technical systems. Neurocomputers. 2022. V. 24. № 1. Р. 25–35. DOI 10.18127/j19998554-202201-03. (in Russian)
18. Petrov A.A., Druzhinina O.V., Masina O.N. Approach to neural network modeling of the propagation of electromagnetic waves. Electromagnetic waves and electronic systems. 2022. V. 27. № 6. P. 53−58. DOI 10.18127/j15604128-202206-07. (in Russian)
19. Gupta P., Bagchi A. Introduction to NumPy. Essentials of Python for Artificial Intelligence and Machine Learning. 2024. P. 127–159. DOI 10.1007/978-3-031-43725-0_4.
20. Bezanson J., Karpinski S., Shah V.B., Edelman A. Julia: A Fast Dynamic Language for Technical Computing. arXiv. 2012. arXiv:1209.5145v1 [cs.PL]. P. 1–27. DOI 10.48550/arXiv.1209.5145.
21. Innes M., Saba E., Fischer K., Gandhi D., Rudilosso M.C., Joy N.M., Karmali T., Pal A., Shah V. Fashionable Modelling with Flux. arXiv. 2012. arXiv:abs/1811.01457 [cs.PL]. P. 1–7. DOI 10.48550/arXiv.1811.01457.
22. Innes M. Flux: Elegant Machine Learning with Julia. Journal of Open Source Software. 2018. V. 3. № 25. P. 602. DOI 10.21105/ joss.00602.