Trajectory Data Mining for Performance Measurement of Public Transportation Systems

The main objective of this proposal is to develop a system that can process massive amounts of global positioning system (GPS) trajectories from public transportation vehicles and implement statistical algorithms to analyze variety of public transportation system performance metrics such as travel-time reliability, on-time performance, bus bunching and travel-time estimation. To this end, the project will conduct fundamental research in mining and correlation of real-time and historical bus GPS trajectory datasets in Los Angeles (LA) County, which the project have collected and archived in the projects database over the past four years. Furthermore, to demonstrate the benefits of this research, the project will develop a novel proof-of-concept web-based application to enable access and visualization of the performance metrics of public transportation vehicles. This research will exploit the real-world Los Angeles traffic sensor and bus GPS datasets collected from Regional Integration of Intelligent Transportation Systems (RIITS) under Archived Traffic Data Management System (ADMS) project.

• Record URL:
  https://www.metrans.org/research/trajectory-data-mining-performance-measurement-public-transportation-systems

Language

• English

Project

• Status: Active
• Funding: $100,000
• Contract Numbers:

  65A0533

• Sponsor Organizations:

  California Department of Transportation

  1227 O Street
  Sacramento, CA  United States  95843

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Project Managers:

  Deguzman, Victoria

• Performing Organizations:

  National Center for Metropolitan Transportation Research

  University of Southern California
  650 Childs Way, RGL 107
  Los Angeles, CA  United States  90089-0626
• Principal Investigators:

  Demiryurek, Ugur

• Start Date: 20170101
• Expected Completion Date: 20171231
• Actual Completion Date: 0

Subject/Index Terms

• TRT Terms: Bus transit; Data mining; Global Positioning System; On time performance; Public transit; Traffic data; Travel time
• Geographic Terms: Los Angeles County (California)
• Subject Areas: Data and Information Technology; Operations and Traffic Management; Public Transportation;

Filing Info

• Accession Number: 01618767
• Record Type: Research project
• Source Agency: National Center for Metropolitan Transportation Research
• Contract Numbers: 65A0533
• Files: UTC, RiP
• Created Date: Dec 12 2016 9:35AM