ORIGINAL RESEARCH article
Front. Aerosp. Eng.
Sec. Intelligent Aerospace Systems
Anomaly Detection Method of ADS-B Air Traffic Control Data Based on Fast Fourier Transform and Convolutional Neural Network
Provisionally accepted
- 1Anhui Technical College of Industry and Economy, Hefei, China
- 2College of Computer Science, Sichuan University, Chengdu, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Abstract—The current ADS-B air traffic control data anomaly detection faces significant challenges, such as frequency deviation and abnormal data injection, which can compromise the reliable functioning of the air traffic management system. In response to these issues, this paper proposes a deep learning-based method for detecting anomalies in ADS-B air traffic control data. This approach employs the Fast Fourier Transform (FFT) algorithm to correct the frequency offset in ADS-B data, ensuring data accuracy. A sliding window approach is used to expand the feature dimension, and the expanded features are fed into a Convolutional Neural Network. Following convolution, pooling, and processing through a Multi-Layer Perceptron, the Softmax classifier outputs the anomaly detection results. Experimental results demonstrate that this method can effectively identify various types of anomalies in ADS-B air traffic control data, such as speed deviations. The AUC value for anomaly detection exceeds 0.9, enabling timely warnings of potential safety risks, enhancing aviation safety, and safeguarding public lives and property.
Keywords: ADS-B anomaly detection, FFT, Convolutional Neural Network, Aviation safety, data reliability
Received: 14 Aug 2025; Accepted: 27 Oct 2025.
Copyright: © 2025 She, Jia and Zhu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Ruchun Jia, jiaruchun@stu.scu.edu.cn
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.