Dynamic procedure for short-term prediction of traffic conditions

Wei Hua Lin, Qingying Lu, Joy Dahlgren

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Many existing models for forecasting traffic conditions are based on traffic flows. Field data are used here to show that these traffic conditions may not fluctuate from day to day in the same manner as does the traffic flow. Consequently, flow data are inappropriate for predicting traffic conditions because the same flow level may correspond to either a congested or a free-flow traffic state, a phenomenon that can be easily explained with the flow-density relationship. Occupancy, which is proportional to density, is a better indicator of traffic condition. A simple dynamic model based on occupancy data is proposed. The model utilizes occupancy and occupancy increments in an integrated way and treats them as two random variables represented by two normal distribution functions. It is shown that flow data, which are more stable than occupancy data, can be used indirectly to improve the performance of the proposed model. Self- and cross-validation efforts are made to examine the performance of the model. The results are promising. The expected absolute deviance for predicted occupancy (ranging from 0 to 100%) is about 1.25 %, which is accurate enough for most applications. The model requires little effort in calibration and computation and is exceedingly simple to implement in the field.

Original languageEnglish (US)
Pages (from-to)149-157
Number of pages9
JournalTransportation Research Record
Issue number1783
StatePublished - 2002

Fingerprint

Normal distribution
Random variables
Distribution functions
Dynamic models
Calibration

ASJC Scopus subject areas

  • Civil and Structural Engineering

Cite this

Dynamic procedure for short-term prediction of traffic conditions. / Lin, Wei Hua; Lu, Qingying; Dahlgren, Joy.

In: Transportation Research Record, No. 1783, 2002, p. 149-157.

Research output: Contribution to journalArticle

Lin, Wei Hua ; Lu, Qingying ; Dahlgren, Joy. / Dynamic procedure for short-term prediction of traffic conditions. In: Transportation Research Record. 2002 ; No. 1783. pp. 149-157.
@article{9abbec9e19b64bfa9bb5d96e77493b3a,
title = "Dynamic procedure for short-term prediction of traffic conditions",
abstract = "Many existing models for forecasting traffic conditions are based on traffic flows. Field data are used here to show that these traffic conditions may not fluctuate from day to day in the same manner as does the traffic flow. Consequently, flow data are inappropriate for predicting traffic conditions because the same flow level may correspond to either a congested or a free-flow traffic state, a phenomenon that can be easily explained with the flow-density relationship. Occupancy, which is proportional to density, is a better indicator of traffic condition. A simple dynamic model based on occupancy data is proposed. The model utilizes occupancy and occupancy increments in an integrated way and treats them as two random variables represented by two normal distribution functions. It is shown that flow data, which are more stable than occupancy data, can be used indirectly to improve the performance of the proposed model. Self- and cross-validation efforts are made to examine the performance of the model. The results are promising. The expected absolute deviance for predicted occupancy (ranging from 0 to 100{\%}) is about 1.25 {\%}, which is accurate enough for most applications. The model requires little effort in calibration and computation and is exceedingly simple to implement in the field.",
author = "Lin, {Wei Hua} and Qingying Lu and Joy Dahlgren",
year = "2002",
language = "English (US)",
pages = "149--157",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",
number = "1783",

}

TY - JOUR

T1 - Dynamic procedure for short-term prediction of traffic conditions

AU - Lin, Wei Hua

AU - Lu, Qingying

AU - Dahlgren, Joy

PY - 2002

Y1 - 2002

N2 - Many existing models for forecasting traffic conditions are based on traffic flows. Field data are used here to show that these traffic conditions may not fluctuate from day to day in the same manner as does the traffic flow. Consequently, flow data are inappropriate for predicting traffic conditions because the same flow level may correspond to either a congested or a free-flow traffic state, a phenomenon that can be easily explained with the flow-density relationship. Occupancy, which is proportional to density, is a better indicator of traffic condition. A simple dynamic model based on occupancy data is proposed. The model utilizes occupancy and occupancy increments in an integrated way and treats them as two random variables represented by two normal distribution functions. It is shown that flow data, which are more stable than occupancy data, can be used indirectly to improve the performance of the proposed model. Self- and cross-validation efforts are made to examine the performance of the model. The results are promising. The expected absolute deviance for predicted occupancy (ranging from 0 to 100%) is about 1.25 %, which is accurate enough for most applications. The model requires little effort in calibration and computation and is exceedingly simple to implement in the field.

AB - Many existing models for forecasting traffic conditions are based on traffic flows. Field data are used here to show that these traffic conditions may not fluctuate from day to day in the same manner as does the traffic flow. Consequently, flow data are inappropriate for predicting traffic conditions because the same flow level may correspond to either a congested or a free-flow traffic state, a phenomenon that can be easily explained with the flow-density relationship. Occupancy, which is proportional to density, is a better indicator of traffic condition. A simple dynamic model based on occupancy data is proposed. The model utilizes occupancy and occupancy increments in an integrated way and treats them as two random variables represented by two normal distribution functions. It is shown that flow data, which are more stable than occupancy data, can be used indirectly to improve the performance of the proposed model. Self- and cross-validation efforts are made to examine the performance of the model. The results are promising. The expected absolute deviance for predicted occupancy (ranging from 0 to 100%) is about 1.25 %, which is accurate enough for most applications. The model requires little effort in calibration and computation and is exceedingly simple to implement in the field.

UR - http://www.scopus.com/inward/record.url?scp=0036949705&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036949705&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0036949705

SP - 149

EP - 157

JO - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

IS - 1783

ER -