SBIR/STTR Research Award

TEMPORAL REASONING IN A CASE-BASED REASONING SYSTEM

Award identifier 240c51118e6a254ce8430beafb56b5f20049bce132cf77f6f5e78ad7fb39faf5Awarding agency Department of Defense · Defense Advanced Research Projects Agency

Award amount

$243,818

Program and phase

SBIR · Phase II

Award year

1992

Explore This Research Award in CaptureIQ

Research the technology, evaluate the recipient and agency, identify related opportunities, and explore potential follow-on work with CaptureIQ.

Award details

Awarding agency
Department of Defense
Branch
Defense Advanced Research Projects Agency
Recipient company
Cognitive Systems Inc.
Proposal award date
Not reported
Contract end date
Not reported
UEI
Not reported
Solicitation number
Not reported
Topic code
Not reported

Research abstract

ASE-BASED REASONING (CBR) IS A POWERFUL PARADIGM FOR BUILDING EXPERT SYSTEMS WITH MANY ADVANTAGES OVER OTHER APPROACHES IN TERMS OF TIME AND COST OF KNOWLEDGE ENGINEERING, EASE OF MODIFICATION OF THE SYSTEM, AND ABILITY TO CAPTURE EXPERT KNOWLEDGE IN DOMAINS WHERE STRONG DOMAIN THEORIES DO NOT EXIST. MANY CBR SYSTEMS DO A GOOD JOB OF HANDLING STATIC CASES (I.E., CASES THAT REPRESENT A SINGLE POINT IN TIME), BUT DO NOT HAVE FACILITIES FOR DOING TEMPORAL REASONING ACROSS A SET OF CASES. COGNITIVE SYSTEMS PROPOSES TO EXTEND ITS CURRENT CBR SHELL (SEE SECTION F. RELATED WORK) TO INCLUDE USER-FRIENDLY FACILITIES FOR DOING TEMPORAL REASONING. COGNITIVE HAS ALREADY DEVELOPED A GENERIC CBR SHELL WHICH IS CAPABLE OF LIMITED TEMPORAL REASONING (SIMPLE SEQUENCING) AND HAS USED THAT TOOL TO DEVELOP A CASE-BASED NATURAL LANGUAGE PARSER. WE ARE ALSO INVOLVED IN ONGOING DEVELOPMENT OF A MACHINE FAULT DIAGNOSIS SYSTEM WITH LOCKHEED AND OF A NETWORK FAILURE DIAGNOSIS SYSTEM WITH APPLE. BOTH OF THESE PROJECTS HAVE TEMPORAL ISSUES THAT MUST BE ADDRESSED. COGNITIVE WILL USE THE EXPERIENCE GAINED FROM THESE PROJECTS TO GUIDE DEVELOPMENT OF POWERFUL NEW FEATURES TO AID TEMPORAL REASONING. NEW FEATURES WILL INCLUDE INTERFACES TO FACILITATE SPECIFICATION AND MANIPULATION OF TEMPORAL LINKS, AND ENHANCEMENTS TO INDEX GENERATION TO FULLY EXPLOIT ANY TEMPORAL INFORMATION WHICH WILL BE AVAILABLE. IN ADDITION, COGNITIVE WILL USE THE EXISTING CASE-BASES AS A TEST BED FOR THE NEW FEATURES. ANTICIPATED BENEFITS/POTENTIAL COMMERCIAL APPLICATIONS - INCORPORATING TEMPORAL REASONING ABILITIES INTO A CBR SHELL WILL ENABLE THE SHELL TO BE USED IN A WIDE RANGE OF APPLICATIONS AND DOMAINS WHERE REASONING ABOUT TIME IS SIGNIFICANT. IN ADDITION, BUILDING EFFECTIVE INTERFACES FOR REPRESENTING TEMPORAL INFORMATION WILL RESULT IN A REDUCTION IN KNOWLEDGE ENGINEERING TIME REQUIRED TO SPECIFY AND TAKE ADVANTAGE OF TEMPORAL INFORMATION. DEMONSTRATING THE FEASIBILITY OF ADDING TEMPORAL REASONING CAPABILITIES TO A COMMERCIAL CBR SYSTEM MAY ALSO SPUR OTHER COMPANIES TO DEVELOP SIMILAR TECHNOLOGIES. KEY WORDS - ARTIFICIAL INTELLIGENCE, CASE-BASED REASONING, EXPERT SYSTEMS, TEMPORAL REASONING, PARSING, FAULT DIAGNOSIS

Technology keywords

Not reported

Agency intelligence

Department of Defense

Back to SBIR/STTR Research Awards

Don't take our word for it. Ask AI about RFPCapture.

See what leading AI assistants have to say about RFPCapture and CaptureIQ.

Gemini opens without a prefilled question. The question is copied to your clipboard when the button works. You can also copy it here:

What is RFPCapture.com and its CaptureIQ platform from Smart Logic AI? How does it help federal contractors discover opportunities, evaluate bid/no-bid decisions, research government contracts, and prepare proposals? How does it compare with other federal capture platforms? Use independent sources where available.