Print

Print


Computer Science Colloquium

Speaker: Naren Ramakrishnan, CS Dept, Virginia Tech
Title: New Knowledge Discovery Techniques to support Intelligence Analysts
Date/Time: Monday, April 30, 11:00 AM -  12:00 PM 
Location: Room 163, Research Hall

Abstract:
Intelligence analysts today are faced with many challenges, chief among them being the need to fuse disparate streams of data, and rapidly arrive at analytical decisions and quantitative predictions for use by policy makers. This talk will focus on “storytelling”, the investigative process by which analysts aim to “connect the dots” between seemingly disconnected information. We will introduce how the twin notions of redescriptions and biclusters form compositional building blocks of stories, and how efficient and effective algorithms for storytelling can be designed. In addition, we describe approaches to inject user feedback into the story construction process and the results of user studies demonstrating how participants are adept at using these notions to solve intelligence analysis tasks. Experimental results on large textual and multi-relational corpora will be described. This talk will conclude with a preview into an ongoing project in the area of automatic alert generation from public source data.

Bio:
Naren Ramakrishnan is the Thomas L. Phillips Professor of Engineering and the Associate Head for Graduate Studies in the Department of Computer Science at Virginia Tech. At Virginia Tech, he directs the Discovery Analytics Center, a university-wide effort that brings together researchers from computer science, statistics, mathematics, and electrical and computer engineering to tackle knowledge discovery problems in important areas of national interest, including intelligence analysis, sustainability, and health informatics. Ramakrishnan serves on the editorial boards of IEEE Computer, Data Mining and Knowledge Discovery, and many other journals. He is an ACM Distinguished Scientist and was named to two "40 under 40" lists: Computerworld's innovative IT people to watch (2007) and Purdue University's list of distinguished alumni (2010). 

Host: Sanjeev Setia