USA flag logo/image

An Official Website of the United States Government

A Generalized Event Representation Modeling and Analysis Tool

Award Information

Department of Defense
Award ID:
Program Year/Program:
1997 / SBIR
Agency Tracking Number:
Solicitation Year:
Solicitation Topic Code:
Solicitation Number:
Small Business Information
Knowledge Based Systems, Inc.
1408 University Drive East College Station, TX 77840-2335
View profile »
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No
Phase 1
Fiscal Year: 1997
Title: A Generalized Event Representation Modeling and Analysis Tool
Agency / Branch: DOD / ARMY
Contract: N/A
Award Amount: $92,835.00


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.

Principal Investigator:

Dr. Satheesh Ramachandran

Business Contact:

Small Business Information at Submission:

Knowledge Based Systems, Inc.
One Kbsi Place 1408 University Dr. College Station, TX 77840

Number of Employees:
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No