Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Real-time Train Arrival Time Prediction at Multiple Stations and Arbitrary Times

Tiong, Kah Yong LU ; Ma, Zhenliang and Palmqvist, Carl William LU orcid (2022) 25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022 In IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC 2022-October. p.793-798
Abstract

Real-time prediction of train arrivals is important for proactive traffic control and information provision in passenger rails. Despite many studies in predicting arrival times or delays at stations, they are essentially the next-step time series prediction problem which may limit their applications in practice. For example, passengers on the trains or waiting on platforms may have different destinations and need the predicted train arrival times for any downstream stations rather than only the next station. The paper aims to formulate a real-time train arrival times prediction problem at multiple stations and arbitrary times. We develop multi-output machine learning models and systematically evaluate their performance using train... (More)

Real-time prediction of train arrivals is important for proactive traffic control and information provision in passenger rails. Despite many studies in predicting arrival times or delays at stations, they are essentially the next-step time series prediction problem which may limit their applications in practice. For example, passengers on the trains or waiting on platforms may have different destinations and need the predicted train arrival times for any downstream stations rather than only the next station. The paper aims to formulate a real-time train arrival times prediction problem at multiple stations and arbitrary times. We develop multi-output machine learning models and systematically evaluate their performance using train operation data in Sweden. The direct multi-output regression models with different regression functions are tested, including LightGBM, linear regression, random forest regression, and gradient boosting regression models. The hyperparameters are optimized using random grid search and five-fold cross-validation methods. The results show that the Direct Multi-Output LightGBM significantly outper-formed other models in terms of accuracy. The predictions at downstream stations improve as the train moves along given more real-time information is observed.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
High-speed railway, LightGBM, Machine learning, Multi-Output Regression, Train arrival times
host publication
2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022
series title
IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
volume
2022-October
pages
6 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022
conference location
Macau, China
conference dates
2022-10-08 - 2022-10-12
external identifiers
  • scopus:85141846305
ISBN
9781665468817
9781665468800
DOI
10.1109/ITSC55140.2022.9922299
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2022 IEEE.
id
aa9f9484-f53a-4589-92f4-1e18b382cb42
date added to LUP
2022-11-28 08:31:07
date last changed
2024-04-18 16:25:39
@inproceedings{aa9f9484-f53a-4589-92f4-1e18b382cb42,
  abstract     = {{<p>Real-time prediction of train arrivals is important for proactive traffic control and information provision in passenger rails. Despite many studies in predicting arrival times or delays at stations, they are essentially the next-step time series prediction problem which may limit their applications in practice. For example, passengers on the trains or waiting on platforms may have different destinations and need the predicted train arrival times for any downstream stations rather than only the next station. The paper aims to formulate a real-time train arrival times prediction problem at multiple stations and arbitrary times. We develop multi-output machine learning models and systematically evaluate their performance using train operation data in Sweden. The direct multi-output regression models with different regression functions are tested, including LightGBM, linear regression, random forest regression, and gradient boosting regression models. The hyperparameters are optimized using random grid search and five-fold cross-validation methods. The results show that the Direct Multi-Output LightGBM significantly outper-formed other models in terms of accuracy. The predictions at downstream stations improve as the train moves along given more real-time information is observed.</p>}},
  author       = {{Tiong, Kah Yong and Ma, Zhenliang and Palmqvist, Carl William}},
  booktitle    = {{2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022}},
  isbn         = {{9781665468817}},
  keywords     = {{High-speed railway; LightGBM; Machine learning; Multi-Output Regression; Train arrival times}},
  language     = {{eng}},
  pages        = {{793--798}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC}},
  title        = {{Real-time Train Arrival Time Prediction at Multiple Stations and Arbitrary Times}},
  url          = {{http://dx.doi.org/10.1109/ITSC55140.2022.9922299}},
  doi          = {{10.1109/ITSC55140.2022.9922299}},
  volume       = {{2022-October}},
  year         = {{2022}},
}