A HYBRID NEURAL NETWORK/EXPERT SYSTEM ENVIRONMENT

Award Information
Agency:
National Aeronautics and Space Administration
Branch
n/a
Amount:
$50,000.00
Award Year:
1991
Program:
SBIR
Phase:
Phase I
Contract:
n/a
Agency Tracking Number:
16943
Solicitation Year:
n/a
Solicitation Topic Code:
n/a
Solicitation Number:
n/a
Small Business Information
Charles River Analytics Inc
55 Wheeler St, Cambridge, MA, 02138
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
N
Duns:
n/a
Principal Investigator:
() -
Business Contact:
() -
Research Institution:
n/a
Abstract
THE INTEGRATION OF ARTIFICIAL NEURAL NETWORKS (ANNS) AND KNOWLEDGE-BASED EXPERT SYSTEMS IS AN IDEAL STEP IN THE DEVELOPMENT OF INTELLIGENT SYSTEMS. IN GENERAL, THE TWO METHODS COMPLEMENT EACH OTHER, WITH THE ANNS PROVIDING SOFT CONSTRAINTS AND EXPERT SYSTEMS, HARD CONSTRAINTS. SPECIFICALLY, ANNS PERFORM NONLINEAR FUNCTIONS, PATTERN RECOGNITION, FAULT TOLERANCE, AND PARALLEL PROCESSING; EXPERT SYSTEMS INVOLVE LANGUAGE PROCESSING, FORMAL LOGIC, AND RULE INTERPRETATION. THE HYBRID COMBINATION OF ANNS ANDEXPERT SYSTEMS WILL FACILITATE THE AUTOMATION OF VARIOUS SPACE STATION APPLICATIONS WHILE PROVIDING UNSUPERVISED ADAPTABILITY AND REAL-TIME FUNCTIONALITY. THIS PROJECT WILL IDENTIFY AND DEVELOP BASELINE ARCHITECTURE AND REQUIREMENTS SPECIFICATION FOR THE INTEGRATION OF NEURAL NETWORKS AND OF EXPERT SYSTEMS TO FORM A HYBRID SOFTWARE ENVIRONMENT. ADDITIONALLY, STRATEGIES FOR THE IMPLEMENTATION OF INTELLIGENT SYSTEMS WITHIN THE HYBRID ENVIRONMENT WILL BE INVESTIGATED FOR SPACE STATION CONTROL AND SENSOR MONITORING APPLICATIONS. THE INTEGRATION OF ARTIFICIAL NEURAL NETWORKS (ANNS) AND KNOWLEDGE-BASED EXPERT SYSTEMS IS AN IDEAL STEP IN THE DEVELOPMENT OF INTELLIGENT SYSTEMS. IN GENERAL, THE TWO METHODS COMPLEMENT EACH OTHER, WITH THE ANNS PROVIDING SOFT CONSTRAINTS AND EXPERT SYSTEMS, HARD CONSTRAINTS. SPECIFICALLY, ANNS PERFORM NONLINEAR FUNCTIONS, PATTERN RECOGNITION, FAULT TOLERANCE, AND PARALLEL PROCESSING; EXPERT SYSTEMS INVOLVE LANGUAGE PROCESSING, FORMAL LOGIC, AND RULE INTERPRETATION. THE HYBRID COMBINATION OF ANNS ANDEXPERT SYSTEMS WILL FACILITATE THE AUTOMATION OF VARIOUS SPACE STATION APPLICATIONS WHILE PROVIDING UNSUPERVISED ADAPTABILITY AND REAL-TIME FUNCTIONALITY. THIS PROJECT WILL IDENTIFY AND DEVELOP BASELINE ARCHITECTURE AND REQUIREMENTS SPECIFICATION FOR THE INTEGRATION OF NEURAL NETWORKS AND OF EXPERT SYSTEMS TO FORM A HYBRID SOFTWARE ENVIRONMENT. ADDITIONALLY, STRATEGIES FOR THE IMPLEMENTATION OF INTELLIGENT SYSTEMS WITHIN THE HYBRID ENVIRONMENT WILL BE INVESTIGATED FOR SPACE STATION CONTROL AND SENSOR MONITORING APPLICATIONS.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government