Flight operation anomaly detection based on one-class SVM

Yizhen Jia; Haiyan Chen; Ligang Yuan; Xiaye Hou

doi:10.1117/12.2619663

22 December 2021 Flight operation anomaly detection based on one-class SVM

Yizhen Jia, Haiyan Chen, Ligang Yuan, Xiaye Hou

Proceedings Volume 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021); 120583A (2021) https://doi.org/10.1117/12.2619663
Event: 5th International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 2021, Chongqing, China

Abstract

Safety is the primary prerequisite of air transport. It is important to detect flight operations anomaly through weather, flight, air traffic and other data in advance. In this paper, we propose a One-class SVM-based anomaly detection method for flight operation. We first construct a flight operation dataset based on the factors of abnormal flight operation, and apply data pre-processing methods to standardize the dataset. Then, a flight operation anomaly detection model based on One-class SVM is proposed to predict the risk. The experimental results show that, compared with LOF and DBSCAN, the proposed model has better performance in Precision, Recall and F1 score, which fully demonstrates the effectiveness and superiority of our model.

Citation Download Citation

Yizhen Jia, Haiyan Chen, Ligang Yuan, and Xiaye Hou "Flight operation anomaly detection based on one-class SVM", Proc. SPIE 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 120583A (22 December 2021); https://doi.org/10.1117/12.2619663

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available