Research on drone recognition based on their acoustic emission using fully connected neural networks
DOI:
https://doi.org/10.30837/rt.2025.3.222.12Keywords:
drone, recognition, fully connected neural network, cepstral coefficients, acoustic radiation, architectureAbstract
The relevance of the research on recognizing the self-acoustic emissions of drones using fully connected neural networks and cepstral coefficients has been substantiated. A dataset of acoustic recordings has been created, including self-emissions of various drone models, background sounds, and seven types of sound sources with spectral characteristics similar to drone acoustic emissions. The optimal number of cepstral coefficients has been identified for further recognition by fully connected neural networks in terms of maximizing the probability of correct recognition and minimizing misclassification. The optimal neural network architecture has been determined to ensure the highest probability of correct recognition. The requirements for a microprocessor-based hardware platform for recognizing drone self-acoustic emissions have been calculated.
References
Agapiou A. Drones in Construction: A Comparative International Review of the Legal and Regulatory Landscape // Management Procurement and Law. 2020. Vol. 174, No.3. P.1–8. DOI:10.1680/jmapl.19.00041
Pyrgies J. The UAVs threat to airport security: risk analysis and mitigation // Journal of Airline and Airport Management. 2019. Terrassa. Vol. 9, Iss.2. P.63–96.
Mowafaq SA, Muhyeeddin A, Al-Batah MS. AI in the Sky: Developing Real-Time UAV Recognition Systems to Enhance Military Security // Data and Metadata. Nazarre. 2024. Vol. 3. P.1–19. https://doi.org/10.56294/dm2024.417
Aouladhadj D., Kpre E., Deniau V., Kharchouf A., Gransart C., Gaquière C. Drone Detection andTracking Us-ing RF IdentificationSignals // Sensors. Basel. 2023. Vol. 23. P.1–24. https://doi.org/10.3390/s23177650
Yousaf J., Zia H., Alhalabi M., Yaghi M., Basmaji T., Shehhi E.A., Gad A., Alkhedher M., Ghazal M. Drone and Controller Detection and Localization: Trends and Challenges// Appl. Sci. Basel. 2022. Vol.12, Iss.24, P.1–22. https://doi.org/10.3390/app122412612
Zubkov O.V., Sheiko S.O., Oleynikov V.M., Kartashov V.M., Babkin S.I. Investigation Of The Yolov5 Algorithm Efficiency For Drone Recognization // Telecommunications and Radio Engineering. Danbury. 2024. Vol.83, Iss.1. P. 65–79. DOI: 10.1615/TelecomRadEng.2023048987
Oleynikov V., Zubkov O., Kartashov V., Korytsev I., Babkin S., Sheiko S. Investigation of the efficiency of detection and recognition of small-sized unmanned aerial vehicles by their acoustic radiation. Radiotekhnika. 2018. Vol.4, No.195. P.209–217. https://doi.org/10.30837/rt.2018.4.195.21
Paszkowski W., Gola A., Świć A. Acoustic-Based Drone Detection Using Neural Networks – A Comprehen-sive Analysis// Advances in Science and Technology Research Journal. Lublin. 2024. Vol.18, Iss.1. P.36–47. https://doi.org/10.12913/22998624/175863
Tejera-Berengue D., Zhu-Zhou F., Utrilla-Manso M., Gil-Pita R., Rosa-Zurera M. Analysisof Distance and EnvironmentalImpact on UAV Acoustic Detection // Electronics. Basel. 2024. Vol. 13.
https://doi.org/10.3390/electronics13030643
Othman E., Cibilić I., Poslončec-Petrić V., Saadallah D. Investigating Noise Mapping in Cities to Associate Noise Levels with Sources of Noise Using Crowdsourcing Applications// Urban Sci. 2024. Vol.8, Iss.1. https://doi.org/10.3390/urbansci8010013
Dombrovschi M., Deaconu M., Cristea L., Frigioescu T.F., Cican G., Badea ., Totu G. Acoustic Analysis of a Hybrid Propulsion System for Drone Applications// Acoustics. Basel. 2024. Vol. 6, Iss.3. P. 698–712. https://doi.org/10.3390/acoustics6030038
Islam M., Haque M., Islam S., Mia Z.A., Rahman M. DCNN-LSTM Based Audio ClassificationCombining Multiple Feature Engineeringand Data Augmentation Techniques Intelligent // Computing & Optimization Springer. Cham. 2021. Vol. 371. P.227–236. DOI:10.1007/978-3-030-93247-3_2 3
Wei N., Gu J.X., Gu F., Chen Z., Li G., Wang T., Ball A.D. An Investigation into the Acoustic Emissions of Internal Combustion Engines with Modelling and Wavelet Package Analysis for Monitoring Lubrication Conditions // Energies. Basel. 2019. Vol.12, Iss.4. P. 1–14. https://doi.org/10.3390/en12040640
Zrar K.A., Abdulbasit K.A. Mel Frequency Cepstral Coefficient and its Applications: A Review // IEEE Ac-cess. Piscataway. 2022. Vol.10. P.122136–122158. DOI:10.1109/ACCESS.2022.3223444
Sithara A., Abraham T., Mathew D. Study of MFCC and IHC Feature Extraction Methods With Probabilistic Acoustic Models for Speaker Biometric Applications // Procedia Computer Science. Amsterdam. 2018. Vol. 143.P. 267–276. DOI:10.1016/j.procs.2018.10.395
Fazal M.A., Baig M.A., Manj W.A., Faraz Z., Mallah G.A. Implementation of Deep Learning for Acoustic Classification // Journal of Xidian University. Christchurch. 2023. Vol. 17, Iss. 8. P.1653–1673. DOI:10.37896/jxu17.8/138
Pham L., Ngo D., Salovic D.c, Jalali A., Schindler A., Nguyen P. X., Tran K., Vu H. Lightweight deep neural networks for acoustic scene classification and an effective visualization for presenting sound scene contexts // Applied Acoustics. Basel. 2023. Vol. 211. P.723–731. DOI:10.1016/j.apacoust.2023.109489
Jung H.K., Choi G.S. Improved YOLOv5: Efficient Object Detection Using Drone Images under Various Conditions // Appl. Sci. Basel. 2022. Vol. 12. Р.1–16. DOI: 10.3390/app12147255
Pang B., Nijkamp E., Nian Y.W. Deep Learning With TensorFlow: A Review // Journal of Educational and Behavioral Statistics. 2019. Vol. 45, Iss. 2. P.415–421. https://doi.org/10.3102/107699861987276
Soujanya B., Sitamahalakshmi T. Optimization with ADAM and RMSprop in Convolution neural Network (CNN): A Case study for Telugu Handwritten Characters // International Journal of Emerging Trends in Engineering Research. Pawan. 2020. Vol. 8. No. 9. P.5116–5121.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
