Center for Data Reduction and Analysis Support

The Center for Data Reduction and Analysis Support (CDRAS) supports standardized access to and analysis of numerous naturalistic driving study data sets (currently 2.5 PB) housed at the Virginia Tech Transportation Institute for researchers within and outside of the institute. Services include coding of video and audio data, data quality assurance, data standardization, data mining, event selection, and data analysis. The center actively supports data analysis collaborations with external institutions.

Miguel Perez
Center Director

SHRP2 NDS Data Dissemination and User Technical Support

Projects are focused on the accessibility and application assistance of general use data files and interfaces to support data users, including those that are not SHRP 2 contractors. As part of this effort, reduced or de-identified files such as trip files, event files, and other reduced or aggregated files were developed to provide easier access to the SHRP 2 naturalistic driving study data. The projects included the production and distribution of early results from the NDS data, data documentation, webinars, workshops, and other training and communication activities. Read More

SHRP2 NDS Data Dissemination and User Technical Support

Projects are focused on the accessibility and application assistance of general use data files and interfaces to support data users, including those that are not SHRP 2 contractors. As part of this effort, reduced or de-identified files such as trip files, event files, and other reduced or aggregated files were developed to provide easier access to the SHRP 2 naturalistic driving study data. The projects included the production and distribution of early results from the NDS data, data documentation, webinars, workshops, and other training and communication activities.

Additionally, researchers provided technical support for users of the SHRP 2 NDS data. This technical support included initial or ongoing data access consulting, assistance in the preparation of specialized data files for analysis, video reduction, consulting, data access, data linking, data transformations, data tabulations, specialized data subsets, manual or automated video analysis, use of the VTTI secure data enclave to access restricted data, and other support which facilitated use of the NDS data. Researchers provided one-on-one and need-specific support for individual users of NDS data.

Shanghai NDS Study

The Virginia Tech Transportation Institute (VTTI) and its research partners are transitioning lessons learned about conducting naturalistic driving research to China. Tongji University of Shanghai, General Motors, and VTTI are collaborating to study driving in Shanghai, the most populated city in China, with over 20 million people and two million cars. The project is the first study outside of the U.S. to use the NextGen data acquisition system developed by VTTI to collect vehicle, traffic, and driver behavior data. Read More

Shanghai NDS Study

The Virginia Tech Transportation Institute (VTTI) and its research partners are transitioning lessons learned about conducting naturalistic driving research to China. Tongji University of Shanghai, General Motors, and VTTI are collaborating to study driving in Shanghai, the most populated city in China, with over 20 million people and two million cars. The project is the first study outside of the U.S. to use the NextGen data acquisition system developed by VTTI to collect vehicle, traffic, and driver behavior data.

In the past few decades, China has grown to the world’s largest automobile market in production and sales. At the same time, the traffic accident and fatality rate in China is substantially higher than the U.S. and other industrial counties. The project will recruit 90 participants to drive five General Motors vehicles instrumented with the NextGen system over a three-year study period.

"This project provides a unique opportunity to provide crucial information on the traffic flow characteristics and driver behaviors in one of China's major cities, and an opportunity to compare driving behavior and traffic conditions internationally," said the project's principal investigator Feng Guo, an assistant professor of statistics in the College of Science at Virginia Tech and Virginia Tech Transportation Institute.

Virginia Tech Transportation Institute strives to advance transportation through innovation and to impact public policy on the national and international level.

Support for FHWA Safety Training and Analysis Center

The SHRP2 Safety Data consists of an extensive collection of detailed information describing the driver, vehicle, trip, and roadway. The driver, vehicle and trip information is referred to as NDS data, while the roadway data is referred to as RID data. Read More

