Abstract | ||
---|---|---|
The ultimate goal in the development of decision support systems is to reach the competence and flexibility set by the human
standard. We present an approach which is aimed at the efficient handling of situations with incomplete and partially inconsistent
data. Its static structure is derived from a hierarchical implementation of the Dempster/Shafer Belief theory, which is extended
towards a multi-layered representation by a set of hierarchies. The dynamic behavior is controlled by an adaptive strategy which can reduce the specific problems which may arise due to the predetermined strategies like “best hypotheses”,
“establish-refinetechniques”, “hypothetic-deductive strategies”. The suggested strategy is based on the principle of maximum
information gain and is able to take the complete “activation pattern” of the representation into account. Acting together,
both components can provide reasonable reactions even in ambiguous and ill-defined situations.
|
Year | DOI | Venue |
---|---|---|
1997 | 10.1007/BFb0052110 | Foundations of Computer Science: Potential - Theory - Cognition |
Keywords | Field | DocType |
decision support systems,adaptive reasoning strategies,dempster shafer,decision support system,information gain | Belief theory,Data collection,Adaptive strategies,Intelligent decision support system,Computer science,Adaptive reasoning,Decision support system,Artificial intelligence,Evidential reasoning approach,Hierarchy,Machine learning | Conference |
ISBN | Citations | PageRank |
3-540-63746-X | 6 | 0.55 |
References | Authors | |
2 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kerstin Schill | 1 | 183 | 25.15 |