K-Mean Clustering in Transportation: A Work Zone Simulator Case Study

Abstract

Transportation engineering considers many different categories such as accident management, infrastructure management, driver behavior, and traffic management and generates large amount of data. Data mining methods are a common engineering approach to understand data-intensive scenarios and use techniques to extract patterns, correlations, and information from large amounts of data. This research uses a simulator to compare driver patterns and behaviors when comparing reactions to the Missouri Department of Transportation (MoDOT) alternate sign with the Manual on Uniform Traffic Control Devices (MUTCD) current sign. K-mean clustering method is used to cluster driver response to work zone sign configurations presented in the simulator environment and uncover patterns that can assist engineers with usability of work zone signage. Key findings of this research will help the transportation engineering manager make data-driven decisions regarding work zone safety and design.

Meeting Name

2017 International Annual Conference of the American Society for Engineering Management, ASEM 2017 (2017: Oct. 18-21, Huntsville, AL)

Department(s)

Engineering Management and Systems Engineering

Research Center/Lab(s)

Intelligent Systems Center

Comments

This study is sponsored by Missouri Department of Transportation under grant number TR201612.

Keywords and Phrases

Data mining; Decision analytics; Pattern recognition; Transportation

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2017 American Society for Engineering Management (ASEM), All rights reserved.

Publication Date

01 Oct 2017

This document is currently not available here.

Share

 
COinS