The EMBERS architecture for streaming predictive analytics

Author

Doyle, Andy ; Katz, Gil ; Summers, Kathryn ; Ackermann, Chris ; Zavorin, Ilya ; Zunsik Lim ; Muthiah, Sathappan ; Liang Zhao ; Chang-Tien Lu ; Butler, Patrick ; Khandpur, Rupinder Paul ; Fayed, Youssef ; Ramakrishnan, N.

Author_Institution

CACI Inc., Lanham, MD, USA

fYear

2014

fDate

27-30 Oct. 2014

Firstpage

11

Lastpage

13

Abstract

Developed under the IARPA Open Source Initiative program, EMBERS (Early Model Based Event Recognition using Surrogates) is a large-scale Big-Data analytics system for forecasting significant societal events, such as civil unrest incidents and disease outbreaks on the basis of continuous, automated analysis of large volumes of publicly available data. It has been operational since November of 2012, delivering approximately 50 predictions each day. EMBERS is built on a streaming, scalable, share-nothing architecture and is deployed on Amazon Web Services (AWS).

Keywords

Big Data; Web services; cloud computing; public domain software; software architecture; AWS; Amazon Web Services; EMBERS architecture; IARPA open source initiative program; civil unrest incidents; continuous automated analysis; disease outbreaks; early model-based event recognition-using-surrogates; large-scale Big-Data analytics system; predictive analytics streaming; publicly available data; societal event forecasting; streaming-scalable-share-nothing architecture; Big data; Computer architecture; Data models; Data visualization; Diseases; Feeds; Predictive models;

fLanguage

English

Publisher

ieee

Conference_Titel

Big Data (Big Data), 2014 IEEE International Conference on

Conference_Location

Washington, DC

Type

conf

DOI

10.1109/BigData.2014.7004477

Filename

7004477