Fuzzy Systems and Data Mining

Data mining and fuzzy systems share an important common feature that is information granulation. Information granules, and fuzzy sets exploited in the setting of this study, are used to reveal stable, transparent and meaningful patterns in databases. While there exists panoply of various forms of patterns, we focus on associations and rules as the two commonly encountered constructs that exist both in data mining and fuzzy systems. Associations are modeled in the language of fuzzy relations and are direction-free concepts meaning that they are not concerned as to the question "what implies what". Rules, on the other hand, are direction — based constructs with clearly delineated cause and effect (condition and conclusion). Moreover, it is shown that associations and rules are tied together: associations may entail rules but no other way around. We discuss the role of information granularity in determining consistency of the rules and analyze an impact that linguistic quantification of fuzzy sets has on the consistency of the individual rules. An idea of rule growing is also discussed.