Stochastic model of traffic jam and traffic signal control

Ji Sun Shin, Cheng You Cui, Tae Hong Lee, HeeHyol Lee

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Traffic signal control is an effective method to solve the traffic jam. and forecasting traffic density has been known as an important part of the Intelligent Transportation System (ITS). The several methods of the traffic signal control are known such as random walk method, Neuron Network method, Bayesian Network method, and so on. In this paper, we propose a new method of a traffic signal control using a predicted distribution of traffic jam based on a Dynamic Bayesian Network model. First, a forecasting model to predict a probabilistic distribution of the traffic jam during each period of traffic lights is built. As the forecasting model, the Dynamic Bayesian Network is used to predict the probabilistic distribution of a density of the traffic jam. According to measurement of two crossing points for each cycle, the inflow and outflow of each direction and the number of standing vehicles at former cycle are obtained. The number of standing vehicle at k-th cycle will be calculated synchronously. Next, the probabilistic distribution of the density of standing vehicle in each cycle will be predicted using the Dynamic Bayesian Network constructed for the traffic jam. And then a control rule to adjust the split and the cycle to increase the probability between a lower limit and ceiling of the standing vehicles is deduced. As the results of the simulation using the actual traffic data of Kitakyushu city, the effectiveness of the method is shown.

Original languageEnglish
Pages (from-to)303-310
Number of pages8
JournalIEEJ Transactions on Electronics, Information and Systems
Volume131
Issue number2
DOIs
Publication statusPublished - 2011

Fingerprint

Traffic signals
Bayesian networks
Stochastic models
Telecommunication traffic
Ceilings
Neurons

Keywords

  • Dynamic Bayesian Network
  • Predicted probabilistic distribution
  • Traffic Jam
  • Traffic signal control

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Stochastic model of traffic jam and traffic signal control. / Shin, Ji Sun; Cui, Cheng You; Lee, Tae Hong; Lee, HeeHyol.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 131, No. 2, 2011, p. 303-310.

Research output: Contribution to journalArticle

Shin, Ji Sun ; Cui, Cheng You ; Lee, Tae Hong ; Lee, HeeHyol. / Stochastic model of traffic jam and traffic signal control. In: IEEJ Transactions on Electronics, Information and Systems. 2011 ; Vol. 131, No. 2. pp. 303-310.
@article{c84acc359e864dcbaa7a2909aea92aba,
title = "Stochastic model of traffic jam and traffic signal control",
abstract = "Traffic signal control is an effective method to solve the traffic jam. and forecasting traffic density has been known as an important part of the Intelligent Transportation System (ITS). The several methods of the traffic signal control are known such as random walk method, Neuron Network method, Bayesian Network method, and so on. In this paper, we propose a new method of a traffic signal control using a predicted distribution of traffic jam based on a Dynamic Bayesian Network model. First, a forecasting model to predict a probabilistic distribution of the traffic jam during each period of traffic lights is built. As the forecasting model, the Dynamic Bayesian Network is used to predict the probabilistic distribution of a density of the traffic jam. According to measurement of two crossing points for each cycle, the inflow and outflow of each direction and the number of standing vehicles at former cycle are obtained. The number of standing vehicle at k-th cycle will be calculated synchronously. Next, the probabilistic distribution of the density of standing vehicle in each cycle will be predicted using the Dynamic Bayesian Network constructed for the traffic jam. And then a control rule to adjust the split and the cycle to increase the probability between a lower limit and ceiling of the standing vehicles is deduced. As the results of the simulation using the actual traffic data of Kitakyushu city, the effectiveness of the method is shown.",
keywords = "Dynamic Bayesian Network, Predicted probabilistic distribution, Traffic Jam, Traffic signal control",
author = "Shin, {Ji Sun} and Cui, {Cheng You} and Lee, {Tae Hong} and HeeHyol Lee",
year = "2011",
doi = "10.1541/ieejeiss.131.303",
language = "English",
volume = "131",
pages = "303--310",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "2",

}

TY - JOUR

T1 - Stochastic model of traffic jam and traffic signal control

AU - Shin, Ji Sun

AU - Cui, Cheng You

AU - Lee, Tae Hong

AU - Lee, HeeHyol

PY - 2011

Y1 - 2011

N2 - Traffic signal control is an effective method to solve the traffic jam. and forecasting traffic density has been known as an important part of the Intelligent Transportation System (ITS). The several methods of the traffic signal control are known such as random walk method, Neuron Network method, Bayesian Network method, and so on. In this paper, we propose a new method of a traffic signal control using a predicted distribution of traffic jam based on a Dynamic Bayesian Network model. First, a forecasting model to predict a probabilistic distribution of the traffic jam during each period of traffic lights is built. As the forecasting model, the Dynamic Bayesian Network is used to predict the probabilistic distribution of a density of the traffic jam. According to measurement of two crossing points for each cycle, the inflow and outflow of each direction and the number of standing vehicles at former cycle are obtained. The number of standing vehicle at k-th cycle will be calculated synchronously. Next, the probabilistic distribution of the density of standing vehicle in each cycle will be predicted using the Dynamic Bayesian Network constructed for the traffic jam. And then a control rule to adjust the split and the cycle to increase the probability between a lower limit and ceiling of the standing vehicles is deduced. As the results of the simulation using the actual traffic data of Kitakyushu city, the effectiveness of the method is shown.

AB - Traffic signal control is an effective method to solve the traffic jam. and forecasting traffic density has been known as an important part of the Intelligent Transportation System (ITS). The several methods of the traffic signal control are known such as random walk method, Neuron Network method, Bayesian Network method, and so on. In this paper, we propose a new method of a traffic signal control using a predicted distribution of traffic jam based on a Dynamic Bayesian Network model. First, a forecasting model to predict a probabilistic distribution of the traffic jam during each period of traffic lights is built. As the forecasting model, the Dynamic Bayesian Network is used to predict the probabilistic distribution of a density of the traffic jam. According to measurement of two crossing points for each cycle, the inflow and outflow of each direction and the number of standing vehicles at former cycle are obtained. The number of standing vehicle at k-th cycle will be calculated synchronously. Next, the probabilistic distribution of the density of standing vehicle in each cycle will be predicted using the Dynamic Bayesian Network constructed for the traffic jam. And then a control rule to adjust the split and the cycle to increase the probability between a lower limit and ceiling of the standing vehicles is deduced. As the results of the simulation using the actual traffic data of Kitakyushu city, the effectiveness of the method is shown.

KW - Dynamic Bayesian Network

KW - Predicted probabilistic distribution

KW - Traffic Jam

KW - Traffic signal control

UR - http://www.scopus.com/inward/record.url?scp=80052411230&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052411230&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.131.303

DO - 10.1541/ieejeiss.131.303

M3 - Article

AN - SCOPUS:80052411230

VL - 131

SP - 303

EP - 310

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 2

ER -