Please use this identifier to cite or link to this item:
Title: Machine learning algorithm to predict runway exits at Changi Airport
Authors: Cheng, Kwok Hong
Keywords: Engineering
Issue Date: 2020
Publisher: Nanyang Technological University
Project: A021
Abstract: With increasing demand of airport capacity, Changi Airport Group (CAG) is constantly looking at how to increase the airport capacity to enhance overall passenger experience. Studies had been done to understand the factors that influence the runway capacity. One of the factors is the type and location of runway exits. Since trailing aircraft cannot land before leading aircraft is clear of the runway therefore, location of the runway exit may affect the overall runway occupancy time. Based on various review of literature on utilising machine learning, it has proved that using machine learning models can make accurate predictions and able to provide solutions to numerous industries. However, there has been lack of research in predicting the runway exit for approaches using machine learning. This project aims to create a machine learning model to accurately predict runway exits for approaching aircraft to boost confidence of controllers resulting in smaller buffer that increases overall capacity without compromising safety. The prediction of runway exits was performed using the features extracted from A-SMGCS and the model could achieve eight out of ten correct predictions with Random forest classifier. The results indicate that the accuracy increases when the aircraft approaches closer to the runway exits. Further analysis had been done to understand the limitations in the predictions. Also, future work is needed to identify other features that could enhance the accuracy and efficiency of the prediction model.
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:MAE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
2.2 MBAdobe PDFView/Open

Page view(s)

Updated on Feb 4, 2023

Download(s) 50

Updated on Feb 4, 2023

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.