Application of Non-Negative Tensor Factorization for Airport Flight Delay Pattern Recognition

Han Zhong,Geqi Qi,Xiaochen Hua,Wei Guan

doi:10.1109/access.2019.2955735

Han Zhong, Geqi Qi + Show 2 more

Open Access

https://doi.org/10.1109/access.2019.2955735

Copy DOI

Abstract

With the rapid development of civil aviation transportation in China, huge demand growth has broken the balance between supply and demand, resulting in airspace congestion and increasing flight delays. The delays of large airports have been increasing year by year, which has seriously affected the air travel experience of passengers. Obtaining their flight delay patterns can help identify defects in flight scheduling and airspace utilization. The investigation based on the actual flight operation data of Tianjin Binhai International Airport (TSN) is conducted, in order to capture the relationship and impact between the factors such as traffic flow direction, airline attributes and hourly average delay distribution. Furthermore, Non-negative Tensor Factorization (NTF) is applied to pattern recognition by introducing CP (CANDECOMP/PARAFAC) decomposition and Block Coordinate Descent (BCD) algorithm for selected data set. Numerical experiments show that the designed method has good performance in terms of computation speed and solution quality. Recognition results indicate the significant pattern characteristics of the Tianjin airport delay are extracted, which can provide some new perspectives for air traffic management unit to alleviate airspace congestion and improve service quality.

Highlights

Delays are one of the biggest challenges facing by transportation systems
Passenger flight delays occur daily at airports around the world, resulting in air traffic chaos, billions of dollars in economic losses for airlines, and unpleasant travel for millions of people [2], [3]. In this case, understanding the reasons for the flight delay event can guide the improvement of the air transport system, improve the tactical and operational decisions of the air traffic management department, airport and airline management personnel, and be able to promptly alert passengers so that they have sufficient time to reschedule travel plans [4], [5]
With the increasing interest in the field of artificial intelligence represented by machine learning, pattern recognition as a classic data mining and machine learning tool is widely used in the analysis of various complex systems

Summary

Introduction

Delays are one of the biggest challenges facing by transportation systems. In commercial aviation, delays are usually defined by the difference between the scheduled and actual time of departure or arrival [1]. Built on the existing studies, this paper will apply NTF to extract their respective flight delay patterns from the actual departure and arrival flight data of Tianjin Binhai International Airport (TSN) in order to capture the potential relationship and impact between the factors such as traffic flow direction, airline attributes and hourly average delay distribution.

Results

Conclusion