Streamlining and automating the process of electronically rejuvenating medieval artwork by using a 14th-century altarpiece by Francescussio Ghissi as a working example.
Below is an example of the kinds of projects at Duke that have used innovative data-driven approaches to explore interdisciplinary topics. With these projects, students learn how to marshal, analyze, and visualize data, while gaining broad exposure to data science concepts, methods, and tools. The MIDS program encourages students to participate in small projects like these to hone their domain knowledge and technical expertise.
Understanding the myriad academic pathways traveled by undergraduate students at Duke focusing on data from Mathematics and the Duke Global Health Institute.
Automating the diagnosis of vascular anomalies from Doppler Ultrasound data, with goals of improving diagnostic accuracy and reducing physician time spent on simple diagnoses.
Data-driven analysis of the representation of women in film and in the film industry, with special attention to a metric called the Bechdel Test and working with data from a number of sources, including fivethirtyeight.com and the-numbers.com.
Working with Counter Tools, a local nonprofit that provides support to over a dozen state health departments, trying to understand how open source data can lead to the creation of a national database of tobacco retailers.
Combining success metrics of Duke Surgery residents from a set of databases and creating a user interface for residency program directors and possibly residents themselves to view and better understand residency program performance.
Prototyping interactive interfaces from Type II diabetics' mobile health data to encourage patient self-management and to effectively inform clinicians about patient behavior between visits.