Based On Fuzzy Rough Set Attribute Reduction

Rough set theory and Fuzzy set theory are two different mathematical methods for represent the uncertain knowledge. RS theory was proposed by Pawlak in 1982.The focus of RS theory is on the ambiguity caused by limited discernibility of objects in domain of discourse.Fuzzy set theory was proposed by Zadeh in 1965 and hinges on the notion of a membership function on the domain of discourse, assigning to each object a grade of belongingness in order to represent an imprecise concept.The combination of fuzzy sets and rough sets are a new study and is very value in fact.The paper in just based on combination between fuzzy set and rough set, and mainly makes reseach on reduction of attribute.Our work lists as below:1. Introduce the background of RS and FS theory. This paper compares the fuzzy set and the rough set to show the advantage of combination on attribute reductions.2. Introduce the algorithm of attribute reduction based on discernibility matrix and through analyzing to find the shortage, and then present an improved algorithm.The heuristic reduction algorithm based on the feature weight is more natural and easier in computation and improves the reduction algorithm in speed.3. Summarize some kinds of algorithms for dealing with incomplete data.4. Consider the similarity of objects,we propose fuzzy...