Inventors of the Month - November 2016

This article was posted on: November 21, 2016

Naren Ramakrishnan and the Virginia Tech Discovery Analytics Center

“Early Model Based Event Recognition using Surrogates (EMBERS) software”

During the Cold War, US intelligence agents analyzed “chatter” in Soviet communications to identify potential military exercises. These days, computers analyze worldwide open-source data to forecast geopolitical events of all kinds.

The Office of the Vice President for Research and Innovation recognizes the Virginia Tech Discovery Analytics Center, led by Naren Ramakrishnan, as Inventors of the Month for the Early Model Based Event Recognition using Surrogates (EMBERS) software, a fully automated system for forecasting significant societal events, such as influenza-like illness case counts, rare disease outbreaks, civil unrest, domestic political crises, and elections, from open source surrogates.

Sponsored by a recently concluded $22M IARPA contract, EMBERS scours open source, real-time data streams including tweets, Facebook pages, news articles, blog posts, Google search volume, Wikipedia, meteorological data, economic and financial indicators, coded event data, online restaurant reservations, and satellite imagery. Focused on countries in Latin America, the Middle East and China, EMBERS has successfully forecast many international (and rare) events, such as

  • the “Brazilian Spring” (June 2013)
  • Hantavirus outbreaks in Argentina and Chile (2013)
  • student-led protests in Venezuela (February 2014)
  • protests stemming from the kidnappings and killings of student-teachers in Mexico (September – October 2014)
  • domestic political crises in Bahrain and Egypt (Dec 2015)
  • protests in Paraguay (Feb 2015) against a new public-private partnership law

EMBERS also successfully forecast the winners of the 2014 presidential elections in Panama and Colombia even as every major poll indicated other candidates would come out on top. EMBERS has been featured in a variety of popular media, such as Newsweek, Wall Street Journal, Chronicle of Higher Education, and Slate, as well as academic journals, such as Science and Big Data Journal.

Naren Ramakrishnan is the Thomas L. Phillips Professor of Engineering in the Department of Computer Science at Virginia Tech and the director of the Discovery Analytics Center. In addition to collaborators from numerous universities and companies, Virginia Tech contributors come from the Biocomplexity Institute, the statistics department, the mechanical engineering department, and the Institute for Critical Technology and Applied Science (ICTAS).

Virginia Tech faculty and students who have contributed to the development of the EMBERS software suite for civil unrest include:

  • Patrick Butler
  • Jose Cadena
  • Feng Chen
  • Andy Hoegh
  • Ting Hua
  • Rupinder Paul Khandpur
  • Gizem Korkmaz
  • Chris Kuhlman
  • Scotland Leman
  • Chang-Tien Lu
  • Achla Marathe
  • Sathappan Muthiah
  • Naren Ramakrishnan
  • Parang Saraf
  • Anil Kumar Vullikanti
  • Liang Zhao

 

 

Members of the staff of the Discovery Analytics Center. Left to right are Nathan Self, Patrick Butler, and Naren Ramakrishnan.
 
.

(Above and below) EMBERS successfully forecast the Feb 2014 violent protests in Venezuela

 

logo for VTIP

 

 

VTIP facilitates the licensing of technology to companies, encourages new faculty startup ventures, works with publishers and distributors of software, and supports the transfer of research and knowledge to other universities, research institutes and companies.


Virginia Tech Intellectual Properties
Campus Mail Code 0459
2200 Kraft Drive, Suite 1050
Blacksburg, VA 24060

www.vtip.org


PATENT APPLICATIONS