区间值不协调信息系统基于变精度优势关系的知识约简算法

Knowledge Reduction Algorithm of Interval-valued Inconsistent Information Systems Based on Variable Precision Dominance Relation

知识约简是粗糙集理论的重要研究内容.针对区间值不协调决策信息系统的特点,引入优势可能度和变精度优势关系概念,提出一种基于优势关系类的属性约简算法.该算法通过确定分配区分对象集和区分函数的最小析取范式从而得到分配约简集,给出了具体的算法步骤.理论分析和实例表明该文算法的有效性和合理性.

Knowledge reduction of information system is an important research content of data mining.According to the characteristics of the interval-valued inconsistent information system,the paper introduces the concepts of precision dominance relation and assignment reduction,and puts forward to an attribution reduction algorithm based on dominance relation classification.The algorithm accesses attribution reduction sets by determining assignment set of objects and assignment function minimum disjunctive normal form.Theoretical analysis and examples are used to illustrate that the proposed algorithm is effective and rational.