Virginia Polytechnic Institute and State University (Virginia Tech) is home to the Early Model Based Even Recognition using Surrogates (EMBERS) project, which was created to develop ways to use big data to forecast significant societal events.
The EMBERS project recently held a panel to discuss the future of forecasting using big data. "It is not just the volume of data we are interested in, but the veracity and variety as well," says Virginia Tech professor Wu Feng.
One project the researchers are focused on is a program that reads images of parking lots outside of health centers and hospitals to monitor upticks in "fill rate."
"Teaching a machine to extract meaning from an image involves labeling an exorbitant number of objects," says Virginia Tech professor Devi Parikh, who leads the Computer Vision lab at Virginia Tech.
As computer networks become more advanced and are better able to handle large amounts of data, and the algorithms for interpreting the data become more sophisticated, researchers may be able to forecast important social phenomena all over the world.
Naren Ramakrishnan, who leads the EMBERS project and also is director of the Discovery Analytics Center Arlington site, notes all of the event alerts are emailed in real time and compared against a gold standard report organized by a third party.
From Virginia Tech News
View Full Article
Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA