Classification and Regression Tree Approach for Predicting Drivers’ Merging Behavior in Short-Term Work Zone Merging Areas

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 site in 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.

[1]  Essam Radwan,et al.  Evaluation of New Simplified Dynamic Lane Merging Systems (SDLMS) for Short-Term Work Zone Lane Closure Configuration , 2011 .

[2]  Christopher K Strong,et al.  Collecting Vehicle-Speed Data by Using Time-Lapse Video Recording Equipment , 2003 .

[3]  Andrzej P. Tarko,et al.  SAFETY AND CAPACITY EVALUATION OF THE INDIANA LANE MERGE SYSTEM , 2001 .

[4]  Qiang Meng,et al.  An improved cellular automata model for heterogeneous work zone traffic , 2011 .

[5]  Harilaos N. Koutsopoulos,et al.  A microscopic traffic simulator for evaluation of dynamic traffic management systems , 1996 .

[6]  Toshiyuki Yamamoto,et al.  Drivers’ Route Choice Behavior: Analysis by Data Mining Algorithms , 2002 .

[7]  Xuedong Yan,et al.  Classification analysis of driver's stop/go decision and red-light running violation. , 2010, Accident; analysis and prevention.

[8]  Haris N. Koutsopoulos,et al.  Integrated driving behavior modeling , 2007 .

[9]  Hideyuki Kita,et al.  A merging–giveway interaction model of cars in a merging section: a game theoretic analysis , 1999 .

[10]  Tommy Gärling,et al.  Computational-Process Modelling of Household Activity Scheduling , 1993 .

[11]  Michael Schreckenberg,et al.  Particle hopping models for two-lane traffic with two kinds of vehicles: Effects of lane-changing rules , 1997 .

[12]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[13]  Tapan K. Datta,et al.  Dynamic Late Lane Merge System at Freeway Construction Work Zones , 2007 .

[14]  Qiang Meng,et al.  Decision Tree–Based Model for Estimation of Work Zone Capacity , 2011 .

[15]  Geert Wets,et al.  Identifying Decision Structures Underlying Activity Patterns: An Exploration of Data Mining Algorithms , 2000 .

[16]  Kerrie L Schattler,et al.  ASSESSING THE IMPACTS OF THE DYNAMIC EARLY LANE MERGE TRAFFIC CONTROL SYSTEM , 2003 .

[17]  Qiang Meng,et al.  Cellular Automata Model for Work Zone Traffic , 2010 .

[18]  Tarek Sayed,et al.  Modeling Driver Behavior and Safety on Freeway Merging Areas , 2008 .

[19]  Chuck Louisell.  A Simple Algorithm for Quantifying the Impact of Driver Behavior on Traffic Flow and Safety During Forced Merges in Work Zones , 2006 .

[20]  Hideyuka Kita,et al.  EFFECTS OF MERGING LANE LENGTH ON THE MERGING BEHAVIOR AT EXPRESSWAY ON-RAMPS. , 1993 .