Skip to main content

Research Repository

Advanced Search

Unsupervised anomaly detection in unmanned aerial vehicles

Khan, Samir; Liew, Chun Fui; Yairi, Takehisa; McWilliam, Richard

Authors

Samir Khan

Chun Fui Liew

Takehisa Yairi

Richard McWilliam



Abstract

Having a real-time anomaly detection solution indicates a continuous stream of operational and labelled data that must satisfy a number of resource and latency requirements. Traditional solutions to the problem rely heavily on well-defined features and prior supervised knowledge, where most techniques refer to hand-crafted rules derived from known conditions. While successful in controlled situations, these rules assume that good data is available for them to detect anomalies; indicating that these rules will fail to generalise beyond known scenarios. To investigate these issues, current literature is examined for solutions that can be used to detect known and unknown anomalous instances whilst functioning as an out-of-the-box approach for efficient decision-making. The applicability of the isolation forest is discussed for engineering applications using the Aero-Propulsion System Simulation dataset as a benchmark where it is shown to outperform other unsupervised distance-based approaches. In addition, the authors have carried out real-time experiments on an unmanned aerial vehicle to highlight further applications of the method. Finally, some conclusions are drawn with respect to its simplicity and robustness in handling diagnostic problems.

Citation

Khan, S., Liew, C. F., Yairi, T., & McWilliam, R. (2019). Unsupervised anomaly detection in unmanned aerial vehicles. Applied Soft Computing, 83, Article 105650. https://doi.org/10.1016/j.asoc.2019.105650

Journal Article Type Article
Online Publication Date Aug 1, 2019
Publication Date Oct 1, 2019
Deposit Date Jul 26, 2019
Journal Applied Soft Computing
Print ISSN 1568-4946
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 83
Article Number 105650
DOI https://doi.org/10.1016/j.asoc.2019.105650
Public URL https://durham-repository.worktribe.com/output/1296525


You might also like



Downloadable Citations