Forecasting multiple-period freeway link travel times using modular neural networks

Dongjoo Park, Laurence R. Rilett

Research output: Contribution to journalArticle

136 Citations (Scopus)

Abstract

With the advent of route guidance systems (RGS), the prediction of short-term link travel times has become increasingly important. For RGS to be successful, the calculated routes should be based on not only historical and real-time link travel time information but also anticipatory link travel time information. An examination is conducted on how real-time information gathered as part of intelligent transportation systems can be used to predict link travel times for one through five time periods (of 5 minutes' duration). The methodology developed consists of two steps. First, the historical link travel times are classified based on an unsupervised clustering technique. Second, an individual or modular artificial neural network (ANN) is calibrated for each class, and each modular ANN is then used to predict link travel times. Actual link travel times from Houston, Texas, collected as part of the automatic vehicle identification system of the Houston Transtar system were used as a test bed. It was found that the modular ANN outperformed a conventional singular ANN. The results of the best modular ANN were compared with existing link travel time techniques, including a Kalman filtering model, an exponential smoothing model, a historical profile, and a real-time profile, and it was found that the modular ANN gave the best overall results.

Original languageEnglish (US)
Pages (from-to)163-170
Number of pages8
JournalTransportation Research Record
Issue number1617
DOIs
StatePublished - Jan 1 1998

Fingerprint

Highway systems
Travel time
Neural networks
Automatic vehicle identification

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Mechanical Engineering

Cite this

Forecasting multiple-period freeway link travel times using modular neural networks. / Park, Dongjoo; Rilett, Laurence R.

In: Transportation Research Record, No. 1617, 01.01.1998, p. 163-170.

Research output: Contribution to journalArticle

@article{dbebb3ee33ff4dfaaf1f73f8e588f6bd,
title = "Forecasting multiple-period freeway link travel times using modular neural networks",
abstract = "With the advent of route guidance systems (RGS), the prediction of short-term link travel times has become increasingly important. For RGS to be successful, the calculated routes should be based on not only historical and real-time link travel time information but also anticipatory link travel time information. An examination is conducted on how real-time information gathered as part of intelligent transportation systems can be used to predict link travel times for one through five time periods (of 5 minutes' duration). The methodology developed consists of two steps. First, the historical link travel times are classified based on an unsupervised clustering technique. Second, an individual or modular artificial neural network (ANN) is calibrated for each class, and each modular ANN is then used to predict link travel times. Actual link travel times from Houston, Texas, collected as part of the automatic vehicle identification system of the Houston Transtar system were used as a test bed. It was found that the modular ANN outperformed a conventional singular ANN. The results of the best modular ANN were compared with existing link travel time techniques, including a Kalman filtering model, an exponential smoothing model, a historical profile, and a real-time profile, and it was found that the modular ANN gave the best overall results.",
author = "Dongjoo Park and Rilett, {Laurence R.}",
year = "1998",
month = "1",
day = "1",
doi = "10.3141/1617-23",
language = "English (US)",
pages = "163--170",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",
number = "1617",

}

TY - JOUR

T1 - Forecasting multiple-period freeway link travel times using modular neural networks

AU - Park, Dongjoo

AU - Rilett, Laurence R.

PY - 1998/1/1

Y1 - 1998/1/1

N2 - With the advent of route guidance systems (RGS), the prediction of short-term link travel times has become increasingly important. For RGS to be successful, the calculated routes should be based on not only historical and real-time link travel time information but also anticipatory link travel time information. An examination is conducted on how real-time information gathered as part of intelligent transportation systems can be used to predict link travel times for one through five time periods (of 5 minutes' duration). The methodology developed consists of two steps. First, the historical link travel times are classified based on an unsupervised clustering technique. Second, an individual or modular artificial neural network (ANN) is calibrated for each class, and each modular ANN is then used to predict link travel times. Actual link travel times from Houston, Texas, collected as part of the automatic vehicle identification system of the Houston Transtar system were used as a test bed. It was found that the modular ANN outperformed a conventional singular ANN. The results of the best modular ANN were compared with existing link travel time techniques, including a Kalman filtering model, an exponential smoothing model, a historical profile, and a real-time profile, and it was found that the modular ANN gave the best overall results.

AB - With the advent of route guidance systems (RGS), the prediction of short-term link travel times has become increasingly important. For RGS to be successful, the calculated routes should be based on not only historical and real-time link travel time information but also anticipatory link travel time information. An examination is conducted on how real-time information gathered as part of intelligent transportation systems can be used to predict link travel times for one through five time periods (of 5 minutes' duration). The methodology developed consists of two steps. First, the historical link travel times are classified based on an unsupervised clustering technique. Second, an individual or modular artificial neural network (ANN) is calibrated for each class, and each modular ANN is then used to predict link travel times. Actual link travel times from Houston, Texas, collected as part of the automatic vehicle identification system of the Houston Transtar system were used as a test bed. It was found that the modular ANN outperformed a conventional singular ANN. The results of the best modular ANN were compared with existing link travel time techniques, including a Kalman filtering model, an exponential smoothing model, a historical profile, and a real-time profile, and it was found that the modular ANN gave the best overall results.

UR - http://www.scopus.com/inward/record.url?scp=0032155636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032155636&partnerID=8YFLogxK

U2 - 10.3141/1617-23

DO - 10.3141/1617-23

M3 - Article

AN - SCOPUS:0032155636

SP - 163

EP - 170

JO - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

IS - 1617

ER -