TESTING, VERIFICATION, AND VALIDATION OF EXPERT SYSTEMS

In an effort to help test, verify and validate expert systems, this paper addresses key issues in evaluating an expert system: problem complexity; no 'correct answers'; the problem of defining expert level performance; and considerations in knowledge-base refinement. The paper suggests ways to make comparisons between expert system and human expert inferences so that ease of use, knowledge-base adequacy, and completeness may be examined. It is suggested that although some quantitative performance measures are useful for the evaluation process, a qualitative evaluation is also appropriate for many aspects of these kinds of system. Conclusions drawn from the evaluation are presented and discussed.

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 00609185
  • Record Type: Publication
  • Files: TRIS, ATRI
  • Created Date: May 31 1991 12:00AM