Detection and Identification of Aircraft by Acoustic Recognition Using Deep Learning

DOI

10.2991/978-94-6463-866-0_2How to use a DOI?

Keywords

Acoustics; Aircraft classification; Deep Learning techniques; Convolution Neural Network; Recurrent Neural Network

Abstract

Low-flying aircraft pose significant challenges to radar systems, making them impossible to detect. To address these risks, it is critical to detect and identify such aircraft in real time. This work presents an approach for aircraft detection and classification using acoustic signatures. The acoustic data, captured from low-altitude aircraft, was processed and analysed to identify the unique acoustic signatures associated with various types of aircraft. For the classification of the aircraft, deep learning techniques were employed, comparing the results of Convolutional Neural Networks (CNN) with corresponding results from Recurrent Neural Networks (RNN). The project was implemented using MATLAB and Python. The CNN-based model demonstrated superior performance, achieving a classification accuracy of 100% for known aircraft types, while the RNN model achieved an accuracy of 96.4%. It was noted that the system’s performance yielded a maximum accuracy of 65% when unknown files of classes were fed into the algorithm, and the corresponding tabulations were represented as tendency charts.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - J. Gayathri
AU  - Arun Nayak
AU  - A. Saravanakumar
AU  - K. Senthilkumar
PY  - 2025
DA  - 2025/10/31
TI  - Detection and Identification of Aircraft by Acoustic Recognition Using Deep Learning
BT  - Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
PB  - Atlantis Press
SP  - 4
EP  - 14
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-866-0_2
DO  - 10.2991/978-94-6463-866-0_2
ID  - Gayathri2025
ER  -