Hovering recognition by ADS-B data mining
Lei Bian, Yu Liu, Yi-Xuan Zhan, Hongwu Tang, M. H. Bo, Linfeng Zhang, Kun Luan, Xinyan Yin, Jingde Ding · 2020 IEEE 2nd International Conference on Civil Aviation Safety and Information Technology (ICCASIT · 2020
Hover often occurs during flight. It is easy to distinguish whether the aircraft has a hovering phenomenon by observing trajectory curve by naked eyes, but it is extremely challenging if we want to recognize hover phenomenon automatically and accurately through algorithms. This paper presents a method to identify whether an aircraft hovers and hovering circles based on ADS-B data. It can not only accurately identify whether an aircraft has a hovering phenomenon but also calculate the number of hovering circles around a certain point and support hovering time and hovering location, including longitude and latitude. We use millions of flights data of ADS-B to evaluate our algorithm offline, deploy the solution on Umetrip application, as well as the Air China Control system, which is a collaborative product between Umetrip and Air China. Extensive evaluation shows that the algorithm we propose is significantly better than algorithm before and is ahead of the solutions for aircraft hovering recognition provided in the industry as well.