Online prediction of travel time

Experience from a pilot trial

Research output: Contribution to journalArticleScientific

1 Citation (Scopus)

Abstract

This study was designed to present an online model which predicted travel times on an interurban two-lane two-way highway section on the basis of field measurements.
The study included two parts: an evaluation of the performance of the model, and an examination of the possibility to improve the model in case of unsatisfactory performance. The model was based on MLP neural networks. The main results of the evaluation showed that the prediction model outperformed a non-predictive system.
However, the model for one section had not performed as well during the trial period as was expected. This might be due to a slight change in the congestion phenomenon. After further development, the findings showed that the model could be improved considerably with new data.
The main implication was that even a simple prediction model improves the quality of travel time information substantially, compared to estimates based directly on the latest measurements.
Original languageEnglish
Pages (from-to)271-287
JournalTransportation Planning and Technology
Volume30
Issue number2-3
DOIs
Publication statusPublished - 2007
MoE publication typeB1 Article in a scientific magazine

Fingerprint

time experience
Travel time
travel time
travel
prediction
trial
congestion
evaluation
neural network
performance
road
Neural networks
examination

Keywords

  • Prediction
  • travel time
  • information
  • neural networks
  • highway

Cite this

@article{4de98aec33354b73995bfa0a25ddc109,
title = "Online prediction of travel time: Experience from a pilot trial",
abstract = "This study was designed to present an online model which predicted travel times on an interurban two-lane two-way highway section on the basis of field measurements. The study included two parts: an evaluation of the performance of the model, and an examination of the possibility to improve the model in case of unsatisfactory performance. The model was based on MLP neural networks. The main results of the evaluation showed that the prediction model outperformed a non-predictive system. However, the model for one section had not performed as well during the trial period as was expected. This might be due to a slight change in the congestion phenomenon. After further development, the findings showed that the model could be improved considerably with new data. The main implication was that even a simple prediction model improves the quality of travel time information substantially, compared to estimates based directly on the latest measurements.",
keywords = "Prediction, travel time, information, neural networks, highway",
author = "Satu Innamaa",
year = "2007",
doi = "10.1080/03081060701395535",
language = "English",
volume = "30",
pages = "271--287",
journal = "Transportation Planning and Technology",
issn = "0308-1060",
publisher = "Taylor & Francis",
number = "2-3",

}

Online prediction of travel time : Experience from a pilot trial. / Innamaa, Satu.

In: Transportation Planning and Technology, Vol. 30, No. 2-3, 2007, p. 271-287.

Research output: Contribution to journalArticleScientific

TY - JOUR

T1 - Online prediction of travel time

T2 - Experience from a pilot trial

AU - Innamaa, Satu

PY - 2007

Y1 - 2007

N2 - This study was designed to present an online model which predicted travel times on an interurban two-lane two-way highway section on the basis of field measurements. The study included two parts: an evaluation of the performance of the model, and an examination of the possibility to improve the model in case of unsatisfactory performance. The model was based on MLP neural networks. The main results of the evaluation showed that the prediction model outperformed a non-predictive system. However, the model for one section had not performed as well during the trial period as was expected. This might be due to a slight change in the congestion phenomenon. After further development, the findings showed that the model could be improved considerably with new data. The main implication was that even a simple prediction model improves the quality of travel time information substantially, compared to estimates based directly on the latest measurements.

AB - This study was designed to present an online model which predicted travel times on an interurban two-lane two-way highway section on the basis of field measurements. The study included two parts: an evaluation of the performance of the model, and an examination of the possibility to improve the model in case of unsatisfactory performance. The model was based on MLP neural networks. The main results of the evaluation showed that the prediction model outperformed a non-predictive system. However, the model for one section had not performed as well during the trial period as was expected. This might be due to a slight change in the congestion phenomenon. After further development, the findings showed that the model could be improved considerably with new data. The main implication was that even a simple prediction model improves the quality of travel time information substantially, compared to estimates based directly on the latest measurements.

KW - Prediction

KW - travel time

KW - information

KW - neural networks

KW - highway

U2 - 10.1080/03081060701395535

DO - 10.1080/03081060701395535

M3 - Article

VL - 30

SP - 271

EP - 287

JO - Transportation Planning and Technology

JF - Transportation Planning and Technology

SN - 0308-1060

IS - 2-3

ER -