O.V. Esikov1, V.L. Rumyantsev2, I.V. Milko3, S.A. Kurbatsky4, I.A. Kleshchary5, L.D. Shcherbakov6

1–4JS CDBAE (Tula, Russia)
5, 6 Tula State University (Tula, Russia)
1 eovmail@rambler.ru, 2 vlroom@yandex.ru, 3 milko_igor@mail.ru, 4 cdbae@cdbae.ru, 5 klesharivan5@gmail.ru, 6 lev.denisovich@yandex.ru

To solve the problem of recognition of air traffic objects based on radar information, the application of the CatBoost method is proposed and experimentally verified. The rational values of the algorithm parameters that provide the best recognition accuracy have been experimentally determined. The accuracy of air traffic object recognition using the proposed method and an artificial neural network with direct signal propagation has been compared. It has been shown that the CatBoost method provides higher recognition accuracy than an artificial neural network with a smaller training set.

Esikov O.V., Rumyantsev V.L., Milko I.V., Kurbatsky S.A., Klesh chary I.A., Shcherbakov L.D. Application of the CatBoost algorithm for recognition of air tra ffic objects. Nonlinear World. 2026. V. 24. № 1. P. 80–90. DOI: https:// doi.org/10.18127/ j20700970-202601-07 (In Russian)

