Traffic-event Unification System Highlighting Arterial Roads

The focus of this work is on development of machine learning techniques that use historical and real-time data for fusion of information and detection of incidents and accidents on arterial networks. This research seeks to investigate the application of machine learning in data relevance amplification and incident detection, explore potential challenges and propose innovative solutions. If machine learning can be successfully integrated with existing systems it would potentially open an array of future applications and benefits not only in operations aspects but also in safety, reliability and planning. With automated vehicular technology around the corner, the integration of machine learning with signal systems would provide additional capabilities especially in the transition phase where there will be a mix of automated vehicle (AV), connected vehicle (CV), and manual vehicles creating a complex heterogeneous environment.

    Language

    • English

    Project

    • Status: Active
    • Funding: $299717
    • Contract Numbers:

      BDV31 977-97

    • Sponsor Organizations:

      Florida Department of Transportation

      Research Center
      605 Suwannee Street MS-30
      Tallahassee, FL  United States  32399-0450
    • Project Managers:

      Dilmore, Jeremy

      Ponnaluri, Raj

    • Performing Organizations:

      University of Florida, Gainesville

      219 Grinter Hall
      Gainesville, FL  United States  32611
    • Principal Investigators:

      Ranka, Sanjay

      Rangarajan, Anand

      Srinivasan, Siva

    • Start Date: 20180319
    • Expected Completion Date: 20190915
    • Actual Completion Date: 0

    Subject/Index Terms

    Filing Info

    • Accession Number: 01662968
    • Record Type: Research project
    • Source Agency: Florida Department of Transportation
    • Contract Numbers: BDV31 977-97
    • Files: RiP, STATEDOT
    • Created Date: Mar 20 2018 7:31AM