Metadata Generation
SBIR FY04.1 Topic AF04-097
Department of Defense (DOD)/Air Force - Information Directorate

The entire solicitation may be viewed at http://www.acq.osd.mil/sadbu/sbir/solicitations/sbir041/index.htm

AF04-097 TITLE: Metadata Generation

TECHNOLOGY AREAS: Information Systems

OBJECTIVE: Automatically Index and tag all multimedia intelligence documents, for storage, web based retrieval, and summarization, providing "quick look" global awareness of all available Homeland Security information.

DESCRIPTION: The major complaint that is being heard from the Intelligence and Homeland Defense user communities is the inability to quickly, and easily find items of interest across the Government's web based systems. Furthermore, these same communities complain about the time and expense of generating metadata to alleviate their problems. Metadata is generated manually making timely intelligence information very expensive or simply non-existent. Metadata, XML, and Document tags are intended to provide greater insight into the content and structure of information and, thereby, to facilitate discovery by query and retrieval tools. The problem is that today only humans generate metadata creating a situation that is error prone, time consuming and labor intensive for both those who generate the information and those that use it. Information indexes, should be developed by the computer, retrieved by the computer, and graphically summarized by the computer. Computer generated metadata should use a signature analysis technique describing text and multimedia data as a compressed "image" in the web based library index. Furthermore, every entry in the library should be zoned, parsed, and geospatially tagged so that information can be summarized with a timeline/ temporal analysis displays (icons on an image, geographic map background, or timeline), Indications and Warning (I&W) display or some other graphic. Information users should not be forced to actually read the entire web holdings in order to get a sense of what information is stored on all of its servers.

PHASE I: Perform feasibility study with initial implementation and experimentation on the proposed approach, and provide initial results potential proving the validity of the approach and use as an information management system

PHASE II: The second phase develops a fully functional prototype to support a broad range of intelligence and surveillance web users.

DUAL USE COMMERCIALIZATION: This technology is directly applicable to a broad range of military applications. Known commercial application areas include general internet search engines and specialized search engines for medical, bioinformatics, drug discovery, financial, and leagal applications.

COMMERCIAL POTENTIAL: Recent Internet markets indicate the growing need to manage large complex web based libraries. ). Dual Use Potential is enormous since all industries that will use Web based communications have requirements for automated metadata generation.

REFERENCES: Related REFERENCES:
1. Tannenbaum, A. (2001). Metadata Solutions: Using Metamodels, Repositories, XML, and Enterprise Portals to Generate Information on Demand. Addison Wesley Professional, Reading, MA.

2. Berry, M. W., Browne, M. (1999). Understanding Search Engines: Mathematical Modeling and Text Retrieval (Software, Environments, Tools). Society for Industrial & Applied Mathematics, Philadelphia, PA.

3. Baeza-Yates, R., Ribeiro-Neto, B., Baeza-Yates, R. (1999). Modern Information Retrieval. Addison-Wesley Pub Co., Reading, MA.

4. Guidelines for Intelink Metadata, Version 1.1: Intelink Conference, San Antonio TX, August 1998

5. Proceedings Intelink Conference, New Orleans LA , May 2002

KEYWORDS: metadata, indexing, text understanding, intelligent systems, document tags, XML, search engines

Questions about SBIR and Solicitation Topics

TECHNICAL POINT OF CONTACT:

Doug Poore
Phone:
Fax:
Email:

INFORMATION DIRECTORATE PROGRAM MANAGER:

Janis Norelli

Between October 1 and November 28, 2003, you may talk directly with the Topic Authors to ask technical questions about the topics. Their names, phone numbers, and e-mail addresses are listed within each solicitation topic above. For reasons of competitive fairness, direct communication between proposers and topic authors is not allowed starting December 1, when DoD begins accepting proposals for this solicitation. However, proposers may still submit written questions about solicitation topics through the SBIR/STTR Interactive Topic Information System (SITIS), in which the questioner and respondent remain anonymous and all questions and answers are posted electronically for general viewing until the solicitation closes. All proposers are advised to monitor SITIS (04.1 Q&A) during the solicitation period for questions and answers, and other significant information, relevant to the SBIR 04.1 topic under which they are proposing.