Applying cluster method to reduce the traffic data feature for accident duration forecasting on freeway

Ying Lee, Chien-Hung Wei

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

Abstract

This study creates two Artificial Neural Network-based models and provides a sequential forecast of accident duration from the accident notification to the accident site clearance. With these two models, the estimated duration time can be provided by plugging in relevant traffic data as soon as an accident is notified. To reduce data feature, cluster method can decreases the number of model inputs and preserves the relevant traffic characteristics with fewer inputs. This study shows proposed models are feasible ones in the Intelligent Transportation Systems (ITS) context.

Original languageEnglish
Title of host publicationProceedings of the 13th International Conference of Hong Kong Society for Transportation Studies
Subtitle of host publicationTransportation and Management Science
Pages271-280
Number of pages10
Publication statusPublished - 2008
Event13th International Conference of Hong Kong Society for Transportation Studies: Transportation and Management Science - Kowloon, Hong Kong
Duration: 2008 Dec 132008 Dec 15

Other

Other13th International Conference of Hong Kong Society for Transportation Studies: Transportation and Management Science
CountryHong Kong
CityKowloon
Period08-12-1308-12-15

Fingerprint

Highway systems
Accidents
accident
traffic
transportation system
neural network
Neural networks

All Science Journal Classification (ASJC) codes

  • Transportation

Cite this

Lee, Y., & Wei, C-H. (2008). Applying cluster method to reduce the traffic data feature for accident duration forecasting on freeway. In Proceedings of the 13th International Conference of Hong Kong Society for Transportation Studies: Transportation and Management Science (pp. 271-280)
Lee, Ying ; Wei, Chien-Hung. / Applying cluster method to reduce the traffic data feature for accident duration forecasting on freeway. Proceedings of the 13th International Conference of Hong Kong Society for Transportation Studies: Transportation and Management Science. 2008. pp. 271-280
@inproceedings{91da654c9dc446669c74e8037d64e1d9,
title = "Applying cluster method to reduce the traffic data feature for accident duration forecasting on freeway",
abstract = "This study creates two Artificial Neural Network-based models and provides a sequential forecast of accident duration from the accident notification to the accident site clearance. With these two models, the estimated duration time can be provided by plugging in relevant traffic data as soon as an accident is notified. To reduce data feature, cluster method can decreases the number of model inputs and preserves the relevant traffic characteristics with fewer inputs. This study shows proposed models are feasible ones in the Intelligent Transportation Systems (ITS) context.",
author = "Ying Lee and Chien-Hung Wei",
year = "2008",
language = "English",
isbn = "9789889884734",
pages = "271--280",
booktitle = "Proceedings of the 13th International Conference of Hong Kong Society for Transportation Studies",

}

Lee, Y & Wei, C-H 2008, Applying cluster method to reduce the traffic data feature for accident duration forecasting on freeway. in Proceedings of the 13th International Conference of Hong Kong Society for Transportation Studies: Transportation and Management Science. pp. 271-280, 13th International Conference of Hong Kong Society for Transportation Studies: Transportation and Management Science, Kowloon, Hong Kong, 08-12-13.

Applying cluster method to reduce the traffic data feature for accident duration forecasting on freeway. / Lee, Ying; Wei, Chien-Hung.

Proceedings of the 13th International Conference of Hong Kong Society for Transportation Studies: Transportation and Management Science. 2008. p. 271-280.

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

TY - GEN

T1 - Applying cluster method to reduce the traffic data feature for accident duration forecasting on freeway

AU - Lee, Ying

AU - Wei, Chien-Hung

PY - 2008

Y1 - 2008

N2 - This study creates two Artificial Neural Network-based models and provides a sequential forecast of accident duration from the accident notification to the accident site clearance. With these two models, the estimated duration time can be provided by plugging in relevant traffic data as soon as an accident is notified. To reduce data feature, cluster method can decreases the number of model inputs and preserves the relevant traffic characteristics with fewer inputs. This study shows proposed models are feasible ones in the Intelligent Transportation Systems (ITS) context.

AB - This study creates two Artificial Neural Network-based models and provides a sequential forecast of accident duration from the accident notification to the accident site clearance. With these two models, the estimated duration time can be provided by plugging in relevant traffic data as soon as an accident is notified. To reduce data feature, cluster method can decreases the number of model inputs and preserves the relevant traffic characteristics with fewer inputs. This study shows proposed models are feasible ones in the Intelligent Transportation Systems (ITS) context.

UR - http://www.scopus.com/inward/record.url?scp=84896841739&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896841739&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789889884734

SP - 271

EP - 280

BT - Proceedings of the 13th International Conference of Hong Kong Society for Transportation Studies

ER -

Lee Y, Wei C-H. Applying cluster method to reduce the traffic data feature for accident duration forecasting on freeway. In Proceedings of the 13th International Conference of Hong Kong Society for Transportation Studies: Transportation and Management Science. 2008. p. 271-280