Ongoing Research
Deep Learning in Archaeology: Understanding the Composition of Ancient Mortars
Oct. 27, 2022—Mortar is an essential part of construction, and has been used by builders for centuries. Ancient builders prepared them as members of changing communities of practice. But, to what degree did interactions among contemporaries lead to standardized mortars? Did builders learn from culturally different predecessors? In partnership with the Vanderbilt Data Science Institute, Dr. Markus...
Project WISE: Wearables for Teachers, Enabling Real-Time Instructional Feedback
Jan. 18, 2022—Project WISE is working to develop a measurement tool that can measure teachers’ implementation of evidence-based behavior management practices in general and special education classrooms. Typically, researchers and school administrators will use systematic direct observation (SDO) to collect data on teacher practices; however, this can be resource intensive and requires rigorous observer training. The rapid development...
Wearables for Teachers: Enabling Real-Time Instructional Feedback
Aug. 25, 2021—What can I do to provide the best instructional environment for my students? What actions can I take to more effectively manage my classroom and encourage constructive behavior in my students? Vanderbilt alum and Founder and CEO of The Behavior Company Dr. Alyssa Van Camp seeks to provide support to teachers through a wearable which...
Data Science for Social Good: GATEways to Gifted and Talented Education for All
Aug. 12, 2021—Millions of students are missing from Gifted and Talented Education (GATE) classrooms across the United States. What types of students are missing? How does this compare across individual states, counties, and districts, and what can be done at all municipal levels to combat these issues? Director of the Scholar Identity Institute and Vanderbilt Associate Professor...
Improving Ultrasound Image Quality with Deep Learning
Aug. 6, 2021—Ultrasound remains an invaluable tool for clinicians because it is real-time, cost-effective, and portable. However, poor image quality can make diagnostic and guidance tasks with ultrasound unreliable (e.g., tumor and gallbladder boundaries difficult to see in left most figure). Machine learning techniques applied to ultrasound data have had great success for improving image quality. Among...
Data Science for Social Good: Recycling in Nashville
Jul. 6, 2021—Would Nashville even be Nashville without the scores of construction cranes dotting the skyline of the city? Nashville is a rapidly growing and evolving city, in both population and infrastructure. With growth comes construction, renovation, remodeling, and demolition – generating tons of waste which can be responsibly recycled and reused. In 2017, Nashville Public Works initiated...
Data Science for Social Good: Legal Assistance for Tennesseans
Jul. 6, 2021—The need for legal assistance across Tennessee outpaces the capacity of available lawyers. Legal representation is more available in urban than in rural counties, and the magnitude and type of unmet needs in rural counties is unknown. This summer, three Data Science for Social Good Fellows are building predictive models to estimate the number and...