Rule-based Functionality for Decision Making with Reasoning and Its Application: Case Studies on Three Data Sets.

We have been coping with rough set-based rule generation and Apriori-based rule generation. We developed a software tool termed "NIS-Apriori." The software tool makes use of the characteristics of both rough sets and the Apriori algorithm. This NIS-Apriori generates certain rules and possible rules based on the possible world semantics, and the mathematical properties of "soundness and completeness" for defined rules are preserved. Some important propositions have been proved for the framework of the NIS-Apriori. We are now applying this environment to several different data sets, and we especially describe three cases of data sets in this paper. This paper newly considers the rule-based functionality for decision making with reasoning, which will recover the black-box problem in recent AI. [ABSTRACT FROM AUTHOR]