The National Academies

NCHRP 08-157 [Anticipated]

Best Practices for Data Fusion of Probe and Point Detector Data

  Project Data
Source: Ohio DOT
Funds: $200,000
Staff Responsibility: David M. Jared
Fiscal Year: 2022

This project has been tentatively selected and a project statement (request for proposals) is expected to be available on this website. The problem statement below will be the starting point for a panel of experts to develop the project statement.

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.


To create a link to this page, use this URL: http://apps.trb.org/cmsfeed/TRBNetProjectDisplay.asp?ProjectID=5135