Please use this identifier to cite or link to this item: https://doi.org/10.1061/(ASCE)TE.1943-5436.0000412
Title: Classification and regression tree approach for predicting drivers' merging behavior in short-term work zone merging areas
Authors: Meng, Q. 
Weng, J.
Keywords: Accuracy
Decision making
Driver behavior
Merging
Vehicle
Work zone
Issue Date: Aug-2012
Source: Meng, Q., Weng, J. (2012-08). Classification and regression tree approach for predicting drivers' merging behavior in short-term work zone merging areas. Journal of Transportation Engineering 138 (8) : 1062-1070. ScholarBank@NUS Repository. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000412
Abstract: This study aims to use the classification and regression tree (CART) approach, one of the most powerful data mining techniques, to predict drivers' merging behavior in a work zone merging area. On the basis of the eight factors affecting drivers' merging behavior, a binary CART is built using the merging traffic data collected from a short-term work zone sitein Singapore. The CART comprises 7 levels and 15 leaf nodes to predict drivers' merging behavior in the work zone merging area. The results show that the CART provides much higher prediction accuracy than the conventional binary logit model. Traffic engineers can easily understand how drivers make merging/nonmerging decisions. This demonstrates that the CART approach is a good alternative for investigating drivers' merging behavior in work zone merging areas. © 2012 American Society of Civil Engineers.
Source Title: Journal of Transportation Engineering
URI: http://scholarbank.nus.edu.sg/handle/10635/58984
ISSN: 0733947X
DOI: 10.1061/(ASCE)TE.1943-5436.0000412
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

12
checked on Dec 14, 2017

WEB OF SCIENCETM
Citations

9
checked on Nov 17, 2017

Page view(s)

31
checked on Dec 17, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.