Incident duration model on urban freeways using three different algorithms of decision tree

Ruimin Li; Xiaoqiang Zhao; Xinxin Yu; Junwei Li; Nan Cheng; Jie Zhang

doi:10.1109/ICICTA.2010.602

Incident duration model on urban freeways using three different algorithms of decision tree

Ruimin Li^*, Xiaoqiang Zhao, Xinxin Yu, Junwei Li, Nan Cheng, Jie Zhang

^*Corresponding author for this work

Tsinghua University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Citations (Scopus)

Abstract

Effective incident management requires accurate prediction of incident duration. In this paper, Classification and Regression Tree (CART), CHAID and Exhaustive CHAID is employed to model the incident duration. All 65000 incident records from Beijing Transportation Management Bureau are used for model establishment and another 8000 records for validation. The average relative error of the CART model is 29.5197% while CHAID is 30.78%; Exhaustive CHAID is 31.23%.It shows that the reliability of the three models is quite satisfactory. The average relative error of the prediction on different ring roads of Beijing is approximately the same.

Original language	English
Title of host publication	2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010
Pages	526-528
Number of pages	3
DOIs	https://doi.org/10.1109/ICICTA.2010.602
Publication status	Published - 2010
Externally published	Yes
Event	2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010 - Changsha, China Duration: 11 May 2010 → 12 May 2010

Publication series

Name	2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010
Volume	2

Conference

Conference	2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010
Country/Territory	China
City	Changsha
Period	11/05/10 → 12/05/10

Keywords

CHAID
Classification and regression tree
Decision tree
Exhaustive CHAID
Incident duration

Access to Document

10.1109/ICICTA.2010.602

Cite this

Li, R., Zhao, X., Yu, X., Li, J., Cheng, N., & Zhang, J. (2010). Incident duration model on urban freeways using three different algorithms of decision tree. In 2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010 (pp. 526-528). Article 5523431 (2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010; Vol. 2). https://doi.org/10.1109/ICICTA.2010.602

@inproceedings{9123db48b84f4fb094ea06ed977ce557,

title = "Incident duration model on urban freeways using three different algorithms of decision tree",

abstract = "Effective incident management requires accurate prediction of incident duration. In this paper, Classification and Regression Tree (CART), CHAID and Exhaustive CHAID is employed to model the incident duration. All 65000 incident records from Beijing Transportation Management Bureau are used for model establishment and another 8000 records for validation. The average relative error of the CART model is 29.5197\% while CHAID is 30.78\%; Exhaustive CHAID is 31.23\%.It shows that the reliability of the three models is quite satisfactory. The average relative error of the prediction on different ring roads of Beijing is approximately the same.",

keywords = "CHAID, Classification and regression tree, Decision tree, Exhaustive CHAID, Incident duration",

author = "Ruimin Li and Xiaoqiang Zhao and Xinxin Yu and Junwei Li and Nan Cheng and Jie Zhang",

year = "2010",

doi = "10.1109/ICICTA.2010.602",

language = "English",

isbn = "9780769540771",

series = "2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010",

pages = "526--528",

booktitle = "2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010",

note = "2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010 ; Conference date: 11-05-2010 Through 12-05-2010",

}

Li, R, Zhao, X, Yu, X, Li, J, Cheng, N & Zhang, J 2010, Incident duration model on urban freeways using three different algorithms of decision tree. in 2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010., 5523431, 2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010, vol. 2, pp. 526-528, 2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010, Changsha, China, 11/05/10. https://doi.org/10.1109/ICICTA.2010.602

Incident duration model on urban freeways using three different algorithms of decision tree. / Li, Ruimin; Zhao, Xiaoqiang; Yu, Xinxin et al.
2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010. 2010. p. 526-528 5523431 (2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Incident duration model on urban freeways using three different algorithms of decision tree

AU - Li, Ruimin

AU - Zhao, Xiaoqiang

AU - Yu, Xinxin

AU - Li, Junwei

AU - Cheng, Nan

AU - Zhang, Jie

PY - 2010

Y1 - 2010

N2 - Effective incident management requires accurate prediction of incident duration. In this paper, Classification and Regression Tree (CART), CHAID and Exhaustive CHAID is employed to model the incident duration. All 65000 incident records from Beijing Transportation Management Bureau are used for model establishment and another 8000 records for validation. The average relative error of the CART model is 29.5197% while CHAID is 30.78%; Exhaustive CHAID is 31.23%.It shows that the reliability of the three models is quite satisfactory. The average relative error of the prediction on different ring roads of Beijing is approximately the same.

AB - Effective incident management requires accurate prediction of incident duration. In this paper, Classification and Regression Tree (CART), CHAID and Exhaustive CHAID is employed to model the incident duration. All 65000 incident records from Beijing Transportation Management Bureau are used for model establishment and another 8000 records for validation. The average relative error of the CART model is 29.5197% while CHAID is 30.78%; Exhaustive CHAID is 31.23%.It shows that the reliability of the three models is quite satisfactory. The average relative error of the prediction on different ring roads of Beijing is approximately the same.

KW - CHAID

KW - Classification and regression tree

KW - Decision tree

KW - Exhaustive CHAID

KW - Incident duration

UR - https://www.scopus.com/pages/publications/77955703099

U2 - 10.1109/ICICTA.2010.602

DO - 10.1109/ICICTA.2010.602

M3 - Conference contribution

AN - SCOPUS:77955703099

SN - 9780769540771

T3 - 2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010

SP - 526

EP - 528

BT - 2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010

T2 - 2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010

Y2 - 11 May 2010 through 12 May 2010

ER -

Li R, Zhao X, Yu X, Li J, Cheng N, Zhang J. Incident duration model on urban freeways using three different algorithms of decision tree. In 2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010. 2010. p. 526-528. 5523431. (2010 International Conference on Intelligent Computation Technology and Automation, ICICTA 2010). doi: 10.1109/ICICTA.2010.602

Incident duration model on urban freeways using three different algorithms of decision tree

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this