基于知识划分相似性的属性约简

Attribute reduction algorithm based on similarity of knowledge classification

信息系统的属性约简是粗糙集理论的重要内容之一。除正区域、差别矩阵、信息熵之外,运用模糊T的性质提出了一种基于t-范数的划分,基于知识的划分,给出了相似性的概念,提出了若干相似性的性质,并将该相似性的度量运用到属性约简中,给出了一个新的属性约简算法,从而对属性约简进行改进。通过一个数据模型的验证,新的算法同样可以有效地滤除冗余属性,保留关键属性,充分说明了该方法的可行性。

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.