Spectral basis neural networks for real-time travel time forecasting

Dongjoo Park, Laurence R. Rilett, Gunhee Han

Research output: Contribution to journalArticle

149 Citations (Scopus)

Abstract

This paper examines 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 ahead (of 5-min duration). The study employed a spectral basis artificial neural network (SNN) that utilizes a sinusoidal transformation technique to increase the linear separability of the input features. Link travel times from Houston that had been collected as part of the automatic vehicle identification system of the TranStar system were used as a test bed. It was found that the SNN outperformed a conventional artificial neural network and gave similar results to that of modular neural networks. However, the SNN requires significantly less effort on the part of the modeler than modular neural networks. The results of the best SNN were compared with conventional link travel time prediction techniques including a Kalman filtering model, exponential smoothing model, historical profile, and real-time profile. It was found that the SNN gave the best overall results

Original languageEnglish
Pages (from-to)515-523
Number of pages9
JournalJournal of Transportation Engineering
Volume125
Issue number6
DOIs
Publication statusPublished - 1999 Jan 1

Fingerprint

Travel time
neural network
travel
Neural networks
Automatic vehicle identification
transportation system
time

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Transportation

Cite this

Park, Dongjoo ; Rilett, Laurence R. ; Han, Gunhee. / Spectral basis neural networks for real-time travel time forecasting. In: Journal of Transportation Engineering. 1999 ; Vol. 125, No. 6. pp. 515-523.
@article{db692a5dd48f41b38bd7ef1433810da3,
title = "Spectral basis neural networks for real-time travel time forecasting",
abstract = "This paper examines 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 ahead (of 5-min duration). The study employed a spectral basis artificial neural network (SNN) that utilizes a sinusoidal transformation technique to increase the linear separability of the input features. Link travel times from Houston that had been collected as part of the automatic vehicle identification system of the TranStar system were used as a test bed. It was found that the SNN outperformed a conventional artificial neural network and gave similar results to that of modular neural networks. However, the SNN requires significantly less effort on the part of the modeler than modular neural networks. The results of the best SNN were compared with conventional link travel time prediction techniques including a Kalman filtering model, exponential smoothing model, historical profile, and real-time profile. It was found that the SNN gave the best overall results",
author = "Dongjoo Park and Rilett, {Laurence R.} and Gunhee Han",
year = "1999",
month = "1",
day = "1",
doi = "10.1061/(ASCE)0733-947X(1999)125:6(515)",
language = "English",
volume = "125",
pages = "515--523",
journal = "Transportation engineering journal of ASCE",
issn = "0733-947X",
publisher = "American Society of Civil Engineers (ASCE)",
number = "6",

}

Spectral basis neural networks for real-time travel time forecasting. / Park, Dongjoo; Rilett, Laurence R.; Han, Gunhee.

In: Journal of Transportation Engineering, Vol. 125, No. 6, 01.01.1999, p. 515-523.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Spectral basis neural networks for real-time travel time forecasting

AU - Park, Dongjoo

AU - Rilett, Laurence R.

AU - Han, Gunhee

PY - 1999/1/1

Y1 - 1999/1/1

N2 - This paper examines 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 ahead (of 5-min duration). The study employed a spectral basis artificial neural network (SNN) that utilizes a sinusoidal transformation technique to increase the linear separability of the input features. Link travel times from Houston that had been collected as part of the automatic vehicle identification system of the TranStar system were used as a test bed. It was found that the SNN outperformed a conventional artificial neural network and gave similar results to that of modular neural networks. However, the SNN requires significantly less effort on the part of the modeler than modular neural networks. The results of the best SNN were compared with conventional link travel time prediction techniques including a Kalman filtering model, exponential smoothing model, historical profile, and real-time profile. It was found that the SNN gave the best overall results

AB - This paper examines 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 ahead (of 5-min duration). The study employed a spectral basis artificial neural network (SNN) that utilizes a sinusoidal transformation technique to increase the linear separability of the input features. Link travel times from Houston that had been collected as part of the automatic vehicle identification system of the TranStar system were used as a test bed. It was found that the SNN outperformed a conventional artificial neural network and gave similar results to that of modular neural networks. However, the SNN requires significantly less effort on the part of the modeler than modular neural networks. The results of the best SNN were compared with conventional link travel time prediction techniques including a Kalman filtering model, exponential smoothing model, historical profile, and real-time profile. It was found that the SNN gave the best overall results

UR - http://www.scopus.com/inward/record.url?scp=0032779078&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032779078&partnerID=8YFLogxK

U2 - 10.1061/(ASCE)0733-947X(1999)125:6(515)

DO - 10.1061/(ASCE)0733-947X(1999)125:6(515)

M3 - Article

AN - SCOPUS:0032779078

VL - 125

SP - 515

EP - 523

JO - Transportation engineering journal of ASCE

JF - Transportation engineering journal of ASCE

SN - 0733-947X

IS - 6

ER -