Analysis and Prediction of Spatiotemporal Impact of Traffic Incidents for Better Mobility and Safety in Transportation Systems

In this proposal, the authors propose to study a machine learning approach to predict the spatiotemporal impact of traffic accidents on the upstream traffic and the surrounding region. The main objective of the authors' research is to forecast how and when the travel-time delays - caused by road accidents - will occur on the transportation network in both time and space. Towards this end, the authors will conduct fundamental research in mining and correlation of traffic incidents and sensor datasets that they have been collecting and archiving in the last past three years. Furthermore, to demonstrate the benefits of their research, the authors will develop a novel proof-of-concept mobile application and extend their existing web based application to enable monitoring and querying of the incident impacts on real-time and historical datasets. This research will exploit the real-world Los Angeles traffic sensor data and California Highway Patrol (CHP) accident logs collected from Regional Integration of Intelligent Transportation Systems (RIITS) under Archived Traffic Data Management System (ADMS) project. The mobile application developed as a result of this proposal will be released for public use.

• Record URL:
  http://www.metrans.org/research/analysis-and-prediction-spatiotemporal-impact-traffic-incidents-better-mobility-and-safety
• Supplemental Notes:
  • http://infolab.usc.edu/research.php#traffic_prediction

Language

• English

Project

• Status: Completed
• Funding: $99,999
• Contract Numbers:

  65A0533

• Sponsor Organizations:

  Research and Innovative Technology Administration

  University Transportation Centers Program
  1200 New Jersey Avenue
  Washington, DC  United States  20590

  California Department of Transportation

  1120 N Street
  Sacramento, CA  United States  95814
• Project Managers:

  Valentine 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

  Shahabi, Cyrus

• Start Date: 20150101
• Expected Completion Date: 0
• Actual Completion Date: 20151231
• Source Data: RiP Project 37357

Subject/Index Terms

• TRT Terms: Data mining; Intelligent transportation systems; Machine learning; Mobile applications; Sensors; Traffic crashes; Traffic delays; Traffic incidents; Traffic safety
• Identifier Terms: California Highway Patrol
• Uncontrolled Terms: Spatiotemporal analysis
• Geographic Terms: Los Angeles (California)
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Safety and Human Factors;

Filing Info

• Accession Number: 01602382
• Record Type: Research project
• Source Agency: National Center for Metropolitan Transportation Research
• Contract Numbers: 65A0533
• Files: UTC, RiP
• Created Date: Jun 21 2016 1:00AM