Entropy Approach to Detection of Anomalies in UAV Trajectories
DOI:
https://doi.org/10.47839/ijc.25.2.4654Keywords:
dynamic network topology, UAV trajectory analysis, data-driven modelling, anomaly detection, Kozachenko–Leonenko entropy (KLE), combined entropy statistic, trajectory hyperparameter optimizationAbstract
The paper presents a comprehensive entropy-based approach for anomaly detection in the trajectories of agents within a multi-component dynamic system of unmanned aerial vehicles (UAVs). The proposed mathematical model represents the movement of agents using a directed graph that takes into account kinematic parameters (spatial coordinates, velocity, and acceleration), stochastic factors, and topology of interactions. Potential anomalies are detected using combined entropy statistics that integrate local and structural entropy estimated via the Kozachenko–Leonenko method. Model hyperparameters are then optimized by stratified cross-validation using modern machine learning algorithms. Experimental evaluation on the SynDrone-Swarm dataset shows that ML-based calibration substantially improves detection quality, increasing ROC-AUC from 0.748 to 0.915 and PR-AUC from 0.768 to 0.924, while reducing false positives and improving temporal and spatial localization of anomalous events. The practical significance of this work lies in improving the efficiency of monitoring and managing UAV groups by enabling real-time detection of complex and latent anomalies.
References
D. Symonov, “Algorithm for determining the optimal flow in Supply Chains, considering multi-criteria conditions and stochastic processes,” Bulletin of Taras Shevchenko National University of Kyiv. Physical and Mathematical Sciences, vol. 2, pp. 109-116, 2021. https://doi.org/10.17721/1812-5409.2021/2.15.
A. Ghasemi, A. Ghaffari, N. Derakhshanfard, N. Ibrahimoglu, and A. Pakmehr, “Anomaly detection in unmanned aerial vehicles flight data: A survey,” Ad Hoc Networks, vol. 178, p. 103989, 2025. https://doi.org/10.1016/j.adhoc.2025.103989.
U. Pisarenko, C. Melkumyan, I. Varava, A. Koval, and N. Chumakova, “About the organization of regional situational centers of the intellectual system ‘Control_TEP’ with the use of UAVS,” Stuc. intelekt., vol. 27, issue 1, pp. 275-287, 2022. https://doi.org/10.15407/jai2022.01.275.
V. Bell, D. Rengasamy, B. Rothwell, and G.P. Figueredo, “Anomaly detection for unmanned aerial vehicle sensor data using a stacked recurrent autoencoder method with dynamic thresholding,” arXiv preprint, arXiv:2203.04734, 2022. https://doi.org/10.4271/01-15-02-0017.
S. G., U. Verma, M.M.M. Pai, et al., “Contextual information based anomaly detection for multi-scene aerial videos,” Scientific Reports, vol. 15, p. 25805, 2025. https://doi.org/10.1038/s41598-025-07486-5.
A. Palamas, N. Souli, T. Panayiotou, P.S. Kolios, and G. Ellinas, “A multi-task learning framework for drone state identification and trajectory prediction,” Proceedings of the 2023 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT), pp. 676-683, 2023. https://doi.org/10.1109/DCOSS-IoT58021.2023.00107.
S. Chakri, N. Mouhni, and F. Ennaama, “Exploring the frontiers of trajectory outlier detection: an in-depth review and comparative analysis,” International Journal of Electrical and Computer Engineering (IJECE), 2024. https://doi.org/10.11591/ijece.v14i5.pp5984-5997.
K. Lee, “Advancements in information-theoretic methods for data analytics,” Entropy, vol. 27, issue 7, p. 708, 2025. https://doi.org/10.3390/e27070708.
N. Murugesan, I. Cho, and C. Tortora, “Benchmarking in cluster analysis: A study on spectral clustering, DBSCAN, and K-Means,” in: T. Chadjipadelis, B. Lausen, A. Markos, T.R. Lee, A. Montanari, R. Nugent (Eds.), Data Analysis and Rationality in a Complex World. IFCS 2019. Studies in Classification, Data Analysis, and Knowledge Organization, Springer, Cham, 2021, pp. 175-185. https://doi.org/10.1007/978-3-030-60104-1_20.
D.T. Lan and S. Yoon, “Trajectory clustering-based anomaly detection in indoor human movement,” Sensors (Basel, Switzerland), vol. 23, no. 6, p. 3318, 2023. https://doi.org/10.3390/s23063318.
