https://doi.org/10.62660/bcstu/4.2025.69

Volume 30, No. 4, 2025

69-81

  • Read article

    • Real-time drone type recognition using artificial intelligence

    Oleksandr Fomin

    Received 06.06.2025, Revised 30.10.2025, Accepted 15.12.2025

    Abstract

    The rapid proliferation of drones in military, civilian and critical infrastructure requires fast and accurate systems for their recognition and classification. The study aimed to increase the efficiency and accuracy of drone identification by developing an approach to their classification using artificial intelligence methods in real time. The study involved the analysis of drone typology, comparative analysis of artificial intelligence methods, visual modelling, software prototyping, and evaluation of classification accuracy metrics. As a result of the first stage of the study, a classification of drones by design, purpose, size and technical characteristics that affect their visual recognition was formed. The study established that multi-rotor vehicles are the most common due to their ease of operation; single-rotor vehicles are distinguished by their carrying capacity and flight duration; fixed-wing vehicles provide speed and range; and hybrid vehicles combine vertical take-off and horizontal flight. Additionally, specialised types of drones (combat, reconnaissance, photographic, micro- and tactical) were identified, and drones were classified by size, used in the study to compare the dimensions, weight, payload and flight duration with the types of applications. The second stage of the study included a comparative analysis of artificial intelligence methods for identifying types of drones in real time. The study established that computer vision models, in particular, convolutional neural networks, provide high accuracy, and one-stage architectures provide fast object detection. Transformers and fully connected neural layers demonstrate accuracy but require significant resources. Classical machine learning algorithms, such as support vector machine (92%), random forest (89%), nearest neighbours (87.7%), and naive Bayesian classifier (79%), showed different performance. In addition, reinforcement learning can be used in systems to adapt to changes in the environment, and decision trees provide transparency in classification. The results obtained contribute to the development of real-time drone detection and classification systems for defence, infrastructure protection, airspace monitoring and public safety

    Keywords:

    unmanned aerial vehicles; machine learning algorithms; computer recognition; neural networks; identification of rotary-winged drones

    Suggested citation
    Fomin, O. (2025). Real-time drone type recognition using artificial intelligence. Bulletin of Cherkasy State Technological University, 30(4), 69-81. https://doi.org/10.62660/bcstu/4.2025.69
    369 Views

