关键词: 粗糙集, 属性约简, 相似性, 等价类, t-范数

Abstract: Attribute reduction in information system is one of the most important contents of rough set theory. In addition to positive region, discernibility matrix and information entropy, an division based on the t-norm is put forward by using the nature of fuzzy T. The concept of similarity and the natures of the similarity are put forward based on the division of knowledge. A new attribute reduction algorithm is given by applying the similarity measure on attribute reduction, thus to improve the attribute reduction. Through a data model, the new algorithm can effectively filter out the redundant attributes and retain key attributes, illustrates the feasibility of this method.

Key words: rough set, attribute reduction, similarity, equivalence class, t-norm