Підвищення рівня безпеки і захищеності транспортної інфраструктури від повітряних загроз на основі їх акустичної ідентифікації

D. O. Bosyi; O. I. Sablin; I. Yu. Potapchuk

doi:10.15802/stp2025/345823

Authors

D. O. Bosyi Ukrainian State University of Science and Technologies, SEI DIIT, Ukraine https://orcid.org/0000-0003-1818-2490
O. I. Sablin Ukrainian State University of Science and Technologies, SEI DIIT, Ukraine https://orcid.org/0000-0001-6784-648X
I. Yu. Potapchuk Ukrainian State University of Science and Technologies, SEI DIIT, Ukraine https://orcid.org/0000-0002-5985-1040

DOI:

https://doi.org/10.15802/stp2025/345823

Keywords:

railway, electrification, infrastructure, contact network, monitoring, safety, acoustic identification, air threats, microcontroller computing, low-frequency cepstral coefficients, neural network

Abstract

Purpose. The purpose of the study is to enhance the safety and protection of transport infrastructure through the development of an intelligent monitoring system capable of detecting and classifying aerial threats based on their acoustic characteristics. The work focuses on designing algorithms for the early recognition of unmanned aerial vehicles (UAVs) and cruise missiles near critical infrastructure, addressing the growing importance of autonomous safety systems under hybrid threat conditions. Methodology. The research applies a comprehensive approach combining digital signal processing, machine learning, and embedded computing. Acoustic signatures of aerial targets were analyzed in MatLab using Audio Toolbox and DSP System Toolbox. Mel-Frequency Cepstral Coefficients (MFCC) were used as primary features to capture the most informative frequency components. The artificial neural network model was optimized for STM32 microcontrollers and implemented using CMSIS-DSP and X–CUBE–AI libraries. Wireless data exchange between sensor nodes employed ZigBee and LoRa protocols, ensuring scalable and energy-efficient communication. Findings. The system provides real-time acquisition, processing, and classification of acoustic signals with an accuracy of 85–90%. The MEMS-based sensor node prototype performs fully local processing without cloud services. Originality. For the first time, a concept integrating acoustic identification of aerial threats into transport infrastructure monitoring has been developed using embedded artificial intelligence, on-device learning, and local decision-making capabilities. Practical value. The results can be used to create distributed early-warning systems, upgrade contact line and infrastructure monitoring, and strengthen technological autonomy in defense and transport security applications.

References

Bosyi, D. O., Sablin, O. I., & Potapchuk, I. Yu. (2024). Increasing the security of critical transport infrastructure facilities based on geospatial analysis of acoustic signatures of aerial threats. Bulletin of Vinnytsia Polytechnic Institute, 4, 147-156. DOI: https://doi.org/10.31649/1997-9266-2024-175-4-147-156 (in Ukrainian)

Danyk, Yu. H., & Buhaiov, M. V. (2015). Analysis of the efficiency of detecting tactical unmanned aerial vehicles by passive and active observation means. Problems of Development, Testing, and Operation of Complex Information Systems, 10, 5-20. (in Ukrainian)

Kartashov, V. M., Pososhenko, V. O., Kapusta, A. I., Rybnikov, M. V., & Pershyn, Ye. V. (2022). Features of detecting and observing groups of unmanned aerial vehicles. Radiotekhnika, 211, 84-92. https://doi.org/10.30837/rt.2022.4.211.06 (in Ukrainian)

Lepikh, Ya. I., Santonii, V. I., Budiianska, L. M., Ivanchenko, I. O., & Yanko, V. V. (2019). Optyko-elektronni systemy blyzhnoi lokatsii. Odesa: Odesa National University named after I. I. Mechnikov. (in Ukrainian)

Bosyi, D. O., Sablin, O. I., & Potapchuk, I. Yu. (2025). Systema monitorynhu tekhnichnykh parametriv kon-taktnoi merezhi elektryfikovanykh zaliznyts z identyfi-katsiieiu povitrianykh zahroz (Patent № 159173, Ukraine). Ukrainian State University of Science and Technologies. (in Ukrainian)

Sokolskyi, S. O., & Movchaniuk, A. V. (2021). Overview of Detection and Localization Methods of Small Unmanned Aerial Vehicles. Visnyk NTUU KPI Seriia. Radiotekhnika Radioaparatobuduvannia, 87, 46-55. https://doi.org/10.20535/RADAP.2021.87.46-55 (in Ukrainian)

Surma, S., & Lukasik, J. (2013). Contact network monitoring. Electrification of Transport, 5, 113-118. (in Russian)

Sukhodolia, O. M., Kharazishvili, Yu. M., & Riabtsev, H. L. (2023). Enerhetychna bezpeka Ukrainy: perspektyvna model upravlinnia ryzykamy. Kyiv: NISS. DOI: https://doi.org/10.53679/niss-book.2023.01 (in Ukrainian)

Tykhonov, V. A., Kartashov, V. M., Oleinikov, V. M., Leonidov, V. I., Timoshenko, L. P., Seleznev, I. S., & Rybnikov, М. V. (2020). Detection-Recognition of Unmanned Aerial Vehicles using the Composed Auto-Regression Model of their Acoustic Radiation. Visnyk NTUU KPI Seriia. Radiotekhnika Radioaparato-buduvannia, 81, 38-46. DOI: https://doi.org/10.20535/radap.2020.81.38-46 (in Russian)

