Characterizing Flight Delay Profiles with a Tensor Factorization Framework
Characterizing Flight Delay Profiles with a Tensor Factorization Framework作者机构：School of Electronic and Information EngineeringBeihang UniversityBeijing 100191China National Engineering Laboratory for Comprehensive Transportation Big Data Application TechnologyBeijing 100191China Department of Civil Engineering and Applied MechanicsMcGill UniversityMontrealQC H3A 0C3Canada
出 版 物：《Engineering》 (工程（英文）)
年 卷 期：2021年第7卷第4期
页 面：465-472页
核心收录：
学科分类：08[工学] 0825[工学-航空宇航科学与技术]
基 金：This paper is supported by the National Key Research and Development Program of China(2019YFF0301400) the National Natural Science Foundation of China(61671031,61722102,and 61961146005)
主 题：Air traffic management Flight delay Latent class model Tensor decomposition
摘 要：In air traffic and airport management,experience gained from past operations is crucial in designing appropriate strategies when facing a new ***,this paper uses massive spatiotemporal flight data to identify similar traffic and delay patterns,which become critical for gaining a better understanding of the aviation system and relevant ***,as the datasets imply complex dependence and higher-order interactions between space and time,retrieving significant features and patterns can be very *** this paper,we propose a probabilistic framework for highdimensional historical flight *** apply a latent class model and demonstrate the effectiveness of this framework using air traffic data from 224 airports in China during 2014–*** find that profiles of each dimension can be clearly divided into various patterns representing different regular *** prove the effectiveness of these patterns,we then create an estimation model that provides preliminary judgment on the airport delay *** outcomes of this study can help airport operators and air traffic managers better understand air traffic and delay patterns according to the experience gained from historical scenarios.
维普期刊数据库
同方期刊数据库