Seminar: True Novelty in Big Data Research: The LITMUS Experience and Research Opportunities

 

  

Calton Pu, Professor and J.P. Imlay, Jr. Chair in Software

Georgia Institute of Technology

Monday October 7, 2019

3 pm

Patrick F. Taylor Hall, Room 3107

Abstract

With billions of smartphones and millions of video cameras, social media and surveillance video are generating real-time big data around the world. Paradoxically, the main consumers of this growing big data have been humans, limiting the effectiveness of applications such as proactive public safety and disaster management, due to the time lag between the actual events recorded by sensor data to novelty discovery and confirmation. There are several reasons traditional machine learning algorithms have difficulties with novelty discovery, including the lack of ground truth data on novelty.

We outline the Evidence-Based Knowledge Acquisition (EBKA) approach to automated novelty discovery. EBKA has been applied in the LITMUS landslide information system, which integrates primary sources such as Tweeter (with high coverage and high levels of noise) with corroborative sources such as CNN.com (with limited coverage, but high reliability), to achieve high coverage and high accuracy. LITMUS is running live in the project website at grait-dm.org . In collaboration with the University of Sao Paulo (USP, Brazil), we are applying EBKA to analyze live video data from 300+ cameras on USP campus for application areas such as proactive public safety.

Bio

Calton Pu was born in Taiwan and grew up in Brazil.  He received his PhD from University of Washington and served on the faculty of Columbia University and Oregon Graduate Institute.  Currently, he is holding the position of Professor and John P. Imlay, Jr. Chair in Software in the College of Computing, Georgia Institute of Technology.  He has worked on several projects in systems and database research.  His contributions to systems research include program specialization and software feedback.  His contributions to database research include extended transaction models and their implementation.  His recent research has focused on automated system management in clouds (Elba project), information quality (e.g., spam processing), and novelty in big data (GRAIT-DM project).

He has collaborated extensively with scientists and industry researchers.  He has published more than 70 journal papers and book chapters, 280 conference and refereed workshop papers. He served on more than 120 program committees, including the co-PC chairs of SRDS'95, ICDE’99, COOPIS’02, SRDS’03, DOA’07, DEBS’09, ICWS’10, CollaborateCom'11, ICAC’13, CLOUD’15, BigData Congress’16, CIC’16, IEEE BigData’18, and co-general chair of ICDE'97, CIKM'01, ICDE’06, DEPSA’07, CEAS’07, SCC’08, CollaborateCom’08 and ‘12, SCF’11 and ‘18, CollaborateCom’12, IEEE CIC’15, and ICDCS’17. He is a Fellow of AAAS and IEEE.