Approaches for freeway work zone capacity estimation: Incorporating probe vehicle data

Bo Du; Joyoung Lee; Branislav Dimitrijevic; Kitae Kim; Steven Chien

Approaches for freeway work zone capacity estimation: Incorporating probe vehicle data

Bo Du, Joyoung Lee, Branislav Dimitrijevic, Kitae Kim, Steven Chien

Civil and Environmental Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

This study presents an Artificial Neural Network (ANN) model for estimating work zone capacity by taking into consideration various factors affecting the capacity, such as approaching traffic volume, average work zone speed, and travel time. To overcome the deficiencies of the existing parametric model-based approaches, probe vehicle data are incorporated into the work zone capacity estimation procedure. Exploiting a VISSIM-based hypothetical work zone environment on a freeway, the accuracy of estimated capacity produced by the ANN model with and without probe vehicle data is examined. Simulation results show that the accuracy of estimated capacity incorporating probe-based travel time is improved up to 5%.

Original language	English (US)
State	Published - 2014
Event	21st World Congress on Intelligent Transport Systems: Reinventing Transportation in Our Connected World, ITSWC 2014 - Detroit, United States Duration: Sep 7 2014 → Sep 11 2014

Other

Other	21st World Congress on Intelligent Transport Systems: Reinventing Transportation in Our Connected World, ITSWC 2014
Country/Territory	United States
City	Detroit
Period	9/7/14 → 9/11/14

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Mechanical Engineering
Automotive Engineering
Transportation
Electrical and Electronic Engineering

Keywords

Artificial neural network
Capacity
Probe vehicle data
Work zone

Cite this

@conference{90e5e34eb1ac4804881f6806cddb3f4a,

title = "Approaches for freeway work zone capacity estimation: Incorporating probe vehicle data",

abstract = "This study presents an Artificial Neural Network (ANN) model for estimating work zone capacity by taking into consideration various factors affecting the capacity, such as approaching traffic volume, average work zone speed, and travel time. To overcome the deficiencies of the existing parametric model-based approaches, probe vehicle data are incorporated into the work zone capacity estimation procedure. Exploiting a VISSIM-based hypothetical work zone environment on a freeway, the accuracy of estimated capacity produced by the ANN model with and without probe vehicle data is examined. Simulation results show that the accuracy of estimated capacity incorporating probe-based travel time is improved up to 5%.",

keywords = "Artificial neural network, Capacity, Probe vehicle data, Work zone",

author = "Bo Du and Joyoung Lee and Branislav Dimitrijevic and Kitae Kim and Steven Chien",

year = "2014",

language = "English (US)",

note = "21st World Congress on Intelligent Transport Systems: Reinventing Transportation in Our Connected World, ITSWC 2014 ; Conference date: 07-09-2014 Through 11-09-2014",

}

Approaches for freeway work zone capacity estimation: Incorporating probe vehicle data. / Du, Bo; Lee, Joyoung ; Dimitrijevic, Branislav et al.
2014. Paper presented at 21st World Congress on Intelligent Transport Systems: Reinventing Transportation in Our Connected World, ITSWC 2014, Detroit, United States.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Approaches for freeway work zone capacity estimation

T2 - 21st World Congress on Intelligent Transport Systems: Reinventing Transportation in Our Connected World, ITSWC 2014

AU - Du, Bo

AU - Lee, Joyoung

AU - Dimitrijevic, Branislav

AU - Kim, Kitae

AU - Chien, Steven

PY - 2014

Y1 - 2014

N2 - This study presents an Artificial Neural Network (ANN) model for estimating work zone capacity by taking into consideration various factors affecting the capacity, such as approaching traffic volume, average work zone speed, and travel time. To overcome the deficiencies of the existing parametric model-based approaches, probe vehicle data are incorporated into the work zone capacity estimation procedure. Exploiting a VISSIM-based hypothetical work zone environment on a freeway, the accuracy of estimated capacity produced by the ANN model with and without probe vehicle data is examined. Simulation results show that the accuracy of estimated capacity incorporating probe-based travel time is improved up to 5%.

AB - This study presents an Artificial Neural Network (ANN) model for estimating work zone capacity by taking into consideration various factors affecting the capacity, such as approaching traffic volume, average work zone speed, and travel time. To overcome the deficiencies of the existing parametric model-based approaches, probe vehicle data are incorporated into the work zone capacity estimation procedure. Exploiting a VISSIM-based hypothetical work zone environment on a freeway, the accuracy of estimated capacity produced by the ANN model with and without probe vehicle data is examined. Simulation results show that the accuracy of estimated capacity incorporating probe-based travel time is improved up to 5%.

KW - Artificial neural network

KW - Capacity

KW - Probe vehicle data

KW - Work zone

UR - http://www.scopus.com/inward/record.url?scp=84929192387&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929192387&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84929192387

Y2 - 7 September 2014 through 11 September 2014

ER -

Approaches for freeway work zone capacity estimation: Incorporating probe vehicle data

Abstract

Other

All Science Journal Classification (ASJC) codes

Keywords

Other files and links

Fingerprint

Cite this