B. Aditya Prakash, an assistant professor of computer science in Virginia Tech’s College of Engineering has received a Faculty Early Career Development (CAREER) Award from the National Science Foundation to help improve national security and public health.

Prakash is working to prove that data-driven approaches can provide “real-time” and flexible options to standard model-based strategies that affect national security, public health, and other network-based phenomena.

This year’s massive flu outbreak is one example of how Prakash’s network-based research can be applied to public health crises.

“If we use data gathered from patient visits and are also able to determine how people come into contact with each other, vaccines could be distributed to people in a more targeted manner, like aiming for infection ‘hotspots,’ to stop the flu from spreading faster. We can also use the data to develop more responsive immunization policies,” said Prakash.

Prakash, who is also a faculty member at the Discovery Analytics Center, has been collaborating with Oak Ridge National Laboratory, utilizing more than a billion anonymized influenza-related electronic medical claims records nationwide to inform his research.

The five-year, $550,000 NSF CAREER award will help Prakash develop more data-driven tools, like the one he developed to study the flu, to understand and control network-based propagation phenomena across many different systems.

In Prakash’s research, networks can be anything from social networks to population networks to computer networks. Many phenomena can be abstracted as a contagion propagating over these underlying networks.

“With social media, our work can help monitor viral posts for insights on stopping rumors and misinformation. In cybersecurity, we can help reconstruct and fill gaps in malware traces to better prioritize response,” said Prakash. “The same applies for failure events in critical infrastructure networks, like power and communication, during disasters.”

Prakash is also committed to strengthening the big data and network mining curriculum at Virginia Tech. He is already fostering interdisciplinary problem solving in his classes of students with majors ranging from the social sciences to engineering to physics and agriculture.

“Students get excited when I explain how we can combine graph theory, sociological models, and the idea of phase transitions to develop more efficient immunization algorithms,” he said.

The award will allow Prakash to further extend educational and research opportunities to students with non-computer science backgrounds while supporting data mining for the public good. He will also leverage Virginia Tech programs, like the Student Transition Engineering Program, to extend outreach.

Prakash’s research interests include data mining, applied machine learning, and databases, with an emphasis on big data problems in large real-world networks and sequences. He has published one book, written multiple award-winning papers, and obtained two U.S. patents.

“Coupled with increasing computing capacity, trends in collecting electronic health records, online media, and sensor monitoring have made observing and acquiring large amounts of data — sometimes in real-time — not only easier, but less expensive,” Prakash said. “Designing more general, more robust methods that do not rely on single specific models has the potential to significantly enhance the reach of network mining into nontraditional and innovative areas.”

Established in 1995, the NSF CAREER Award is the most prestigious award given by the NSF in support of junior faculty who demonstrate the potential to effectively integrate research and education.

Written by Barbara L. Micale

Share this story