Automated Assistance with Metadata Generation (A2MG) Tools for PBA/IPB
Department of Defense
Agency Tracking Number:
Solicitation Topic Code:
Small Business Information
8640 Guilford Road, Suite 241, COLUMBIA, MD, 21046
Socially and Economically Disadvantaged:
AbstractARGTEC is developing a new and innovative technology based on the theory of Attributed Relational Graph (ARG) for automated indexing and retrieval in multi-channel, unstructured environments for the Global Information Grid (GIG). Our system captures the information contents of unstructured (as well as structured or semi-structured) data through the use of a hierarchical ARG representation scheme. The scheme does not rely on pre-defined concepts; it automatically defines and extracts relevant sparse information contents and multi-feature concepts from the user query and from the multi-channel data itself. This feature of our approach render our system to be the most suited to deal with the challenges of finding concealed information in difficult scenarios. We have achieved several breakthroughs in the development of this technology which proved it to be very successful in Automated Fingerprint Identification Systems (AFIS) as well as in web-based indexing and retrieval using the contents of free-text documents. ARGTEC proposes to develop and implement a generalized hierarchical ARG model as an Automated Metadata Representation scheme tailored for Predictive Battlespace Awareness (PBA) and Intelligence Preparation of the Battlesapce (IPB). We will show that the hierarchical ARG representation technique, coupled with our suites of inexact matching algorithms are especially effective for identifying and retrieving various types of relevant information, especially in the unstructured GIG environment. We have worked with several industrial partners in both defense and commercial arenas to infuse our technology nuggets into fielded, operational systems.
* information listed above is at the time of submission.