George Mason University

The real value of Big Data lies in its potential to provide actionable insights in multiple applications. Combined effectively, real-time human and sensor data streams can be used to recognize and respond to situations in applications like disaster mitigation, health, defense, traffic, and business intelligence. I present a framework that uses a unified data model to integrate different streams, and provides a set of generic operators to model complex situations. EventShop can be used to combine heterogeneous data streams, recognize situations, and send personalized alerts to millions of users. Recently, EventShop was used to detect Fall season onset based on Flickr uploads, to give personalized activity recommendations to Asthmatic patients, and to send out alerts to users in risky situations during the Hurricane ‘Sandy’.

Dr. Vivek Singh is a post-doctoral researcher working with the Human Dynamics group at MIT Media Lab. He holds aPh.D. in Computer Science from the University of California, Irvine. He obtained his Bachelors and Masters degrees in Computer Science from the National University of Singapore, and was a Lecturer at the Institute of Technical Education, Singapore for 4 years. His work has received two best paper awards so far and he was selected as one of the ‘Emerging leaders in multimedia research’ by IBM Research Labs in 2009. He is general co-chair of the first ACM Workshop on ‘Personal Data Meets Distributed Multimedia’ to be held in Oct 2013. His research interests lie at the intersection of Big Data Analytics, Social Computing and Multimedia.

Date/Time
09/11/2013
3:00 pm - 4:00 pm

Location
C4I Center ENGR 4705