Drones or unmanned aerial vehicles have become a new option for multiple tasks including delivery, photograph, etc. However, the small size and flight ability of drones make it easier to break through any barriers and intrude important facilities. With an increasing safety concern of drone incursions, the research for an effective drone detection and identification approach has drawn a lot of attention in recent years. Among existing methods, passive radio frequency sensing is both reliable and cost-effective. However, previous studies are evaluating both machine learning and statistical methods on private datasets under different settings. To make a fair comparison, we evaluate six machine learning models on an open drone dataset for RF-based drone detection in this paper. The results demonstrate that XGBoost achieves the state-of-the-art results on this pioneering dataset.
RF-based Drone Detection using Machine Learning
01.01.2021
351929 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Drone failure prediction system using machine learning
Europäisches Patentamt | 2022
|Drone Object Detection Using Deep Learning Algorithms
IEEE | 2021
|