EventShop



EventShop is a first-of-its-kind analytics system that provides a graphical way for users to experiment with different layers of cyber-physical data to define and evaluate various situations. Focusing primarily on live (as opposed to 'stale') data, it allows users to experiment with different streams and define situation filters as 'active queries' on them. It provides a generic approach to select, import, visualize, integrate, and analyze heterogeneous data streams to detect personalized situations.
Multiple applications like flu risk recommendation and directing people stranded in unsafe locations during floods in Thailand and Hurricane Sandy have been implemented using EventShop. Many users re-tweeted the messages providing a preliminary indication of an interest in receiving and spreading such information.
Demo: The following video demonstrates how EventShop can be used to find regions within a hurricane's path that are not adequately covered by relief shelters.


Please feeel free to play with the SandBox version, or refer to the Technical Report.

Relevant Publications:
1) EventShop: From Heterogeneous Web Streams to Personalized Situation Detection and Control, M. Gao, V.K. Singh, R. Jain, Web Science Conference, 2012.
2) Situation Recognition: An Evolving Problem for Heterogeneous Dynamic Big Multimedia Data, V.K. Singh, M. Gao, R. Jain, ACM Multimedia Conference, 2012.
3) EventShop: Recognizing situations in web data streams, S. Pongpaichet, V.K. Singh, M. Gao, R. Jain, World Wide Web conference: Workshop on Web Observatories, 2013.