Multi-period forecasting of accident duration based on multiple sources of real-time traffic data

Chien-Hung Wei, Ying Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The aim of this study is to build the adaptive ANN-based models for accident duration prediction. Two types of accident duration models are conducted. Model A is used to forecast the duration at the accident notification and Model B provides multi-period update of incident duration after accident notification. The APE and MAPE of forecasted accident duration at each time point of forecast are mostly under 20%. With these two models, the estimated duration can be provided by plugging in relevant traffic data as soon as the incident is notified. The traveler and traffic management unit can generally realize the impact by the forecasted accident duration. From the assessment of model effects, this study shows very promising practical applicability of the proposed models in the Intelligent Transportation Systems (ITS) context.

Original languageEnglish
Title of host publicationIntelligent Transportation Society of America - 12th World Congress on Intelligent Transport Systems 2005
Pages790-803
Number of pages14
Volume2
Publication statusPublished - 2009
Event12th World Congress on Intelligent Transport Systems 2005 - San Francisco, CA, United States
Duration: 2005 Nov 62005 Nov 10

Other

Other12th World Congress on Intelligent Transport Systems 2005
CountryUnited States
CitySan Francisco, CA
Period05-11-0605-11-10

Fingerprint

Accidents
accident
traffic
incident
time
transportation system
management

All Science Journal Classification (ASJC) codes

  • Mechanical Engineering
  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Transportation
  • Automotive Engineering
  • Computer Networks and Communications
  • Artificial Intelligence
  • Computer Science Applications

Cite this

Wei, C-H., & Lee, Y. (2009). Multi-period forecasting of accident duration based on multiple sources of real-time traffic data. In Intelligent Transportation Society of America - 12th World Congress on Intelligent Transport Systems 2005 (Vol. 2, pp. 790-803)
Wei, Chien-Hung ; Lee, Ying. / Multi-period forecasting of accident duration based on multiple sources of real-time traffic data. Intelligent Transportation Society of America - 12th World Congress on Intelligent Transport Systems 2005. Vol. 2 2009. pp. 790-803
@inproceedings{3cd8f92f47fa4f68950308f2de691421,
title = "Multi-period forecasting of accident duration based on multiple sources of real-time traffic data",
abstract = "The aim of this study is to build the adaptive ANN-based models for accident duration prediction. Two types of accident duration models are conducted. Model A is used to forecast the duration at the accident notification and Model B provides multi-period update of incident duration after accident notification. The APE and MAPE of forecasted accident duration at each time point of forecast are mostly under 20{\%}. With these two models, the estimated duration can be provided by plugging in relevant traffic data as soon as the incident is notified. The traveler and traffic management unit can generally realize the impact by the forecasted accident duration. From the assessment of model effects, this study shows very promising practical applicability of the proposed models in the Intelligent Transportation Systems (ITS) context.",
author = "Chien-Hung Wei and Ying Lee",
year = "2009",
language = "English",
isbn = "9781604236354",
volume = "2",
pages = "790--803",
booktitle = "Intelligent Transportation Society of America - 12th World Congress on Intelligent Transport Systems 2005",

}

Wei, C-H & Lee, Y 2009, Multi-period forecasting of accident duration based on multiple sources of real-time traffic data. in Intelligent Transportation Society of America - 12th World Congress on Intelligent Transport Systems 2005. vol. 2, pp. 790-803, 12th World Congress on Intelligent Transport Systems 2005, San Francisco, CA, United States, 05-11-06.

Multi-period forecasting of accident duration based on multiple sources of real-time traffic data. / Wei, Chien-Hung; Lee, Ying.

Intelligent Transportation Society of America - 12th World Congress on Intelligent Transport Systems 2005. Vol. 2 2009. p. 790-803.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Multi-period forecasting of accident duration based on multiple sources of real-time traffic data

AU - Wei, Chien-Hung

AU - Lee, Ying

PY - 2009

Y1 - 2009

N2 - The aim of this study is to build the adaptive ANN-based models for accident duration prediction. Two types of accident duration models are conducted. Model A is used to forecast the duration at the accident notification and Model B provides multi-period update of incident duration after accident notification. The APE and MAPE of forecasted accident duration at each time point of forecast are mostly under 20%. With these two models, the estimated duration can be provided by plugging in relevant traffic data as soon as the incident is notified. The traveler and traffic management unit can generally realize the impact by the forecasted accident duration. From the assessment of model effects, this study shows very promising practical applicability of the proposed models in the Intelligent Transportation Systems (ITS) context.

AB - The aim of this study is to build the adaptive ANN-based models for accident duration prediction. Two types of accident duration models are conducted. Model A is used to forecast the duration at the accident notification and Model B provides multi-period update of incident duration after accident notification. The APE and MAPE of forecasted accident duration at each time point of forecast are mostly under 20%. With these two models, the estimated duration can be provided by plugging in relevant traffic data as soon as the incident is notified. The traveler and traffic management unit can generally realize the impact by the forecasted accident duration. From the assessment of model effects, this study shows very promising practical applicability of the proposed models in the Intelligent Transportation Systems (ITS) context.

UR - http://www.scopus.com/inward/record.url?scp=84878912312&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878912312&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781604236354

VL - 2

SP - 790

EP - 803

BT - Intelligent Transportation Society of America - 12th World Congress on Intelligent Transport Systems 2005

ER -

Wei C-H, Lee Y. Multi-period forecasting of accident duration based on multiple sources of real-time traffic data. In Intelligent Transportation Society of America - 12th World Congress on Intelligent Transport Systems 2005. Vol. 2. 2009. p. 790-803