Heterogeneous machine learning ensembles for predicting train delays

Al Ghamdi, Mostafa, Parr, Gerard and Wang, Wenjia (2024) Heterogeneous machine learning ensembles for predicting train delays. IEEE Transactions on Intelligent Transportation Systems, 25 (6). pp. 5138-5153. ISSN 1524-9050

Preview

PDF (Heterogeneous Machine Learning Ensembles for Predicting Train Delays) - Accepted Version Download (3MB) | Preview

Abstract

Train delays have been a serious persisting problem in the UK and also many other countries. Due to increasing demand, rail networks are running close to their full capacity. As a consequence, an initial delay can cause many knock-on delays to other trains, and this is the main reason for the overall deterioration in the performance of the rail networks. Therefore, it is really useful to have an AI-based method that can predict delays accurately and reliably, to help train controllers to make and apply alternative plans in time to reduce or prevent further delays, when a delay occurs. However, existing machine learning models are not only inaccurate but more importantly unreliable. In this study, we have proposed a new approach to build heterogeneous ensembles with two novel model selection methods based on accuracy and diversity. We tested our heterogeneous ensembles using the real-world data and the results indicated that they are more accurate and robust than single models and state-of-the-art homogeneous ensembles, e.g. Random Forest and XGBoost. We then verified their performances with an independent dataset from a different train operating company and found that they achieved the consistent and accurate results.

Item Type:	Article
Uncontrolled Keywords:	train delay prediction,machine learning,ensemble,boosting classifiers,random forest,atmospheric modeling,predictive models,random forest,heterogeneous ensemble,rails,diversity,data models,delays,ensemble learning,mechanical engineering,automotive engineering,computer science applications,4*,this paper presented a novel ensemble method for predicting train delays and produced much improved accuracy than those of any individual models. this ieee journal has a relatively high impact factor, arguably the best journal on the domain. ,/dk/atira/pure/subjectarea/asjc/2200/2210
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Data Science and AI Faculty of Science > Research Groups > Smart Emerging Technologies (former - to 2025) Faculty of Science > Research Groups > Cyber Security Privacy and Trust Laboratory (former - to 2025) Faculty of Science > Research Groups > Cyber Intelligence and Networks
Related URLs:	http://www.scopus.com/inward/record.url?... https://ieeexplore.ieee.org/document/103...
Depositing User:	LivePure Connector
Date Deposited:	09 Jan 2024 01:35
Last Modified:	23 Apr 2025 00:16
URI:	https://ueaeprints.uea.ac.uk/id/eprint/94109
DOI:	10.1109/TITS.2023.3337858

Downloads

Actions (login required)

View Item