ABJ30 Members and Friends –

It is time to spread the word about the Transportation Data Competition – please help us make this another big success!!!

Call for Participation – 2014 TRB Annual Meeting Workshop

Transportation Data Competition

Sponsoring Committee: ABJ80 Statistical Methods

Co-Sponsoring Committees: ABJ00 Data Section

ABJ70 Artificial Intelligence and Advanced Computing Applications

ABJ20 Statewide Transportation Data and Information Systems

ABJ50 Information Systems and Technology
AND10 Vehicle User Characteristics
AND30 Simulation and Measurement of Operator Performance

Call Description: Successfully understanding road user behavior is essential for the design, implementation, and operation of a transportation system. The use of complex datasets generated from simulators and instrumented vehicles have attracted considerable attention by both transportation researchers and practitioners, with analysis efforts ranging from classical statistics to a vast array of computational intelligence (CI) techniques.

In an era of rapid technological and scientific advances, the transportation community experiences an increase in data collection and availability, along with powerful analytical tools. Nevertheless, transportation data often pose considerable challenges to researchers and practitioners: differences in data measurement techniques and frequencies, seasonality, local trends, appropriate assumptions, outliers, zero and missing values, and so on. The demands for data by transportation services have become increasingly complex and more demanding; for example, real time control and Intelligent Transportation Systems (ITS) often require short-term predictions of transportation conditions based on existing data.

In this context, the Transportation Research Board is pleased to announce the 2014 Transportation Data Competition workshop, to be held at the 93rd TRB Annual meeting. The scope of the competition is to evaluate the appropriateness of various data analytic methodologies – be they statistics, artificial intelligence, or advanced data visualization– for forecasting trends in safety, with particular attention to missing and incomplete data. The objective is to identify modelling tools in statistics and artificial intelligence for forecasting and to disseminate knowledge on “best practices” in transportation data modeling. The dataset used for this competition will be based on a data set on driver behavior, using data from the National Advanced Driving Simulator (NADS), in which drivers traverse an intersection with a traffic signal that may change from green to yellow phase.

This data analysis competition is open to all areas of statistics, biostatistics, econometrics and computational intelligence.

Researchers, as individuals or groups will participate using the data set provided. Participants will present their results at the 93rd TRB annual meeting workshop, devoted to the Transportation Data Competition to be held Sunday January 12, 2014. Awards will be given to researchers and researcher teams based on: 1) appropriateness of predictions; 2) completeness of a short paper detailing the approach used, advantages and disadvantages, and results.

For more information and for obtaining the data sets please go to the following website after Aug 15, 2013: http://depts.washington.edu/hfsm/.

Subject Areas: Safety, Forecasting, Statistics, And Computational Intelligence

Organizers: Linda Ng Boyle, University of Washington (linda@uw.edu), Matthew G. Karlaftis, National Technical University of Athens (mgk@mail.ntua.gr), and Susan Chrysler, University of Iowa (susan-chrysler@uiowa.edu).

Timeline:

August 15th, 2013 – Data will be available at http://depts.washington.edu/hfsm/.

November 30th, 2013 – Deadline for submission of results and short papers by e-mail.

December 10th , 2013 - Notification to the “winners,” or presenters at the Sunday workshop

January 12th, 2014 - Transportation Data Competition Workshop (13:30-16:30)