Entropy Approach to Detection of Anomalies in UAV Trajectories
International Journal of Computing · 30.06.2026 · 284-294
DOI: 10.47839/ijc.25.2.4654 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computing, online erschienen am 30.06.2026. Verfasst von Yaroslav Kornaga und 4 weiteren Autor:innen.
Abstract (Originalsprache)
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.
Zitieren
APA
Kornaga, Y., Symonov, D., Pisarenko, J., Mamedova, K., & Koval, O. (2026). Entropy Approach to Detection of Anomalies in UAV Trajectories. International Journal of Computing, 284-294. https://doi.org/10.47839/ijc.25.2.4654
Vancouver
Kornaga Y, Symonov D, Pisarenko J, Mamedova K, Koval O. Entropy Approach to Detection of Anomalies in UAV Trajectories. International Journal of Computing. 2026:284-294. doi:10.47839/ijc.25.2.4654
BibTeX
@article{Kornaga2026,
author = {Kornaga, Yaroslav and Symonov, Denys and Pisarenko, Julia and Mamedova, Kateryna and Koval, Olexandr},
title = {Entropy Approach to Detection of Anomalies in UAV Trajectories},
journal = {International Journal of Computing},
year = {2026},
pages = {284--294},
doi = {10.47839/ijc.25.2.4654}
}
EUVIMED