    References

    1. Adebayo, A.S. (2025). AI driven species recognition and digital systematics: Applying artificial intelligence for automated organism classification in ecological and environmental monitoring. International Journal of Research Publication and Reviews, 6(2), 31-49. doi: 10.55248/gengpi.6.0225.0703.
    2. Aguilera, R.C., Mosqueda, M.A.A., Mosqueda, M.E.A., & Coronel, S.L.G. (2025). YOLO expert system for real-time pattern recognition using drones on wind farm turbine. Fractals, 33(5), article number 2550047. doi: 10.1142/ S0218348X25500471.
    3. Babich, A.P., Kibitkin, S.O., Georgiev, Yu.V., & Belzetskyi, R.S. (2024). Formation of a system for detection and recognition of the unmanned aerial vehicles. Visnyk of Vinnytsia Politechnical Institute, 176(5), 109-114. doi: 10.31649/1997-9266-2024-176-5-109-114.
    4. Castro, J., Alcaraz-Segura, D., Baltzer, J.L., Amorós, L., Morales-Rueda, F., & Tabik, S. (2024). Automated precise seeding with drones and artificial intelligence: A workflow. Restoration Ecology, 32(5), article number e14164. doi: 10.1111/rec.14164.
    5. Chae, M.-H., Park, S.-O., Choi, S., & Choi, C.-T. (2024). Reinforcement learning-based counter fixed-wing drone system using GNSS deception. IEEE Access, 12, 16549-16558. doi: 10.1109/ACCESS.2024.3358211.
    6. Chanda, S., Prangon, R.D., & Hoque, K.H. (2024). A CNN-based approach for room number detection using drone in indoor environment. In 2024 IEEE international conference on power, electrical, electronics and industrial applications (pp. 410-415). Rajshahi: IEEE. doi: 10.1109/PEEIACON63629.2024.10800605.
    7. Choosing between multi-rotor, fixed-wing, single-rotor, and hybrid VTOL drones – AUAV’s complete guide for finding your perfect match. (2025). Retrieved from https://www.auav.com.au/news/choosing-betweenmulti-rotor-fixed-wing-single-rotor-and-hybrid-vtol-drones-auavs-complete-guide-for-finding-your-perfectmatch/.
    8. Darwinto, P.A., Widodo, A.M., Agustina, N.P., Wahyuadnyana, K.D., & Rahaman, M. (2025). Artificial intelligence (AI) for autonomous drones. In B.B. Gupta & F. Colace (Eds.), AI developments for industrial robotics and intelligent drones (pp. 55-84). Hershey: IGI Global Publishing. doi: 10.4018/979-8-3693-2707-4.ch004.
    9. Dukowitz, Z. (2025). Big drones: An in-depth guide. Retrieved from https://uavcoach.com/big-drones/.
    10. Emon, S.I., Rahman, M.M., Akter, A., Rajbongshi, S., Yeasmin, S., Quraishi, M.A.N., Shafkat, A., & Majeed, Y. (2025). Automated code smell detection for software quality assurance using a web-based machine learning framework. Research Square. doi: 10.21203/rs.3.rs-6474801/v1.
    11. Essa, E. (2024). Feature fusion vision transformers using MLP-mixer for enhanced deepfake detection. Neurocomputing, 598, article number 128128. doi: 10.1016/j.neucom.2024.128128.
    12. Estrada, M.A.R. (2025). Full autonomous artificial intelligence in attack or defense decisions making in military drones box: The NeuronDrone-box. Journal of Advances in Artificial Intelligence, 3(2), 169-179. doi: 10.18178/ JAAI.2025.3.2.169-179.
    13. Gong, J., Li, D., Yan, J., Hu, H., & Kong, D. (2022). Comparison of radar signatures from a hybrid VTOL fixed-wing drone and quad-rotor drone. Drones, 6(5), article number 110. doi: 10.3390/drones6050110.
    14. Hasan, S.H., & Cansever, G. (2023). Drone tracking and object detection by YOLO and CNN. International Journal of Scientific Trends, 2(7), 78-108.
    15. Hoang, S., & Shen, I.Y. (2024). Effects of deterministic gust modeling for large, multi-rotor drones. In ASME 2023 international mechanical engineering congress and exposition (article number IMECE2023-113645). New Orleans: American Society of Mechanical Engineers. doi: 10.1115/IMECE2023-113645.
    16. Islam, F.A.S. (2025). The role of artificial intelligence in environmental monitoring for sustainable development and future perspectives. Journal of Global Ecology and Environment, 21(2), 164-179. doi: 10.56557/jogee/2025/ v21i29272.
    17. Jain, N., & Lenka, S. (2025). Artificial intelligence based precision agriculture for enhanced productivity. doi: 10.13140/RG.2.2.35586.59843.
