Best Practices for Data Fusion of Probe and Point Detector Data

Data fusion is defined as the process of integrating multiple data sources to produce more consistent, accurate, and useful information than that provided by any individual data source. Research is needed to define the types and characteristics of data for entry into a data fusion engine. This research should delineate the challenges, issues, and best practices for performing data fusion by agencies to estimate or predict travel time, speed, and reliability on road networks. Road traffic datasets of interest include traditional inductive loop detectors; Bluetooth; GPS devices embedded in smartphones, personal navigation devices, taxis, fleets, and other sources; third-party travel time data; and emerging connected vehicle data sets. The objective of this project is to identify the data and data fusion algorithms that will enable road operators to better understand the traffic state on their network for both operations and planning applications. This will be achieved by fusing data from multiple traffic data sources that have differing spatial and temporal characteristics. The project will develop a clear pathway from data selection to fusion model selection that is implementable in the field by agency staff or their contractors. The research will promote the adoption of data fusion technology for improving the safety and efficiency of traffic management by developing (a) a data characterization catalog that assesses the suitability of sensor data as an input into a data fusion process; (b) a decision process that enables the choice of data fusion model and provides guidance on the expected information gain; and (c) methods to estimate the traffic state and the reliability of the estimate considering various traffic flow and data availability scenarios. By enabling better knowledge of the network state, the outcomes of the proposed research will enable improved traffic management and planning decisions. Even a 5% reduction in congestion will produce large economic savings. The economic cost of traffic crashes was estimated at $871 billion in 2013. Improved network state estimates will enable enhanced safety outcomes by identifying locations with high crash rates and anomalous traffic flow conditions.

Language

  • English

Project

  • Status: Proposed
  • Funding: $200000
  • Contract Numbers:

    Project 08-157

  • Sponsor Organizations:

    National Cooperative Highway Research Program

    Transportation Research Board
    500 Fifth Street, NW
    Washington, DC  United States  20001

    American Association of State Highway and Transportation Officials (AASHTO)

    444 North Capitol Street, NW
    Washington, DC  United States  20001

    Federal Highway Administration

    1200 New Jersey Avenue, SE
    Washington, DC  United States  20590
  • Project Managers:

    Jared, David

  • Start Date: 20210525
  • Expected Completion Date: 0
  • Actual Completion Date: 0

Subject/Index Terms

Filing Info

  • Accession Number: 01772924
  • Record Type: Research project
  • Source Agency: Transportation Research Board
  • Contract Numbers: Project 08-157
  • Files: TRB, RIP
  • Created Date: May 24 2021 3:14PM