USA flag logo/image

An Official Website of the United States Government

Automated Assistance with Ontology Generation (A2OG) for PBA/IPB

Award Information

Agency:
Department of Defense
Branch:
Air Force
Award ID:
72915
Program Year/Program:
2006 / SBIR
Agency Tracking Number:
F051-098-2293
Solicitation Year:
N/A
Solicitation Topic Code:
N/A
Solicitation Number:
N/A
Small Business Information
ARGTEC, INC.
8640 Guilford Road, Suite 241 COLUMBIA, MD 21046
View profile »
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No
 
Phase 2
Fiscal Year: 2006
Title: Automated Assistance with Ontology Generation (A2OG) for PBA/IPB
Agency / Branch: DOD / USAF
Contract: FA8750-06-C-0036
Award Amount: $749,945.00
 

Abstract:

ARGTEC is pioneering the use of a new and innovative technology based on the theory of Attributed Relational Graph (ARG) in several application domains for content-based indexing and retrieval in large multimedia databases. We have achieved several breakthroughs in the development of this technology. This technology has been very successful in Automated Fingerprint Identification Systems (AFIS) and in web-based indexing and retrieval using the contents of free-text documents. The ARG is a powerful technique that can be used for the ontology representation of the multimedia information. It is capable of capturing the textual, imagery, graphical, statistical, geometrical, topological, contextual, and semantic information in a multi-dimensional hierarchical representation that enables the system to represent complex concepts in a very compact, yet robust, form. During Phase I of this program, we proved that our technology is extendable to metadata representation and automated ontology generation specific to the domain of Predictive Battlespace Awareness (PBA) and Intelligence Preparation of Battlespace (IPB). We also developed a proof-of-concept demonstration as applied to that application. Our demonstration delivers very promising results with very high selectivity and reliability in real-time identification of computer network exploit messages. Previously, we have been also successful in applying this technology to Automated Fingerprint Identification Systems (AFIS). In tests on large fingerprint databases, it delivered > 99% identification accuracy (i.e., < 1% Type I error) and close to zero false alarm rate. ARGTEC proposes to develop and implement a generalized hierarchical ARG model as an ontology representation scheme tailored for multimedia intelligence documents. We will show that the hierarchical ARG representation technique, coupled with our suites of inexact matching algorithms are especially effective for storage, web-based retrieval and summarization tasks for the Intelligence and Homeland Defense user communities. ARGTEC has worked with several industrial partners in both defense and commercial arenas. Our commercialization strategy lies in converting our algorithm development efforts into system innovations, then teaming with large system integrators to infuse our technology nuggets into fielded, operational systems. We will insure that our technology will be infused into the Collaboration Guard (CG) system as the first operational system that will utilize our product.

Principal Investigator:

Monndy Eshera
President
4102909891
meshera@argtec.com

Business Contact:

Monndy Eshera
President
4102909891
meshera@argtec.com
Small Business Information at Submission:

ARGTEC, INC.
8640 Guilford Road, Suite 241 COLUMBIA, MD 21046

EIN/Tax ID: 521962984
DUNS: N/A
Number of Employees:
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No