    18. Kassab, M., Zitar, R.A., El Fallah, A., & Barbaresco, F. (2023). Bird/Drone detection and classification using classical and deep learning methods. Authorea. doi: 10.22541/au.168075364.45332093/v1.
    19. Khan, A., Kumar, K., & El Sayed, A.F. (2025). Unveiling the sky: Exploring synergies in drone robotics and automation through artificial intelligence and machine learning. In A. Khan, M.K. Hasan, M. Varish & M.A. Husain (Eds.), Advancements in artificial intelligence and machine learning (pp. 182-200). Singapore: Bentham Science Publishers. doi: 10.2174/9789815322583125010012.
    20. Korostin, O.O. (2024). Efficiency of text recognition in the automation of international maritime transport with the help of artificial intelligence. Таuridа Scientific Herald, Technical Sciences, 3, 29-38. doi: 10.32782/tnvtech.2024.3.4.
    21. Li, D., Yi, D., Zhou, X., Chen, X., Geng, Y., & Li, X. (2024). Multisource threatening event recognition scheme targeting drone intrusion in the fiber optic DAS system. IEEE Sensors Journal, 24(20), 32185-32195. doi: 10.1109/ JSEN.2024.3449440.
    22. Li, M. (2025). Beyond conventional drones: A review of unconventional rotary-wing UAV design. Drones, 9(5), article number 323. doi: 10.3390/drones9050323.
    23. Medarametla, S.R., & Thallapally, G. (2025). Comparing K-nearest neighbors and naive bayes in real-time recommendation systems. Global Journal of Engineering Innovations and Interdisciplinary Research, 5(1), article number 18. doi: 10.33425/3066-1226.1075.
    24. Milani, S., Zhang, Z., Topin, N., Shi, T.R., Kamhoua, C., Papalexakis, E.E., & Fang, F. (2023). MAVIPER: Learning decision tree policies for interpretable multi-agent reinforcement learning. In M.-R. Amini, S. Canu, A. Fischer, T. Guns, P.K. Novak & G. Tsoumakas (Eds.), European conference: Machine learning and knowledge discovery in databases (pp. 251-266). Cham: Springer. doi: 10.1007/978-3-031-26412-2_16.
    25. Mrabet, M., Sliti, M., & Ben Ammar, L. (2024). Machine learning algorithms applied for drone detection and classification: Benefits and challenges. Frontiers in Communications and Networks, 5, article number 1440727. doi: 10.3389/frcmn.2024.1440727.
    26. Nagel, L. (2025). Types of drones and UAVs. Retrieved from https://www.tytorobotics.com/blogs/articles/typesof-drones?srsltid=AfmBOoquLrJpCU9jWWg4oiOfy4Id2TWE2u9kUQ1vpiWuULcFMcPsvBHO.
    27. Rennie, J. (2016). Drone types: Multi-rotor vs fixed-wing vs single rotor vs hybrid VTOL. Retrieved from https:// www.auav.com.au/articles/drone-types/.
    28. San-Segundo, R., Angulo, L., Gil-Martin, M., Carramiñana, D., & Bernardos, A.M. (2024). Hybrid artificial intelligence strategies for drone navigation. AI, 5(4), 2104-2126. doi: 10.3390/ai5040103.
    29. Sumathi, P., Thungashree, Y.S., & Pushpalatha, S. (2025). Real-time drone type detection for smart air traffic monitoring. In National level technical symposium (Advaya 2k25) (pp. 44-47). New Delhi: All India Council for Technical Education. doi: 10.59544/WQWN1934/ADVAYA2K25P10.
    30. Thomas, G.A.S., Muthukaruppasamy, S., Kumar, S.S., Karthikeyan, B.J., & Krishnan, S. (2025). Navigating the nexus: Unravelling challenges, ethics, and applications of embodied AI in drone technology through the lens of computer vision. In P. Raj, A. Rocha, S.P. Singh, P.K. Dutta & B. Sundaravadivazhagan (Eds.), Building embodied AI systems: The agents, the architecture principles, challenges, and application domains (pp. 61-78). Cham: Springer. doi: 10.1007/978-3-031-68256-8_3.
    31. Umashankar, N., & Geethanjali, K.S. (2024). A comprehensive study of artificial intelligence applications of drone. Engineering Archive. doi: 10.31224/4194.
    32. Wasswa, H., Abbass, H., & Lynar, T. (2025). Are GNNs worth the effort for IoT botnet detection? A comparative study of VAE-GNN vs. ViT-MLP and VAE-MLP approaches. ArXiv. doi: 10.48550/arXiv.2505.17363.
    33. Yermilova, N., Zourab, Y., & Iermilov, R. (2023). Methods of complex objects automatic recognition by form. Control, Navigation and Communication Systems, 4(74), 80-84. doi: 10.26906/SUNZ.2023.4.080