1. Ritchie M., Fioranelli F., Griffiths H., Torvik B. Monostatic And Bistatic Radar Measurements Of Birds And Micro-Drone. IEEE Radar Conference, RadarConf 2016.
2. Makarenko S.I., Timoshenko A.V., Vasil'chenko A.S. Analiz sredstv i sposobov protivodejstviya bespilotnym letatel'nym apparatam. Сhast' 1. Bespilotnyj letatel'nyj apparat kak ob"ekt obnaruzheniya i porazheniya. Sistemy upravleniya, svyazi i bezopasnosti. 2020. № 1. S. 109–146 (In Russian).
3. Gorelik A.L., Barabash Yu.L., Krivosheev O.V., Epshtejn S.S. Selekciya i raspoznavanie na osnove lokacionnoj informacii. Pod red. A.L. Gorelika. M.: Radio i svyaz'. 1990. 282 c. (In Russian).
4. Dao Van Luk, Konovalov A.A., Le Min' Hoang. Eksperimental'noe issledovanie traektornyh priznakov dlya raspoznavaniya nizkoletyashchih maloskorostnyh radiolokacionnyh celej v poluaktivnoj RLS. Izv. vuzov Rossii. Ser.: Radioelektronika. 2022. T. 25. № 3. S. 39–50 (In Russian).
5. Shirman Ya.D., Gorshkov S.A., Leshchenko S.P., Bratchenko G.D. i dr. Metody radiolokacionnogo raspoznavaniya i ih modelirovanie. Radiolokaciya i radiometriya. 2000. № 3. Radiolokacionnoe raspoznavanie i metody matematicheskogo modelirovaniya. S. 5–64 (In Russian).
6. Subbotin S.A. Postroenie derev'ev reshenij dlya sluchaya maloinformativnyh priznakov. Radioelektronika, informatika, upravlenie. 2019. № 1. S. 1–12 (In Russian).
7. Vorob'ev E.N., Verem'ev V.I., Holodnyak D.V. Raspoznavanie vintomotornyh letatel'nyh apparatov v passivnoj bistaticheskoj RLS. Izv. vuzov Rossii. Ser.: Radioelektronika. 2018. № 6. S. 75–82. DOI: 10.32603/1993-8985-2018-21-6-75-82 (In Russian).
8. Hajkin C. Nejronnye seti: polnyj kurs. Izd. 2-e, ispr.: Per. s angl. M.: OOO «I.D. Vil'yams». 2006. 1104 s. (In Russian).
9. Barsegyan A.A., Kupriyanov M.S., Kuznecov M.S., Stepanenko V.V., Holod I.I. Tekhnologii analiza dannyh: Data Mining, Visual Mining, Text Mining, OLAP. Izd. 2-e, pererab. i dop. SPb.: BHV-Peterburg. 2007. 384 s. (In Russian).
10. Witten I.H., Frank E., Hall M.A. Data Mining: Practical Machine Learning Tools and Techniques. 3rd Edition. Morgan Kaufmann. 2011. 664 p.
11. Andreev A.V., Esikov O.V., Mamon Yu.I., Akinshin R.N., Zatuchnyj D.A., Feoktistova O.G. Primenenie iskusstvennyh nejronnyh setej dlya raspoznavaniya ob"ektov na graficheskih izobrazheniyah. Vestnik Sankt-Peterburgskogo gosudarstvennogo universiteta grazhdanskoj aviacii. Pod. red. M.Yu. Smurova. 2017. № 1 (14). S. 131–141 (In Russian).
12. Maralov A.A., Serimbetov B.A. Sovremennye metody raspoznavaniya obrazov podhody algoritmy i realizaciya v informacionnyh sistemah. Vestnik nauki. 2025. T. 2. № 2 (83). S. 697–703 (In Russian).
13. Kavrin D.A., Subbotin S.A. Izvlechenie sbalansirovannyh obuchayushchih vyborok metodom psevdoklasterizacii. Radioelektronika i informatika. 2019. № 2. S. 26–32 (In Russian).
14. Vozhdaev V.V., Teperin L.L. Harakteristiki radiolokacionnoj zametnosti letatel'nyh apparatov. Fizmatlit. 2018. 376 s. (In Russian).
15. Bespilotnye letatel'nye apparaty. Spravochnoe posobie. Voronezh: Izdatel'sko-poligraficheskij centr «Nauchnaya kniga». 2015. 620 s. (In Russian).
16. Rostopchin V.V. «Napast' XXI veka»: storony odnoj «medali». Aviapanorama. 2018. № 4. S. 12–17 (In Russian).
17. Rostopchin V.V. «Napast' XXI veka»: storony odnoj «medali» (prodolzhenie). Aviapanorama. 2018. № 5. S. 8–21 (In Russian).
18. Rostopchin V.V. «Napast' XXI veka»: storony odnoj «medali» (prodolzhenie). Aviapanorama. 2018. № 6. S. 16–23 (In Russian).
19. Rostopchin V.V. «Napast' XXI veka»: storony odnoj «medali» (prodolzhenie). Aviapanorama. 2019. № 1. S. 12–17 (In Russian).
20. Ruzhickij E.I. Vertolety. M.: Viktoriya, AST. 1997. 192 s. (In Russian)
21. Peto T., Bilicz S., Szucs L., Gyimothy S. et al. The Radar Cross Section of small propellers on Unmanned Aerial Vehicles. 10th European Conf. on Antennas and Propagation, Davos, Switzerland, 10–15 April 2016. P. 1–4. DOI: 10.1109/EuCAP.2016.7481645.
22. Skorost' poleta ptic tablica [Elektronnyj resurs]. URL: https://cyberlesson.ru/skorost-poleta-ptic-tablica/ (data obrashcheniya 25.09.2024) (In Russian).
23. Vorob'ev E.N. Issledovanie signal'nyh priznakov raspoznavaniya malyh BPLA v poluaktivnoj RLS. Vestnik Novgorodskogo gosudarstvennogo universiteta. Ser.: Tekhnicheskie nauki. 2019. № 4. S. 72–77. DOI: 0.34680/2076-8052.2019.4(116).72–77 (In Russian).
24. Salahutdinova K.I., Lebedev I.S., Krivcova I.E. Algoritm gradientnogo bustinga derev'ev reshenij v zadache identifikacii programmnogo obespecheniya. Nauchno-tekhnicheskij vestnik informacionnyh tekhnologij, mekhaniki i optiki. 2018. T. 18. № 6. S. 1016–1022 (In Russian).
25. Prokhorenkova L., Gusev G., Vorobev A., Dorogush A.V., Gulin A. CatBoost: unbiased boosting with categorical features. In Advances in Neural Information Processing Systems. 2018. P. 6638–6648.
26. Chen T., Guestrin C. Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 2016. P. 785–794.
27. Friedman J.H. Stochastic gradient boosting. Computational statistics & data analysis. 2002. T. 38. № 4. P. 367–378.
28. Kaftannikov I.L., Parasich A.V. Osobennosti primeneniya derev'ev reshenij v zadachah klassifikacii. Vestnik YuUrGU. Ser.: Komp'yuternye tekhnologii, upravlenie, radioelektronika. 2015. № 3 (15). S. 26–32 (In Russian).
29. Dorogush A., Ershov V., Gulin A. CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363. 2018.
30. Urvachev E.M. Primenenie algoritma mashinnogo obucheniya dlya opredeleniya parametrov modelej sverhnovyh po ih krivym bleska. Preprinty IPM im. M.V. Keldysha. 2021. № 88. 11 s. (In Russian).
31. Chen T., Guestrin C. Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 2016. P. 785–794.
32. Ke G. et al. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems. 2017. T. 30.
33. Regulyarizaciya parametrov v CatBoost [Elektronnyj resurs]. URL: https://www.geeksforgeeks.org/machine-learning/catboost-regularization-parameters. (data obrashcheniya 25.09.2025) (In Russian).
34. Galushkin A.I. Nejronnye seti: osnovy teorii. M.: Goryachaya liniya – Telekom. 2012. 496 s. (In Russian)
35. Haykin S. Neural Networks and Learning Machines. 3rd ed. Pearson Education. 2009. 906 p.
36. Kiseleva T.V., Maslova E.V., Bychkov A.G. Mashinnoe obuchenie dlya resheniya zadach raspoznavaniya obrazov. ITNOU: Informacionnye tekhnologii v nauke, obrazovanii i upravlenii. 2021. № 2 (18). S. 19–24 (In Russian).