Piranha is a text mining system. It was developed for the United States Department of Energy (DOE) by Oak Ridge National Laboratory (ORNL). The software processes free-text documents and shows relationships amongst them, a technique valuable across numerous data domains, from health care fraud to national security. The results are presented in clusters of prioritized relevance. Piranha uses the term frequency/inverse corpus frequency term weighting method which provides strong parallel processing of textual information, thus the ability to analyze large document sets.

Piranha has six main elements:

  • Collecting and Extracting: Millions of documents from sources such as databases and social media can be collected and text extracted from hundreds of file formats; This information can be translated to other languages.
  • Storing and indexing: Documents in search servers, relational databases, etc. can be stored and indexed.
  • Recommending: The system can highlight the most valuable information for specific users.
  • Categorizing: Grouping items via supervised and semi-supervised machine learning methods and targeted search lists.
  • Clustering: Similarity is used to group documents hierarchically.
  • Visualizing: Showing relationships among documents so that users can quickly recognize connections.

This work has resulted in eight patents (9,256,649, 8,825,710, 8,473,314, 7,937,389, 7,805,446, 7,693,9037, 7,315,858, 7,072,883), and commercial licenses (including TextOre and Pro2Serve), a spin-off company with the inventors, Covenant Health, and Pro2Serve called VortexT Analytics, two R&D 100 Awards, and scores of peer reviewed research publications.

  • Cui, X., Beaver, J., St. Charles, J., Potok, T. (September 2008). Proceedings of the IEEE Swarm Intelligence Symposium, St. Louis, Mo. .
  • Yasin, Rutrell (Nov 29, 2012) GCN.
  • Franklin Jr., Curtis (Nov 30, 2012) Enterprise Efficiency.
  • Breeden II, John (Dec 7, 2012) GCN.
  • Kirby, Bob (Summer 2013) FedTech.
  • R. M. Patton, B. G. Beckerman, T. E. Potok, G. Tourassi, "A Recommender System for Web-Based Discovery and Refinement of Information Radiologists Seek", Radiological Society of North America (RSNA), 2012 Annual Meeting, Nov. 2012, Chicago, IL, USA.
  • R. M. Patton, T. E. Potok, B. A. Worley, "Discovery & Refinement of Scientific Information via a Recommender System", The Second International Conference on Advanced Communications and Computation, Oct. 2012, Venice, Italy.
  • J. W. Reed, T. E. Potok, and R. M. Patton, "A multi-agent system for distributed cluster analysis," in Proceedings of Third International Workshop on Software Engineering for Large-Scale Multi- Agent Systems (SELMAS'04)" W16L Workshop - 26th International Conference on Software Engineering Edinburgh, Scotland, UK: IEE, 2004, pp. 152-5.
  • J. Reed, Y. Jiao, T. E. Potok, B. Klump, M. Elmore, and A. R. Hurson, "TF-ICF: A New Term Weighting Scheme for Clustering Dynamic Data Streams," in Proceedings of 5th International Conference on Machine Learning and Applications (ICMLA'06). vol. 0 ORLANDO, FL, 2006, pp. 258–263.

Awards

  • 2007 R&D 100 Magazine's Award

Patents

  • – System for gathering and summarizing internet information
  • – Method for gathering and summarizing internet information
  • – Agent-based method for distributed clustering of textual information
  • – Dynamic reduction of dimensions of a document vector in a document search and retrieval system
  • – Method and system for determining precursors of health abnormalities from processing medical records

External links

  • DOE Energy Innovlation Portal (2014) .