Short-term prediction of travel time using neural networks on an interurban highway

Research output: Contribution to journalArticleScientificpeer-review

62 Citations (Scopus)

Abstract

The main purpose of this study was to investigate the predictability of travel time with a model based on travel time data measured in the field on an interurban highway. Another purpose was to determine whether the forecasts would be accurate enough to implement the model in an actual online travel time information service. The study was carried out on a 28-kilometre-long rural two-lane road section where traffic congestion was a problem during weekend peak hours. The section was equipped with an automatic travel time monitoring and information system. The prediction models were made as feedforward multilayer perceptron neural networks. The main results showed that the majority of the forecasts were close to the actual measured values. Consequently, use of the prediction model would improve the quality of travel time information based directly on the sum of the latest measured travel times.
Original languageEnglish
Pages (from-to)649 - 669
Number of pages21
JournalTransportation
Volume32
Issue number6
DOIs
Publication statusPublished - 2005
MoE publication typeA1 Journal article-refereed

Fingerprint

Travel time
neural network
travel time
travel
road
Neural networks
prediction
traffic congestion
Traffic congestion
weekend
Information services
Multilayer neural networks
information service
monitoring system
time
information system
Information systems
monitoring
Monitoring
Values

Keywords

  • neural networks
  • prediction
  • travel time
  • two-lane highway
  • road traffic
  • traffic
  • traffic congestion

Cite this

@article{3b0a79127ec244a2be3808ce258c39a5,
title = "Short-term prediction of travel time using neural networks on an interurban highway",
abstract = "The main purpose of this study was to investigate the predictability of travel time with a model based on travel time data measured in the field on an interurban highway. Another purpose was to determine whether the forecasts would be accurate enough to implement the model in an actual online travel time information service. The study was carried out on a 28-kilometre-long rural two-lane road section where traffic congestion was a problem during weekend peak hours. The section was equipped with an automatic travel time monitoring and information system. The prediction models were made as feedforward multilayer perceptron neural networks. The main results showed that the majority of the forecasts were close to the actual measured values. Consequently, use of the prediction model would improve the quality of travel time information based directly on the sum of the latest measured travel times.",
keywords = "neural networks, prediction, travel time, two-lane highway, road traffic, traffic, traffic congestion",
author = "Satu Innamaa",
year = "2005",
doi = "10.1007/s11116-005-0219-y",
language = "English",
volume = "32",
pages = "649 -- 669",
journal = "Transportation",
issn = "0049-4488",
publisher = "Springer",
number = "6",

}

Short-term prediction of travel time using neural networks on an interurban highway. / Innamaa, Satu.

In: Transportation, Vol. 32, No. 6, 2005, p. 649 - 669.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Short-term prediction of travel time using neural networks on an interurban highway

AU - Innamaa, Satu

PY - 2005

Y1 - 2005

N2 - The main purpose of this study was to investigate the predictability of travel time with a model based on travel time data measured in the field on an interurban highway. Another purpose was to determine whether the forecasts would be accurate enough to implement the model in an actual online travel time information service. The study was carried out on a 28-kilometre-long rural two-lane road section where traffic congestion was a problem during weekend peak hours. The section was equipped with an automatic travel time monitoring and information system. The prediction models were made as feedforward multilayer perceptron neural networks. The main results showed that the majority of the forecasts were close to the actual measured values. Consequently, use of the prediction model would improve the quality of travel time information based directly on the sum of the latest measured travel times.

AB - The main purpose of this study was to investigate the predictability of travel time with a model based on travel time data measured in the field on an interurban highway. Another purpose was to determine whether the forecasts would be accurate enough to implement the model in an actual online travel time information service. The study was carried out on a 28-kilometre-long rural two-lane road section where traffic congestion was a problem during weekend peak hours. The section was equipped with an automatic travel time monitoring and information system. The prediction models were made as feedforward multilayer perceptron neural networks. The main results showed that the majority of the forecasts were close to the actual measured values. Consequently, use of the prediction model would improve the quality of travel time information based directly on the sum of the latest measured travel times.

KW - neural networks

KW - prediction

KW - travel time

KW - two-lane highway

KW - road traffic

KW - traffic

KW - traffic congestion

U2 - 10.1007/s11116-005-0219-y

DO - 10.1007/s11116-005-0219-y

M3 - Article

VL - 32

SP - 649

EP - 669

JO - Transportation

JF - Transportation

SN - 0049-4488

IS - 6

ER -