Abishek, A. S. (2023). Audio Classification Deep Learning. GitHub. Retrieved from: https://github.com/abishek-as/Audio-Classification-Deep-Learning (in English)

Al-Emadi, S., Al-Ali, A., & Al-Ali, A. (2021). Audio-Based Drone Detection and Identification Using Deep Learning Techniques with Dataset Enhancement through Generative Adversarial Networks. Sensors, 21(15), 4953. DOI: https://doi.org/10.3390/s21154953 (in English)

Anti-UAV Defence System (AUDS). (2018). Blighter. Retrieved from: https://blighter.com/anti-uav-defence-system-auds-unveiled-by-trio-of-british-technology-companies/ (in English)

Bondarenko, I., Lukoševičius, V., Keršys, R., & Neduzha, L. (2024). Innovative trends in railway condition mon-itoring. Transportation Research Procedia, 77, 10-17. DOI: https://doi.org/10.1016/j.trpro.2024.01.002 (in English)

Bondarenko, I., Lukoševičius, V., & Neduzha, L. (2024). Novel ‘Closed’-system approach for monitoring the technical condition of railway tracks. Sustainability, 16(8), 3180. DOI: https://doi.org/10.3390/su16083180 (in English)

Bosyi, D., Sablin, O., Khomenko, I., Kosariev, Ye., Kebal, I., & Myamlin, S. (2017). Intelligent Technologies for Efficient Power Supply in Transport Systems. Transport Problems, 12(SE), 57-71. DOI: https://doi.org/10.20858/tp.2017.12.se.5 (in English)

Bosyi, D., Sablin, O., & Potapchuk, I. (2024). Decentralized WAMS for Railway Overhead Lines with Audio-Based Drone Detection. 2024 IEEE 5th KhPI Week on Advanced Technology (KhPIWeek). (рр. 1-6), Kharkiv, Ukraine. DOI: https://doi.org/10.1109/khpiweek61434.2024.10877981 (in English)

Kartashov, V. M., Oleynikov, V. N., Sheiko, S. A., Babkin, S. I., Korytsev, I. V., Zubkov, O. V., & Anokhin, M. A. (2018). Information characteristics of sound radiation of small unmanned aerial vehicles. Telecommunica-tions and Radio Engineering, 77(10), 915-924. DOI: https://doi.org/10.1615/telecomradeng.v77.i10.70 (in English)

Kurhan, D., Kovalchuk, V., Markul, R., & Kovalskyi, D. (2025). Development of Devices for Long-Term Railway Track Condition Monitoring: Review of Sensor Varieties. Acta Polytechnica Hungarica, 22(4), 65-82. DOI: https://doi.org/10.12700/aph.22.4.2025.4.5 (in English)

Mizan, M., Karwowski, K., & Karkosiński, D. (2013). Monitoring odbieraków prądu w warunkach eksploatacyjnych na linii kolejowej. Przegląd Elektrotechniczny, 12, 154-160. (in Poland)

Piczak, K. J. (2015). Environmental sound classification with convolutional neural networks. 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP). (рр. 1-6.), Boston, USA. DOI: https://doi.org/10.1109/mlsp.2015.7324337 (in English)

Revolutionising Railway Decisions. (2018). Sensonic GmbH. Retrieved from: https://www.sensonic.com/ (in English)

Ribbing, C. G. (2013). Controlling thermal radiation from surfaces. In: Optical Thin Films and Coatings. 357-390. DOI: https://doi.org/10.1533/9780857097316.2.357 (in English)

Sicat CMS. (2018). Catenary monitoring system for overhead contact line systems. Siemens Mobility GmbH. Retrieved from: https://assets.new.siemens.com/siemens/assets/api/uuid:fc73a788-70d4-4cba-82ba-41208bcef48b/siemens-sicat-cms-pi-en.pdf (in English)

Singha, S., & Aydin, B. (2021). Automated drone detection using YOLOv4. Drones, 5, 95. DOI: https://doi.org/10.3390/drones5030095 (in English)

Sukharevskyi, O. (2015). Electromagnetic Wave Scattering by Aerial and Ground Radar Objects. Boca Raton: CRC Press. DOI: https://doi.org/10.1201/b17239 (in English)

(2016). The Power of Change: Innovation for Development and Deployment of Increasingly Clean Electric Power Technologies. Washington, DC : The National Academies Press. DOI: https://doi.org/10.17226/21712 (in English)

Yaran, W. (2023, July 11). Electrical interface of MEMS microphone introduction. Infineon Knowledge Base Articles. Retrieved from: https://community.infineon.com/t5/Knowledge-Base-Articles/Electrical-interface-of-MEMS-microphone-introduction/ta-p/453658# (in English)

Zhang, X., & Kusrini, K. (2021). Autonomous long-range drone detection system for critical infrastructure safe-ty. Multimedia Tools and Applications, 80(15), 23723-23743. DOI: https://doi.org/10.1007/s11042-020-10231-x (in English)