A Methodology for Modeling Influence Diagrams- A Case-Based Reasoning Approach

목차

Abstract
INTRODUCTION
BACKGROUND
Inence Diagram
DCA to Build an ID
Case-Based Reasoning for DCA
CASE REPRESENTATION AND RETRIEVAL
Case Representation
Case Retrieval
NODE CLASSIFICATION TREE AND CASE
ADAPTATION
Knowledge Representation for Case
Adaptation
Adaptation Process
OVERVIEW OF CASE-BASED REASONING
TO BUILD AN INFLUENCE DIAGRAM
CONCLUSIONS
References

본문내용

Abstract In this paper, a case-based reasoning approach to build an inuence diagram
is described. Building an inuence diagram in decision analysis is known to
be a most complicated and burdensome process. To overcome such a dif®culty,
decision class analysis is suggested, which treats a set of decisions having
some degree of similarity as a single unit. This research suggests a case-based
reasoning approach as a methodology to analyze a class of decisions. The
candidate inuence diagrams are retrieved from a set of similar inuence
diagrams, a case base. They are combined and modi®ed by the node classi-
®cation tree and DM`s preference for the given decision problem. For such a
purpose, the case representation and retrieval process is explained with the
adaptation process. We suggest using two measure, the ®tness and garbage
ratio for the case retrieval process.

참고자료

· Bunn DW. 1984. Applied Decision Analysis. McGraw-
· Hill: New York.
· Chung TY, Kim JK, Kim SH. 1992. Building an
· inuence diagram in a knowledge-based decision
· system.Expert Systems With Applications4: 33±44.
· Holtzman S. 1989. Intelligent Decision Systems.
· Addison-Wesley: Reading, MA.
· Howard RA. 1984. The used car buyer. InReadings
· on the Principles and Applications of Decision Analy-
· sis. Vol. II, Howard RA, Matheson JE (eds). Stra-
· tegic Decision Group: Menlo Park, CA.
· Howard RA. 1988. Decision analysis: practice and
· promise.Management Science34: 679±695.
· Kim JK. 1991.A Knowledge-Based System for Decision
· Analysis, Ph.D. thesis, Department of Industrial
· Engineering, KAIST, Korea, 1991.
· Kim JK. 1995. A study on the development of intelli-
· gent decision systems using inuence diagram.
· Journal of the Korean OR/MS Society20: 77±104.
· Kim JK. 1997. Knowledge acquisition for knowledge-
· based decision systems.Applied Arti®cial Intelligence
· 11: 131±149.
· Kim JK, Chung TY, Kim SH. 1992. A knowledge-
· based decision system to build an inuence dia-
· gram: KIDS.Proceedings of the First World Congress
· on Expert Systems, Orlando, FL.
· Kim JK, Chu SC. 1998a. Analyzing a class of decision
· problems: neural network based approach.Proceed-
· ings of the Thirty-®fth Annual Hawaii International
· Conference on System Science, Kona Coast, Hawaii.
· Kim JK, Chu SC. 1998b. `Sensitivity analysis in the
· decision class analysis using neural networks. Pro-
· ceedings of the Fourth World Congress on Expert
· Systems, Mexico.
· Kim JK, Park KS. 1997. Neural network-based
· decision class analysis for building topological-
· level inuence diagram. International Journal of
· Human±Computer Studies46.
· Kolodner J. 1991. Improving human decision making
· through case-based decision aiding. AI Magazine.
· Kolodner J. 1993.Case-Based Reasoning. Morgan Kauf-
· mann: San Francisco: CA.
· Olmsted SM. 1984. On Representing and Solving
· Decision Problems, Ph.D. thesis, Department of
· Engineering Economic System, Stanford Univer-
· sity.
· Reed J. 1989. Building decision models that modify
· decision systems. Knowledge System Laboratory
· No. KSL-89-21, Stanford University, CA.
· Risebeck CK, Schank RS. 1989.Inside Case-based
· Reasoning. Erlbaum: Northvale, NJ.
· Shachter RD. 1986. Evaluating inuence diagrams.
· Operations Research34: 871±882.