B. Lindemann, B. Maschler, N. Sahlab, and M. Weyrich, “A survey on anomaly detection for technical systems using LSTM networks,” Computers in Industry, vol. 131, p. 103498, 2021. https://doi.org/10.1016/j.compind.2021.103498.
I. Bozcan and E. Kayacan, “UAV-AdNet: Unsupervised anomaly detection using deep neural networks for aerial surveillance,” Proceedings of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1158-1164, 2020. https://doi.org/10.1109/IROS45743.2020.9341790.
T. Wang, M. Jiao, and X. Wang, “Link prediction in complex networks using recursive feature elimination and stacking ensemble learning,” Entropy, vol. 24, no. 8, p. 1124, 2022. https://doi.org/10.3390/e24081124.
K. Zhang, W. Huang, B. Zhang, J. Xu, and X. Yang, “Robust outlier detection method based on local entropy and global density,” Expert Systems with Applications, vol. 290, p. 128424, 2023. https://doi.org/10.1016/j.eswa.2025.128424.
R. Xian, X. Wang, and D. Manocha, “MITFAS: Mutual information based temporal feature alignment and sampling for aerial video action recognition,” Proceedings of the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 2024, pp. 6611-6620. https://doi.org/10.1109/WACV57701.2024.00649.
B. Pérez, M. Resino, T. Seco, F. García, and A. Al-Kaff, “Innovative approaches to traffic anomaly detection and classification using AI,” Applied Sciences, vol. 15, no. 10, p. 5520, 2025. https://doi.org/10.3390/app15105520.
L. Devroye and L. Györfi, “On the consistency of the Kozachenko-Leonenko entropy estimate,” IEEE Transactions on Information Theory, vol. 68, no. 2, pp. 1178–1185, 2022. https://doi.org/10.1109/TIT.2021.3127938.
V. Kovtun, T.A. Altameem, M. Al-Maitah, and W.M. Kempa, “Entropy-metric estimation of the small data models with stochastic parameters,” Heliyon, vol. 10, no. 2, 2024. https://doi.org/10.1016/j.heliyon.2024.e24708.
B. Wang, N.N. Xiong, and F. Xin, “Advances in information entropy,” Advances in Mathematical Physics, 2023. https://doi.org/10.1155/2023/9834568.
W. Qu, J. Li, W. Song, X. Li, Y. Zhao, H. Dong, Y. Wang, Q. Zhao, and Y. Qi, “Entropy-weight-method-based integrated models for short-term intersection traffic flow prediction,” Entropy, vol. 24, no. 7, p. 849, 2022. https://doi.org/10.3390/e24070849.
D. Żelasko, “Cost-aware network traffic anomaly detection with histogram-based gradient boosting,” Applied Sciences; vol. 16, issue 7, 3496, 2026. https://doi.org/10.3390/app16073496.
M. Nouman, N. Cordeschi and A. Fascista, “Machine learning-based histogram boosting approach for attack detection in IoT networks,” Proceedings of the 2025 16th IFIP Wireless and Mobile Networking Conference (WMNC), Leuven, Belgium, 2025, pp. 53-57, https://doi.org/10.23919/WMNC67099.2025.11299281.
Shilpa and K. Jain, “Malware detection in android devices using histogram-based gradient boosting,” Proceedings of the 2024 IEEE 4th International Conference on ICT in Business Industry & Government (ICTBIG), Indore, India, 2024, pp. 1-7, https://doi.org/10.1109/ICTBIG64922.2024.10911600.
U. Zbezhkhovska, V. Slobodyanuk, O. Koval, K. Vasiuta, D. Kalinovskyi, and O. Yasynskyi, “Deep learning for classifying chaotic signals transformed by advanced techniques,” International Journal of Computing, vol. 24, issue 4, pp. 771-779, 2026. https://doi.org/10.47839/ijc.24.4.4343.
M. M. Bapat, C. H. Patil and S. M. Mali. Database Development and Recognition of Facial Expression using Deep Learning. International Journal of Computing, vol. 23, issue 4, pp. 606-617, 2024. https://doi.org/10.47839/ijc.23.4.3760.
M. M. Unal, “SynDrone-Swarm v1.0.0,” 2026. [Online]. Available at: https://github.com/MehmetUnall/SynDrone-Swarm/releases/tag/v1.0.0.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• 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.
• 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.
• 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.
