Dynamic O-D travel time estimation using an artificial neural network

Research output: Contribution to conferencePaper

Abstract

Although the minimum Q-D travel time path in a dynamic traffic network can be calculated using standard minimum path algorithms there are a number of transportation applications which require a quick estimate of this information. These applications include such areas as real time vehicle dispatching systems where potential routes between a large number of origins and destinations have to be continually updated for a variety of vehicles throughout the day. The objective of this paper is to demonstrate the feasibility of using an artificial neural network (ANN) to estimate the O-D travel time in a dynamic traffic network. Three feed forward neural networks were developed to model the travel time behavior during different time periods of the day: AM peak, PM peak and off peak. These ANN models were subsequently trained and tested using a network from the City of Edmonton, Alberta. A comparison of the ANN model with a traditional statistical model is then presented. Lastly, the computational efficiency of the proposed ANN model compared to two shortest path algorithms is demonstrated. The statistical results show that the ANN models are appropriate for estimating dynamic O-D travel times and are significantly faster than the exact minimum path algorithms.

Original languageEnglish (US)
Pages236-242
Number of pages7
StatePublished - Jan 1 1995
EventProceedings of the 6th 1995 Vehicle Navigation and Information Systems Conference - Seattle, WA, USA
Duration: Jul 30 1995Aug 2 1995

Other

OtherProceedings of the 6th 1995 Vehicle Navigation and Information Systems Conference
CitySeattle, WA, USA
Period7/30/958/2/95

Fingerprint

Travel time
Neural networks
Feedforward neural networks
Computational efficiency

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Fu, L., & Rilett, L. R. (1995). Dynamic O-D travel time estimation using an artificial neural network. 236-242. Paper presented at Proceedings of the 6th 1995 Vehicle Navigation and Information Systems Conference, Seattle, WA, USA, .

Dynamic O-D travel time estimation using an artificial neural network. / Fu, L.; Rilett, L. R.

1995. 236-242 Paper presented at Proceedings of the 6th 1995 Vehicle Navigation and Information Systems Conference, Seattle, WA, USA, .

Research output: Contribution to conferencePaper

Fu, L & Rilett, LR 1995, 'Dynamic O-D travel time estimation using an artificial neural network' Paper presented at Proceedings of the 6th 1995 Vehicle Navigation and Information Systems Conference, Seattle, WA, USA, 7/30/95 - 8/2/95, pp. 236-242.
Fu L, Rilett LR. Dynamic O-D travel time estimation using an artificial neural network. 1995. Paper presented at Proceedings of the 6th 1995 Vehicle Navigation and Information Systems Conference, Seattle, WA, USA, .
Fu, L. ; Rilett, L. R. / Dynamic O-D travel time estimation using an artificial neural network. Paper presented at Proceedings of the 6th 1995 Vehicle Navigation and Information Systems Conference, Seattle, WA, USA, .7 p.
@conference{5c36abb8991c43f381b049623d412470,
title = "Dynamic O-D travel time estimation using an artificial neural network",
abstract = "Although the minimum Q-D travel time path in a dynamic traffic network can be calculated using standard minimum path algorithms there are a number of transportation applications which require a quick estimate of this information. These applications include such areas as real time vehicle dispatching systems where potential routes between a large number of origins and destinations have to be continually updated for a variety of vehicles throughout the day. The objective of this paper is to demonstrate the feasibility of using an artificial neural network (ANN) to estimate the O-D travel time in a dynamic traffic network. Three feed forward neural networks were developed to model the travel time behavior during different time periods of the day: AM peak, PM peak and off peak. These ANN models were subsequently trained and tested using a network from the City of Edmonton, Alberta. A comparison of the ANN model with a traditional statistical model is then presented. Lastly, the computational efficiency of the proposed ANN model compared to two shortest path algorithms is demonstrated. The statistical results show that the ANN models are appropriate for estimating dynamic O-D travel times and are significantly faster than the exact minimum path algorithms.",
author = "L. Fu and Rilett, {L. R.}",
year = "1995",
month = "1",
day = "1",
language = "English (US)",
pages = "236--242",
note = "Proceedings of the 6th 1995 Vehicle Navigation and Information Systems Conference ; Conference date: 30-07-1995 Through 02-08-1995",

}

TY - CONF

T1 - Dynamic O-D travel time estimation using an artificial neural network

AU - Fu, L.

AU - Rilett, L. R.

PY - 1995/1/1

Y1 - 1995/1/1

N2 - Although the minimum Q-D travel time path in a dynamic traffic network can be calculated using standard minimum path algorithms there are a number of transportation applications which require a quick estimate of this information. These applications include such areas as real time vehicle dispatching systems where potential routes between a large number of origins and destinations have to be continually updated for a variety of vehicles throughout the day. The objective of this paper is to demonstrate the feasibility of using an artificial neural network (ANN) to estimate the O-D travel time in a dynamic traffic network. Three feed forward neural networks were developed to model the travel time behavior during different time periods of the day: AM peak, PM peak and off peak. These ANN models were subsequently trained and tested using a network from the City of Edmonton, Alberta. A comparison of the ANN model with a traditional statistical model is then presented. Lastly, the computational efficiency of the proposed ANN model compared to two shortest path algorithms is demonstrated. The statistical results show that the ANN models are appropriate for estimating dynamic O-D travel times and are significantly faster than the exact minimum path algorithms.

AB - Although the minimum Q-D travel time path in a dynamic traffic network can be calculated using standard minimum path algorithms there are a number of transportation applications which require a quick estimate of this information. These applications include such areas as real time vehicle dispatching systems where potential routes between a large number of origins and destinations have to be continually updated for a variety of vehicles throughout the day. The objective of this paper is to demonstrate the feasibility of using an artificial neural network (ANN) to estimate the O-D travel time in a dynamic traffic network. Three feed forward neural networks were developed to model the travel time behavior during different time periods of the day: AM peak, PM peak and off peak. These ANN models were subsequently trained and tested using a network from the City of Edmonton, Alberta. A comparison of the ANN model with a traditional statistical model is then presented. Lastly, the computational efficiency of the proposed ANN model compared to two shortest path algorithms is demonstrated. The statistical results show that the ANN models are appropriate for estimating dynamic O-D travel times and are significantly faster than the exact minimum path algorithms.

UR - http://www.scopus.com/inward/record.url?scp=0029190145&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029190145&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029190145

SP - 236

EP - 242

ER -