Predicting Travel Time on Freeway Corridors: Machine Learning Approach

Estimating the travel time of any segments on freeways is of great importance to route planning, traffic monitoring, and bottleneck identification. Many researchers have conducted numerous studies on estimating travel time. However, travel time forecasting is still a very challenging problem since it can be affected by diverse complex factors, including spatial correlations, temporal dependencies, and external conditions (e.g., weather). The purpose of this project is to develop machine learning approach that incorporates the stochastic characteristics of segments to model the travel time on a freeway corridor. Segment travel time correlations will be analyzed and examined using an advanced model (e.g., pattern recognition model and neural network model) based on historical travel time data. To evaluate the quality of such model, other models (including time-series models, and linear regression models) which may not explicitly consider spatial-temporal correlations between segment travel times will also be developed. The proposed approach will be developed, used and tested to analyze and predict the travel time on several freeway corridors in Charlotte, North Carolina using vehicle probe data. The advantages and disadvantages of each model will also be identified and compared.

Language

• English

Project

• Status: Completed
• Funding: $90007
• Contract Numbers:

  69A3551747133

• Sponsor Organizations:

  Center for Advanced Multimodal Mobility Solutions and Education

  University of North Carolina, Charlotte
  Charlotte, NC  United States  28223

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  University of North Carolina, Charlotte

  Department of Civil and Environmental Engineering
  9201 University City Boulevard
  Charlotte, NC  United States  28223-0001
• Project Managers:

  Fan, Wei

• Performing Organizations:

  Center for Advanced Multimodal Mobility Solutions and Education

  University of North Carolina, Charlotte
  Charlotte, NC  United States  28223
• Principal Investigators:

  Fan, Wei

• Start Date: 20181001
• Expected Completion Date: 20200930
• Actual Completion Date: 20200930

Subject/Index Terms

• TRT Terms: Artificial intelligence; Data analysis; Data fusion; Estimating; Freeways; Machine learning; Probe vehicles; Travel time
• Geographic Terms: Charlotte (North Carolina)
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Planning and Forecasting;

Filing Info

• Accession Number: 01699738
• Record Type: Research project
• Source Agency: Center for Advanced Multimodal Mobility Solutions and Education
• Contract Numbers: 69A3551747133
• Files: UTC, RiP
• Created Date: Mar 24 2019 3:34PM