Forecasting Train Travel Times at At-Grade Crossings

Hanseon Cho, Laurence R Rilett

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The ability to accurately forecast train arrival times is essential for the safe and efficient operation of highway-railroad grade crossings (HRGCs). Trains in the United States are required to give a minimum of 20 s of warning time before arriving at an HRGC. With the recent development of new detection-equipment technology, detectors potentially could be employed further upstream of the HRGC, which would result in earlier detection times. This information would be particularly useful for preemption strategies at signalized intersections located near the HRGC (IHRGCs). For example, earlier warning times could be used to reduce or eliminate the risk of unsafe pedestrian movements at IHRGCs. In this study, a modular artificial neural network (ANN) was used to forecast the train arrival time at an HRGC. An ANN was adopted because there is a nonlinear relationship between the independent variables such as train speed profile and the dependent variable arrival time at an HRGC. A modular approach was used because the trains often have different characteristics depending on their cargo and the operational rules in effect at the time they are detected. Because the train detection is continuous, different models were developed for each separate data input. In this case, the prediction interval update was assumed to be 10 s and 24 models were developed. Approximately 499 trains were used for training the ANN and 183 trains were used for testing. It was found that a modular architecture gave superior results to that of a simple ANN model, standard regression techniques, and current forecasting methods for the entire detection time period. It was found that, with an increase in detection time, the forecast accuracy increases for all methods and the prediction interval tends to decrease.

Original languageEnglish (US)
Pages (from-to)94-102
Number of pages9
JournalTransportation Research Record
Issue number1844
DOIs
StatePublished - Jan 1 2003

Fingerprint

Crossings (pipe and cable)
Railroads
Travel time
Neural networks
Detectors
Testing

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Mechanical Engineering

Cite this

Forecasting Train Travel Times at At-Grade Crossings. / Cho, Hanseon; Rilett, Laurence R.

In: Transportation Research Record, No. 1844, 01.01.2003, p. 94-102.

Research output: Contribution to journalArticle

@article{10a304d51ff04fbab6cd9c0d83736717,
title = "Forecasting Train Travel Times at At-Grade Crossings",
abstract = "The ability to accurately forecast train arrival times is essential for the safe and efficient operation of highway-railroad grade crossings (HRGCs). Trains in the United States are required to give a minimum of 20 s of warning time before arriving at an HRGC. With the recent development of new detection-equipment technology, detectors potentially could be employed further upstream of the HRGC, which would result in earlier detection times. This information would be particularly useful for preemption strategies at signalized intersections located near the HRGC (IHRGCs). For example, earlier warning times could be used to reduce or eliminate the risk of unsafe pedestrian movements at IHRGCs. In this study, a modular artificial neural network (ANN) was used to forecast the train arrival time at an HRGC. An ANN was adopted because there is a nonlinear relationship between the independent variables such as train speed profile and the dependent variable arrival time at an HRGC. A modular approach was used because the trains often have different characteristics depending on their cargo and the operational rules in effect at the time they are detected. Because the train detection is continuous, different models were developed for each separate data input. In this case, the prediction interval update was assumed to be 10 s and 24 models were developed. Approximately 499 trains were used for training the ANN and 183 trains were used for testing. It was found that a modular architecture gave superior results to that of a simple ANN model, standard regression techniques, and current forecasting methods for the entire detection time period. It was found that, with an increase in detection time, the forecast accuracy increases for all methods and the prediction interval tends to decrease.",
author = "Hanseon Cho and Rilett, {Laurence R}",
year = "2003",
month = "1",
day = "1",
doi = "10.3141/1844-12",
language = "English (US)",
pages = "94--102",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",
number = "1844",

}

TY - JOUR

T1 - Forecasting Train Travel Times at At-Grade Crossings

AU - Cho, Hanseon

AU - Rilett, Laurence R

PY - 2003/1/1

Y1 - 2003/1/1

N2 - The ability to accurately forecast train arrival times is essential for the safe and efficient operation of highway-railroad grade crossings (HRGCs). Trains in the United States are required to give a minimum of 20 s of warning time before arriving at an HRGC. With the recent development of new detection-equipment technology, detectors potentially could be employed further upstream of the HRGC, which would result in earlier detection times. This information would be particularly useful for preemption strategies at signalized intersections located near the HRGC (IHRGCs). For example, earlier warning times could be used to reduce or eliminate the risk of unsafe pedestrian movements at IHRGCs. In this study, a modular artificial neural network (ANN) was used to forecast the train arrival time at an HRGC. An ANN was adopted because there is a nonlinear relationship between the independent variables such as train speed profile and the dependent variable arrival time at an HRGC. A modular approach was used because the trains often have different characteristics depending on their cargo and the operational rules in effect at the time they are detected. Because the train detection is continuous, different models were developed for each separate data input. In this case, the prediction interval update was assumed to be 10 s and 24 models were developed. Approximately 499 trains were used for training the ANN and 183 trains were used for testing. It was found that a modular architecture gave superior results to that of a simple ANN model, standard regression techniques, and current forecasting methods for the entire detection time period. It was found that, with an increase in detection time, the forecast accuracy increases for all methods and the prediction interval tends to decrease.

AB - The ability to accurately forecast train arrival times is essential for the safe and efficient operation of highway-railroad grade crossings (HRGCs). Trains in the United States are required to give a minimum of 20 s of warning time before arriving at an HRGC. With the recent development of new detection-equipment technology, detectors potentially could be employed further upstream of the HRGC, which would result in earlier detection times. This information would be particularly useful for preemption strategies at signalized intersections located near the HRGC (IHRGCs). For example, earlier warning times could be used to reduce or eliminate the risk of unsafe pedestrian movements at IHRGCs. In this study, a modular artificial neural network (ANN) was used to forecast the train arrival time at an HRGC. An ANN was adopted because there is a nonlinear relationship between the independent variables such as train speed profile and the dependent variable arrival time at an HRGC. A modular approach was used because the trains often have different characteristics depending on their cargo and the operational rules in effect at the time they are detected. Because the train detection is continuous, different models were developed for each separate data input. In this case, the prediction interval update was assumed to be 10 s and 24 models were developed. Approximately 499 trains were used for training the ANN and 183 trains were used for testing. It was found that a modular architecture gave superior results to that of a simple ANN model, standard regression techniques, and current forecasting methods for the entire detection time period. It was found that, with an increase in detection time, the forecast accuracy increases for all methods and the prediction interval tends to decrease.

UR - http://www.scopus.com/inward/record.url?scp=1842428195&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1842428195&partnerID=8YFLogxK

U2 - 10.3141/1844-12

DO - 10.3141/1844-12

M3 - Article

SP - 94

EP - 102

JO - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

IS - 1844

ER -