You are here

A Generalized Event Representation Modeling and Analysis Tool

Award Information
Agency: Department of Defense
Branch: Army
Contract: N/A
Agency Tracking Number: 36752
Amount: $92,835.00
Phase: Phase I
Program: SBIR
Solicitation Topic Code: N/A
Solicitation Number: N/A
Timeline
Solicitation Year: N/A
Award Year: 1997
Award Start Date (Proposal Award Date): N/A
Award End Date (Contract End Date): N/A
Small Business Information
One Kbsi Place 1408 University Dr.
College Station, TX 77840
United States
DUNS: N/A
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Dr. Satheesh Ramachandran
 (409) 260-5274
Business Contact
Phone: () -
Research Institution
N/A
Abstract

This SBIR Phase I project will create an event representation framework and generate a catalogue of reasoning mechanisms for transforming domain specific events into a convenient representational framework. The choice of the representation scheme used to model a domain for analysis by the neural network of fuzzy logic system can make an enormous difference in the ease and efficiency of the problem analysis. Typically, no particular paradigm is best for modeling systems -- multiple models are used to obtain useful inferences. This strategy entails combining multiple bodies of information and establishing a framework for global interpretation of context specific information. The absence of sound and proven techniques that facilitate integrated information modeling and create efficient, global event-in-scenario representations makes such neural network and fuzzy logic applications difficult. The proof of concept for these methodologies will be demonstrated through a prototype for an Generalized Event Representation Modeling and Analysis Tool (GERMAT) for the new generation information processing paradigms. The product is commercially viable -- it will popularize use of neural networks and fuzzy logic application by simplifying modeling in these paradigms, facilitating re-use of information between different neural network and fuzzy logic applications, and facilitating integrated modeling that addresses complex real world problems. A generic framework to rapidly model neural network/fuzzy logic applications would have significant benefits in pattern recognition, forecasting modeling, decision support systems, and control systems.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government