Performance evaluation of unmanned aerial vehicle conflict detection algorithm based on machine learning
Data and Metadata · 15.05.2026 · 5 · 802
DOI: 10.56294/dm2026802 ↗Kurz gefasst
Fachartikel in der Zeitschrift Data and Metadata, online erschienen am 15.05.2026. Verfasst von Wei Zhang. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
The increasing use of UAVs in surveillance, logistics, agriculture, and disaster response has led to higher air traffic and raised concerns about safe flight operations and collision avoidance. Managing multiple UAVs in shared airspace requires efficient conflict detection methods, as traditional approaches struggle with complex flight patterns, uncertain data, and prediction needs.
Objective
This study presents a machine learning framework for unmanned aerial vehicle conflict detection, which uses Adaptive Kookaburra Optimized-Light Gradient Boosting Machine (AdapKO-LightGBM) as its foundational technology.
Method
To detect dynamic flight patterns and temporal conflict patterns, the research used the UAV Conflict Detection Dataset, which includes position, velocity, altitude, heading angle, and inter-UAV distance. The data was preprocessed using min-max normalization and Kalman filtering, and features were extracted using the Short-Time Fourier Transform (STFT), which converted trajectory signals into time-frequency representations.
Result
The proposed model was evaluated through classification accuracy tests, which measured its ability to detect UAV conflicts and non-conflicts through experiments that used a Python implementation. AdapKO-LightGBM reached its highest accuracy of 96,75%, which [w1.1][w2.1]bettered the results of NNPw/Fine-Tuned MobileNetV2 and MobileNetV3 Small. [w3.1][w4.1]
Conclusion
The model develops reliable UAV conflict detection abilities, which improve intelligent airspace management capabilities according to the research findings.
Zitieren
APA
Zhang, W. (2026). Performance evaluation of unmanned aerial vehicle conflict detection algorithm based on machine learning. Data and Metadata, 5, 802. https://doi.org/10.56294/dm2026802
Vancouver
Zhang W. Performance evaluation of unmanned aerial vehicle conflict detection algorithm based on machine learning. Data and Metadata. 2026;5:802. doi:10.56294/dm2026802
BibTeX
@article{Zhang2026,
author = {Zhang, Wei},
title = {Performance evaluation of unmanned aerial vehicle conflict detection algorithm based on machine learning},
journal = {Data and Metadata},
year = {2026},
volume = {5},
pages = {802},
doi = {10.56294/dm2026802}
}
EUVIMED