AP14971907 — Development of a frequency-based reliable system for detecting suspicious drones using SDR and acoustic signatures

The goal of the project is to develop a system that detects suspicious drones and operates in real time, based on the use of deep learning algorithms to represent drone frequencies obtained using SDR radio and acoustic sensors.

Relevance of the project: The main objective of the project proposal is to develop a reliable system for detecting suspicious drones, and develop and introduce it as a bimodal sensor for real-time use in protected areas or special buildings in the country. For the last 4 years, I have been conducting research on recognizing drones by the sound of their flight [8, 9, 10, 11, 12] on the advice of my foreign research supervisor. In studies, acoustic sensor testing was found to be more effective in identifying suspicious drones than other methods.

Scientific supervisor: PhD doctor, Utebaeva Dana

Results obtained: As a result of the project, a comprehensive system based on intelligent sensors and SDR (Software-Defined Radio) was developed for detecting drones in protected areas and predicting their suspicious movements. The system operates in real-time and enables efficient drone recognition by integrating multiple sensor inputs. A weighted voting system combines neural network models to improve detection accuracy. The acoustic database and SDR algorithms provide flexibility and cost-effectiveness. The proposed system can be easily adapted to various protected sites, enhancing security measures. The project advanced research skills and delivered innovative solutions for real-time drone monitoring.

List of publications with links to them

1. Utebayeva D., Ilipbayeva L., Matson E.T. Practical Study of Recurrent Neural Networks for Efficient Real-Time Drone Sound Detection: A Review // Drones. 2023. Vol. 7. P. 26. DOI: https://doi.org/10.3390/drones7010026
2. Utebayeva D., Yembergenova A. Study a deep learning-based audio classification for detecting the distance of UAV // 2024 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS), Madrid, Spain. 2024. P. 1–7. DOI: https://doi.org/10.1109/EAIS58494.2024.10569107
3. Utebayeva D., Ilipbayeva L., Seidaliyeva U., Yembergenova A., Matson E.T. Deep Learning Models for Predicting Drone Sound Distances: Lightweight, Fusion and Hybridization Approaches // Preprints. 2024. 2024102156. DOI: https://doi.org/10.20944/preprints202410.2156.v1
4. Utebayeva D., Ilipbayeva L. Investigation Of Deep Learning Models Based On Single-Layer Simplernn, LSTM And GRU Networks For Recognizing Sounds Of UAV Distances // Scientific Journal of Astana IT University. 2024. Vol. 19. P. 60–75. DOI: https://doi.org/10.37943/19XNOV6347
5. Utebayeva D., Ilipbayeva L. A Comparative Study Of Software-Defined Radio (SDR) And Smart Acoustic Sensor Performance For UAV Detection // Международный Журнал Информационных И Коммуникационных Технологий. 2024. Vol. 5, No. 3. P. 90–98. DOI: https://doi.org/10.54309/IJICT.2024.19.3.008
6. Utebayeva D., Ilipbayeva L. Research on the detection range of smart acoustic sensors for unmanned aerial vehicles // Бағдар-Ориентир. 2024. No. 3. URL: https://nuo.kz/kk/%D0%B1%D0%B0%D0%B3%D0%B4%D0%B0%D1%80-%D3%99%D1%81%D0%BA%D0%B5%D1%80%D0%B8-%D1%82%D0%B5%D0%BE%D1%80%D0%B8%D1%8F%D0%BB%D1%8B%D2%9B-%D0%B6%D1%83%D1%80%D0%BD%D0%B0%D0%BB%D1%8B/
7. Утебаева Д.Ж., Илипбаева Л.Б., Матсон Е. Software Defined Radio әдісімен дрондарды танудың мүмкіндіктерін зерттеу // Рэжбәии Ғылыми Еңбектері. 2024. No. 4 (58).
8. Utebayeva D., Ilipbayeva L., Smailov N., Matson E. Investigation Of Recent Methods Of UAV Sound Detection // Рэжбәии Ғылыми Еңбектері. 2024. No. 4 (58).