Advanced Decision Aid Systems

Period of Performance: 04/16/1998 - 10/15/1998

$65K

Phase 1 SBIR

Recipient Firm

American GNC Corp.
888 Easy Street
Simi Valley, CA 93065
Principal Investigator

Abstract

A decision aid system is a computer application that solves complicated problems that would otherwise require extensive human expertise. To do so, it simulates the human reasoning process by applying specific knowledge and inferences. The highly demanding requirements of the newer and future all-source decision aid system can be met by the integration of various decision making approaches. The primary objective of this Phase I project is to develop intelligent decision aid system by integrating Dempster-Shafer (D-S) method and Quasi Axiomatic Theory (QAT), and provide a comprehensive and adaptive situation analysis decision aid. The D-S method provides a means to account explicitly for unknown possible causes of observational data. The QAT method employs the adaptive mechanism, in which new hypotheses are formed in the presence of conflicting data. The knowledge base that exists in the machine and the knowledge engineering used to capture the expert's skill is explained. A prototyping system will be designed to be user-friendly and easy to use through employing state-of-the art window and object-oriented programming techniques. Thus the operator can interact with the adaptive algorithms to create and assess hypotheses.