S.N. Zamuruev1, M.V. Cvetkov2

1,2 MIREA – Russian University of Technology (Moscow, Russia)
2 maxtsv@rambler.ru

The use of artificial intelligence methods, in particular neural networks, to detect control signals from unmanned aerial vehicles (UAVs) in the framework of electronic intelligence and counter-UAV tasks.

Goal – the features of UAV signals, such as the use of closed protocols, noise-resistant coding, and adaptive parameter tuning depending on the quality of the communication channel, are being investigated (considered).

To identify promising research areas for optimizing neural network architectures, expanding training samples, adapting to new protocols, increasing interpretability, integrating into the electronic warfare complex, and countering electronic warfare methods.

The limitations of radiation detection methods are analyzed to substantiate the prospects of using a neural network approach capable of finding hidden signs of signals in interference conditions.

A generalized methodology for using neural networks, including data collection and markup, preprocessing, feature extraction, classifier training, and postprocessing of results.

Examples of successful applications of various architectural neural networks (convolutional, recurrent, and ensemble) for detecting UAV signals with a low signal-to-noise ratio are studied.

The results obtained make it possible to evaluate the principles of operation of ultra-precise networks with signal spectrograms, which make it possible to detect characteristic time-frequency patterns of UAV signals and identify the direction of further research that will create highly effective adaptive intelligent systems for radio monitoring and countering new-generation UAVs that ensure superiority over enemy technologies.

Zamuruev S.N., Cvetkov M.V. Detection of control signals for unmanned aerial vehicles using neural networks. Achievements of modern radioelectronics. 2025. V. 79. № 12. P. 39–44. DOI: https://doi.org/10.18127/ j20700784-202512-07 [in Russian]

1. Nazarov L.E., Igoshin E.V., Zudilin A.S., Shcheglov M.A. Razrabotka, realizaciya i ispytaniya signal'no-kodovyh konstrukcij dlya vysokoskorostnoj radiolinii svyazi s BPLA. Uspekhi sovremennoj radioelektroniki. 2014. № 8. S. 68–74 [in Russian].
2. Ivanov V.S., Stroitelev B.A., Raevskij G.P. Organizaciya svyazi po sredstvam bespilotnyh letatel'nyh apparatov. Naukoemkie tekhnologii. 2025. T. 26. № 1. S. 37–44. DOI: https://doi.org/ 10.18127/j19998465-202501-05 [in Russian].
3. Makarenko S.I., Afonin I.E., Ivanov M.S. Bespilotnyj letatel'nyj apparat kak cel' protivovozdushnoj oborony. Uspekhi sovremennoj radioelektroniki. 2024. T. 78. № 5. S. 48–59. DOI: https://doi.org/10.18127/j20700784-202405-07 [in Russian].
4. Kagramanov E.E., Ivanova S.S., Kartashov V.S. Sposob predotvrashcheniya radiopomekh v sisteme svyazi bespilotnyh letatel'nyh apparatov. Radiotekhnika. 2024. T. 88. № 7. S. 11–15. DOI: https://doi.org/10.18127/j00338486-202407-02 [in Russian].
5. Ahmed A, Quoitin B, Gros A, Moeyaert V. A Comprehensive Survey on Deep Learning-Based LoRa Radio Frequency Fingerprinting Identification. Sensors (Basel). 2024. Jul. 8. V. 24(13). P. 4411. DOI: 10.3390/s24134411. PMID: 39001190; PMCID: PMC11244599.
6. Jagannath A., Jagannath J., Kumar P.S.P.V. A comprehensive survey on radio frequency (RF) fingerprinting: Traditional approaches, deep learning, and open challenges. Comput. Netw. 2022. V. 219. P. 109455. DOI: 10.1016/j.comnet.2022.109455.
7. Jouhari M., Saeed N., Alouini M.S., Amhoud E.M. A Survey on Scalable LoRaWAN for Massive IoT: Recent Advances, Potentials, and Challenges. IEEE Commun. Surv. Tutor. 2023. V. 25. P. 1841–1876. DOI: 10.1109/COMST.2023.3274934.
8. Khalifeh A., Aldahdouh K.A., Darabkh K.A., Al-Sit W. A Survey of 5G Emerging Wireless Technologies Featuring LoRaWAN, Sigfox, NB-IoT and LTE-M; Proceedings of the 2019 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET); Chennai, India. 21–23 March 2019. P. 561–566.