User:ORNLPirhana/ORNL Computational Data Analytics Group

<<<The content used is the property of the United States federal government. US government website is PD, so this article in not a copyvio>>> Not entirely true. ORNL is operated by a government contractor, so its material isn't necessarily in the public domain.

---

ORNL Computational Data Analytics Group

The Computational Data Analytics Research Group at the Oak Ridge National Laboratory conducts innovative basic and applied computer science research on challenges of national interest. The research focus is in the areas of large-scale data analytics and architectures.

The group has a broad research portfolio of research papers and patents and has collaborated with world-renowned experts. It also develops industry marketable technology, resulting in commercialized licenses, and boasts top researchers and engineers in the field.

The focus is on leveraging our core technologies, expertise, and experience to solve challenging problems of national interest.

Projects:

SCIENCE

Exploratory Data analysis ENvironment (EDEN)

The determination of relationships between climate variables and the identification of the most significant associations between them in various geographic regions is an important aspect of climate model evaluation. The EDEN visual analytics toolkit has been developed to aid such analysis by facilitating the assessment of multiple variables with respect to the amount of variability that can be attributed to specific other variables.

ENERGY

Visualizing Energy Resources Dynamically on the Earth (VERDE) ORNL has developed a national visualization and analysis capability for the Department of Energy. This resource will enable real-time status of the electric grid and critical energy sectors to assist federal agencies in their coordination and response during major events such as wide-area power outages, natural disasters and other catastrophic events.

Among the group's most notable projects is the Piranha data analytics package

ORCA is the group's cyber security data analytics package

HEALTHCARE

Centers for Medicare & Medicaid Services In 2011 the Centers for Medicare & Medicaid Services (CMS) established an Inter-Agency Agreement (IAA) with the US Department of Energy to enlist the assistance of ORNL in prototyping an agile and cost effective data infrastructure to support future business needs. The collaboration between CMS and CDA has resulted in the design and implementation of an overarching framework prototype, the Knowledge Discovery Infrastructure (KDI). Based on the KDI framework, CDA is now working with Lockheed Martin to establish an advanced data integration and analysis pilot in the CMS Baltimore Data Center.

NATIONAL SECURITY

Piranha Big Data Analytics There is a massive amount of intelligence data available that cannot be manually analyzed. Computers can provide some help in this area, but the shear volumes of data make the most promising approaches impractical. The challenge is for a computer to sift through a large amount of data & provide a human with accurate and relevant information, not to merely allow the analyst to search over an ever increasing set of data.

Oak Ridge Cyber Analytics (ORCA) Oak Ridge Cyber Analytics (ORCA) is a suite of tools for applying automation and advanced analytics to pressing information security problems. ORCA is comprised of several components, each of which addresses widespread technology gaps in computer network defense.

Validating Epidemiological Forecast Models Epidemiological models are widely used as a means to understand disease spread mechanisms and how best to control epidemic outbreaks. A significant challenge within the community is the ability to rigorously verify and validate these models.

IntelEx

BUSINESS INTELLIGENCE

DTHSTR - Personalizing Big Data for Business Intelligence Every person, company, and government organization is faced with continuously flowing, massive streams of data that cannot be manually analyzed. Computers have provided significant help in addressing this problem, but the shear volumes of data have made even the most promising approaches impractical. The Distribute The Highest Selected Textual Recommendation (DTHSTR) engine utilizes advanced analytic technology and a low computing footprint, allowing for analysis of very large and dynamic text data with unprecedented speed and accuracy.

Group Members:

Thomas E. Potok, Senior Scientist, Group Leader Angie Scott, Administrative Assistant Justin M. Beaver, Research Scientist, Team Leader Barbara Beckerman, Program Manager – Biomedical Informatics and also Deputy Director, Biomedical Science and Engineering Center (BSEC) Paul Bogen, Research Associate Supriya Chinthavali Jeremy D. Cohen, Senior Program Manager Xiaohui Cui, Research Scientist Rob Gillen, Research Professional Bryan L. Gorman, Senior Research Associate and Team Leader David E. Hill, Network Systems Engineer James L. Horey, Research Scientist Seung-Hwan Lim, PostDoc Wade McNair, Enterprise Architect Özgür Özmen, Postdoctoral Research Associate Robert M. Patton, Research Scientist Laura L. Pullum, Senior Research Scientist David R. Resseguie, Computer and Information Research Scientist Mallikarjun Shankar, Senior Research Scientist Chad A. Steed, Research Scientist Sreenivas "Rangan" Sukumar, Research Scientist Christopher T. Symons, Research Scientist Gautam Thakur Elaine G. Thompson, Research Support Specialist Johnny Tolliver, Senior Research Scientist Jim N. Treadwell, Senior Program Manager Randy M. Walker, Senior Transportation Specialist & Program Developer Ken Woodworth, Field Technician Songhua Xu, Wigner Fellow

Click here for a list of relevant publications.

References

• http://cda.ornl.gov/piranha.shtml
• http://gcn.com/articles/2012/11/29/energy-lab-piranha-text-analysis.aspx
• Potok, Elmore, Reed, Treadwell, and Samatova, “System for Gathering and Summarizing Internet Information,” U.S. Patents 7,072,883, 7,315,858, 7,693,903, (2006).
• Potok and Reed, “Agent-Based Method for Distributed Clustering of Textual information,” U. S. Patent 7,805,446 (2010)
• Jiao and Potok, "Dynamic reduction of dimensions of a document vector in a document search and retrieval system," U. S. Patent 7,937,389 (2011).