Support for FHWA Safety Training and Analysis Center

The SHRP2 Safety Data consists of an extensive collection of detailed information describing the driver, vehicle, trip, and roadway. The driver, vehicle and trip information is referred to as NDS data, while the roadway data is referred to as RID data. The NDS data contains information from over 3,000 volunteer drivers, during a three year data collection period amounting to over 30 million vehicle miles, 5+ million trip files, over 3,900 vehicle years, and more than 1 million hours of video. In addition to video, other sensor data were collected continuously over the entire trip. The RID consists of two general types of data – 1) new roadway data that was collected consistently across the six study sites by mobile data collection vehicles, and quality assured to meet project specifications, and 2) existing data acquired from state DOTs and other public sources. The coverage of the new data is approximately 12,500 centerline miles across the study sites, and in addition to the roadway characteristics and features collected, includes a high definition (HD) video-log. The coverage of the acquired existing data is approximately 200,000 centerline miles. In addition to the state roadway inventory files, it includes supplemental data on traffic volumes, weather, work zones, crash histories, and safety laws. The RID includes over 800 gigabytes of spatial and acquired aerial imagery data, plus an 8 terabyte HD video log. Data access is provided to qualified researchers who have completed the Data Use License (DUL) process.

The Federal Highway Administration (FHWA) has established the STAC – which is located at the Turner-Fairbank Highway Research Center (TFHRC) in McLean, VA – to support the research community with the SHRP2 NDS and RID, including piloting a secure data enclave to remotely access the SHRP2 NDS data.

The objective of this task order is to provide technical support to STAC, related to secure remote access and use of the SHRP2 NDS data.

Generation of de-identified SHRP2 trip traces

The objective of this project is to describe the nature of a trip (trip-purpose, in modeling terms) without revealing personally identifying information. A method to retrieve generic location categories from Google Maps has been developed and is being applied on the Raleigh, North Carolina portion of the SHRP2 NDS data set. Buffers around coordinate pairs are being tested. Read More

Generation of de-identified SHRP2 trip traces

The objective of this project is to describe the nature of a trip (trip-purpose, in modeling terms) without revealing personally identifying information. A method to retrieve generic location categories from Google Maps has been developed and is being applied on the Raleigh, North Carolina portion of the SHRP2 NDS data set. Buffers around coordinate pairs are being tested.

Location categories are things like:

  • Public places
  • Health
  • Store
  • Religious
  • Automotive
  • Food

A data reduction protocol that can be used by other analysts will be developed to identify high frequency personal locations such as work or home. The test project will be completed in 2018, with potential funding for a project to work on the full SHRP2 dataset in 2019.

Data Reduction Group

Julie McClafferty
Group Leader

The Data Reduction Group serves many different research groups, both within and outside of VTTI, whose research requires video and/or audio analysis in the areas of driver performance and behavior metrics, situational analyses, and environmental characteristics. Its goal is to provide efficient, accurate, and comprehensive coding of videos to meet the specific needs of each unique research project. Our work begins with conducting necessary groundwork to prepare a video dataset for analysis and working alongside the researcher to develop a data reduction protocol. We then train and manage the required data reduction staff, conduct extensive quality control throughout the reduction phase, and prepare final sets of coded data. In addition to the Group Leader, the group currently encompasses an analyst, a team of coordinators, a trainer, and support staff as well as a large staff of Data Reductionists housed within three Data Reduction Labs with nearly 50 combined workstations. The labs currently operate six days a week, 60 hours per week.

Logan Blankenbeckler

Data Reduction Coordinator

Ben Boucher

Data Reduction Coorindator

Shannon Lipscomb

Data Reduction Coordinator

Sarah Robinson

Data Reduction Coordinator

Brunilda Swannell

Data Integrity Coordinator

Stuart Walker

Project Associate

Ethel Wiersma

Data Reduction Training Specialist

Data Analysis Support

The Data Analysis Support Group facilities analysis of naturalistic driving data by providing timely and efficient access to the data sets hosted at the Virginia Tech Transportation Institute. The group is composed of experts in data preparation, standardization, mining, and analysis. Analysis support services are provided to any organization interested in utilizing large-scale driving data sets.

Jeremy Sudweeks
Group Leader

Whitney Atkins

Senior Research Specialist

Julie Cook

Research Associate

Kenny Custer

Data Analyst

Maryam Davoodi

Research Associate

Youjia Fang

Research Associate

Feng Guo

Statistician

Charles Layman

Project Associate

Suzie Lee

Project Director

Devon Moeller

Project Associate

Rufina Savio

Project Associate

Edie Sears

Senior Project Associate

Tina Witcher

Senior Project Associate