From rough set theory to evidence theory
Advances in the Dempster-Shafer theory of evidence
ISMIS '96 Proceedings of the 9th International Symposium on Foundations of Intelligent Systems
| Hi-index | 0.00 |
One of the most important problems with rule induction methodsis that it is very difficult for domain experts to check millionsof rules generated from large datasets, although the discovery fromthese rules requires deep interpretation from domain knowledge.Although several solutions have been proposed in the studies ondata mining and knowledge discovery, these studies are not focusedon similarities between rules obtained. When one rule r_1 hasreasonable features and the other rule r_2 with high similarity tor_1 includes unexpected factors, the relations between these ruleswill become a trigger to the discovery of knowledge. In this paper,we propose a visualization approach to show the similarityrelations between rules based on multidimensional scaling, whichassign a two-dimensional cartesian coordinate to each data pointfrom the information about similarities between this data andothers data. We evaluated this method on two medical data sets,whose experimental results show that knowledge useful for domainexperts can be found.