The second Strategic Highway Research Program (SHRP2) is at the forefront of transportation innovation. The safety focus area of SHRP 2 conducted the largest naturalistic driving study (NDS) in the world to better understand the interaction among various factors involved in highway crashes—drivers, vehicles, traffic, environmental conditions, and infrastructure. This rich dataset is available for researchers to explore and uncover the clues of how the interacting factors led to the various types of roadway crashes. Knowledge gained through this work will help develop better safety countermeasures to save lives and reduce injury severity. The SHRP2 safety study produced two major datasets:
(1) NDS Dataset, https://insight.shrp2nds.us/documents/shrp2_background.pdf, which recorded the daily driving activities of 3,400 plus participants in six study sites in the US over a 1–2 year period. This dataset consists of detailed vehicle, driver, and driving information on approximately 5.4 million trips taken by the participants during their monitoring period, including over 1,400 crashes and nearly 3000 near-crashes.
(2) Roadway Information Database (RID), http://www.ctre.iastate.edu/shrp2-rid/, a geospatial database that provides the context (e.g., roadway features and characteristics, traffic volumes, crash histories, and weather) for the millions of NDS trips.
The applicant will collaborate with staff members of the FHWA Safety Training and Analysis Center (STAC, http://www.fhwa.dot.gov/research/resources/stac/), housed within Turner Fairbank Highway Research Center in McLean, VA. The goals of this research are to (1) conduct multivariate data analyses of the SHRP 2 datasets to better understand crashes and near crashes and the casual role of human behavior; (2) investigate the contributing factors to crash severity (e.g., roadway characteristics and features, vehicle speed, seat belt use, etc.); and (3) develop data mining techniques and predictive models for crashes and near crashes.
Experience with analyses of NDS data sets is highly desirable. Talented data analysts with innovative ideas and expertise in analyzing big datasets involving geospatial information, large volumes of text data, and video data are encouraged to apply. Candidates should have demonstrating skills with statistical programs (e.g., R, SAS, etc.), geospatial programs (e.g., ArcGIS), Python, and Matlab.
Thor CP, Gabler HC: Assessing the Residual Teen Crash Risk Factors after Graduated Driver’s License Implementation. Annals of Advances in Automotive Medicine, October 2010
Naturalistic driving; Geographic information systems; Highway safety; Statistical analyses; Crash surrogates;