直觉模糊系统下的属性约简算法及其应用

Attribute Reduction Algorithm Based on Intuitionistic Fuzzy System and Its Application

信息熵是研究信息粒不确定性度量的一种重要方法,并且可以应用于信息系统的属性约简和综合评估中。本文提出了比较两个直觉模糊值大小的新方法,定义了直觉模糊集中香农熵形式的熵度量。以直觉模糊决策系统为背景,结合直觉模糊集理论,基于直觉模糊相似关系分别构造了直觉模糊信息熵和条件熵,利用直觉模糊条件熵给出属性重要度的计算公式,设计了基于直觉模糊条件熵的启发式属性约简算法。在此基础上,通过属性重要度得到了属性指标的权重,进而提出了一种综合评估方法,并将其应用于安全审计风险的研究中,得到可接受的安全风险评估方法,通过结果对比分析,验证了该方法的可靠性和有效性。

Information entropy is an important method to measure the uncertainty of information particles,and it can be applied to attribute reduction and comprehensive evaluation of information systems.In this paper,a new method to compare the values of two intuitionistic fuzzy sets is proposed,and the entropy measure in the form of Shannon entropy in intuitionistic fuzzy sets is defined.Based on the intuitionistic fuzzy decision system and the theory of intuitionistic fuzzy sets,the intuitionistic fuzzy information entropy and conditional entropy are constructed respectively,the formula for calculating attribute importance is given by intuitionistic fuzzy conditional entropy,and a heuristic attribute reduction algorithm based on the intuitionistic fuzzy conditional entropy is designed.On this basis,the weight of attribute index is obtained by attribute importance degree,then a comprehensive evaluation method is put forward and applied to the study of security audit risk,and an acceptable security risk evaluation method is obtained,the reliability and validity of the method are verified by the comparison and analysis of the results.