A new approach to mining fuzzy databases using nearest neighbor classification by exploiting attribute hierarchies

Data classification is a well-organized operation in the field of data mining. This article presents an application of the k-nearest neighbor classification technique for mining a fuzzy database. We consider a data set in which attribute values have certain similarities in nature and analyze the observations for the domain of each attribute, on the basis of fuzzy similarity relations. The proposed technique is general and the presented case study demonstrates the suitability of using this fuzzy approach for mining fuzzy databases, especially when the database contains various levels of abstraction. (C) 2004 Wiley Periodicals, Inc.