The Discovery Analytics Center was strongly represented at the IEEE International Conference on Data Mining (ICDM) in New Orleans, Nov. 18-21, with a number of accepted research papers by DAC faculty and students and DAC faculty serving on committees and panels.
Brian Goode focused on data-driven and process-driven approaches to create predictive models for six outcomes of 4,242 participants. He presented his work at the Fragile Families Challenge Scientific Workshop at Princeton University last week. Click here to read more about Brian’s award.
Elaheh Raisi, a computer science Ph.D. student in the Discovery Analytics Center and her advisor, Bert Huang, assistant professor in the Department of Computer Science, were recently honored with the Best Paper Award at the 2017 IEEE/Association for Computing Machinery International Conference on Advances in Social Networks Analysis and Mining (ASONAM), in Sydney, Australia.
A Center for American Progress report on using open data standards to enhance the quality and availability of online job postings has highlighted the Gov. Terry McAuliffe’s Commonwealth Consortium for Advanced Research and Statistics (CCARS) and its work with the Discovery Analytics Center at Virginia Tech to develop the Open Data, Open Jobs Initiative. The goal of the pilot was to capture and publish a real-time structured data feed of all online job postings in Virginia that would serve as a proof of concept.
Rupinder Paul Khandpur, a DAC Ph.D student in computer science, was invited to speak to a group of analysts at the 2017 International Conference on Cyber Conflict (CyCon). The conference, held in Tallinn, Estonia, focused on the fundamental aspects of cyber security with a theme of Defending the Core.
DAC and the Biocomplexity Institute are leading a $3 million grant awarded by the Defense Advanced Research Projects Agency (DARPA) as part of the Next Generation Social Science (NGS2) program. DAC and BI will conduct research that will streamline modeling processes, experimental design, and methodology in the social sciences. A major objective of the project is to make social science experiments rigorous, reproducible, and scalable to large populations.
New interdisciplinary certificate in urban computing, part of National Science Foundation (NSF) Research Traineeship UrbComp Program, is now available to all Virginia Tech graduate students. Administered through the Discovery Analytics Center, the 12-credit certificate program weaves interdisciplinary applications through new courses and a novel “tapestry” curriculum.
These courses are designed to train students to become competent problem solvers by developing computational models of urban populations from disparate data sources and posing and answering what-if questions via machine learning and visualization methodologies. Students are also trained in the ethical and professional implications of working with massive datasets. Click here to read more about the certificate.
DAC director, Naren Ramakrishnan, takes part in a VT Engineering team leading a three-year, $1.4 million National Science Foundation (NSF) grant to develop a new planning framework for smart, connected, and sustainable communities. The team wants smart cities to features zero energy, zero outage, and zero congestion. They are utilizing big data and interdisciplinary technology as tools to meet that goal. Click here to read more about the project.
Great coverage of DAC Ph.D. student Yaser Keneshloo’s research in collaboration with the Washington Post on applying data science to predict the popularity of news articles. Keneshloo and the Post are working on a popularity prediction experiment, they are doing clickstream analysis and producing a pipeline for processing tens of millions of daily clicks, for thousands of articles. Click here to read more about Keneshloo’s project.
Congratulations to Chandan Reddy, DAC faculty member and associate professor of Virginia Tech – Computer Science, whose paper in collaboration with Korea University, Boosted L-EnsNMF: Local Topic Discovery via Ensemble of Nonnegative Matrix Factorization, received the Best Student Paper Award at the IEEE Conference on Data Mining! Click here for a full list of awards.