A Flight Delay Early Warning Method Based on Evolutionary Undersampling Ensemble Learning

Abstract

The invention discloses a flight delay early warning method based on evolutionary under-sampling integrated learning, which belongs to the technical field of airport flight delay early warning. The specific steps of this method are as follows: First, discretize the target attributes of the flight delay measured data set and remove noise points to obtain a normalized data set; then, use the evolutionary under-sampling method to obtain a majority of the unbalanced data set class conduct T subsampled, constructed T A balanced training set; then, use the grid search technique to optimize the parameters of the classification regression decision tree classifier on each balanced training set and generate a classifier; finally, determine an optimal integration method to form these classifiers An integrated system, EUS‑Bag, is a flight delay early warning model. The early warning model can provide decision-making basis for the air traffic control department to conduct reasonable air traffic scheduling. The method has a high degree of intelligence, and can effectively improve the accuracy and reliability of the early warning of flight delays at airports.

Description

technical field [0001] The invention relates to a flight delay early warning method based on evolutionary under-sampling integrated learning, and belongs to the technical field of airport flight delay early warning methods. Background technique [0002] With the sustained, rapid and healthy development of the national economy, the demand for air transport is also increasing. However, in recent years, the phenomenon of large-scale flight delays has become increasingly prominent, and has become a worldwide problem that plagues civil aviation departments and passengers. Vicious incidents such as passengers refusing to board the plane, bullying the plane, attacking the airport, and beating staff due to flight delays are common occurrences, which have damaged the image of civil aviation's high-quality service and seriously affected the safe operation order of the airport. In order to reduce the delays caused by the airlines themselves, especially the improper formulation of flig...

AI Technical Summary

Problems solved by technology

However, there are many reasons for flight delays, the main reason is insufficient capacity of the airport and airspace, other reasons, such as weather, airport scheduling, company plans, passengers, luggage, etc. may also cause flight delays

In addition, flight delays also have a chain reaction problem: when a flight is delayed, if the schedule is tight, it will affect the punctual arrival or departure of the next flight, which will indirectly affect more downstream flights and airports

[0004] ①There are many types of early warning models based on machine learning algorithms, and it is difficult to objectively evaluate their performance under the same conditions

[0006] ②Various algorithms generally do not consider the class imbalance of the actual flight delay data set

This unbalanced sample distribution will have a great negative impact on the classification performance of the classifier learning algorithm, which will easily cause the early warning to fail.

Since the optimization goal of most classifier learning algorithms when training classifiers is the overall classification accuracy, and the majority class that contains the number of samples accounting for the vast majority of the training set usually contributes the most to the overall classification accuracy, resulting in these The classifier generated by the algorithm is often able to classify the majority class samples very well, but the classification performance of the minority class samples is very poor

Images