NCHRP Research Report 1127 presents a guide for facilitating data fusion and improving data reporting to support traffic management at state departments of transportation (DOTs). This guide provides an overview of pertinent transportation data for fusion, considerations before initiating data fusion, and a proposed framework for fusion of point and probe data. Real-world use-cases demonstrating application of the framework are also included. The guide should be of interest to a broad cross-section of staff at state DOTs seeking to understand the relevance and importance of data fusion, implement it within their agency, and collaborate with other staff in the process.
Data fusion is the process of integrating multiple data sources to produce more consistent, accurate, and comprehensive information than that provided by any individual data source. In a transportation context, state DOTs are seeking to (1) define the types and characteristics of data for entry into data fusion engines; and (2) identify the challenges, issues, and proven or potential practices for performing data fusion to measure or forecast travel time, speed, reliability, and other aspects of operational performance on roadway networks. Traffic datasets of interest include point sensors; Bluetooth; data from GPS devices embedded in smartphones, personal navigation devices, taxis, and fleets; third-party travel time data; and emerging connected vehicle (CV) data sets. Better knowledge of the network state could help improve traffic management and planning decisions to address impacts of recurrent and non-recurrent congestion. Improved network state estimates could also enhance safety outcomes by identifying locations with high crash rates and anomalous traffic flow conditions.
Under NCHRP Project 08-158, “Best Practices for Data Fusion of Probe and Point Detector Data,” MLP LLC was asked to develop (1) a process to identify specific objectives for data fusion and specific data sources; and (2) a guide for state DOTs to facilitate data fusion, improve data reporting, and ultimately improve traffic management. The guide is divided into sections to serve multiple audiences. Chapters 1 through 4 are for all transportation professionals regardless of background or position. Chapter 5, the data fusion framework, has been divided into sections for specific audiences: (1) for executives, a high-level overview of the framework step, explaining its relevance and importance to their agency; (2) for systems implementers, deeper details that someone charged with implementing the data fusion algorithms and technologies would likely need to know; and (3) for traffic systems management and operations (TSMO) professionals, sufficient knowledge to facilitate collaboration with systems implementers.
In addition to NCHRP Research Report 1127, two deliverables are not included in the published report but are available on the TRB website at trb.org by searching for NCHRP Research Report 11xx. The deliverables are as follows: (1) a plan that identifies mechanisms and channels for communicating and implementing this research; and (2) a PowerPoint presentation introducing NCHRP Research Report 1127.