一种基于邻域容差信息熵的组合度量方法

在实际应用中,大多数信息系统中的数据都是混合的,为了度量混合信息系统的不确定性,本文提出了一种组合度量方法.首先在不完备邻域粗糙集中定义了混合近似精度和混合近似粗糙度的概念;接着考虑到这两种单一度量方法对信息系统不确定性评估的不足,然后,进一步引入邻域容差信息熵的概念;最后将混合近似粗糙度和邻域容差信息熵这两种单一度量进行结合提出一种组合度量方法,并且研究了相关性质.UCI实验结果表明,本文所提出的方法在混合信息系统中具有更好的不确定性度量效果,从而验证了该度量方法具有一定的优越性,并且从理论上也证明了该方法的可行性.

Combination Measurement Method Based on Neighborhood Tolerance Information Entropy

In practical applications,most of information systems are mixed type,in order to measure the uncertainty for the mixed information system,a combination measurement method is proposed in this paper.Firstly,the concepts of the mixed approximation accuracy and the mixed approximation roughness are defined in incomplete neighborhood rough set.And then,in consideration of these two single metrics exist some defects for uncertainty assessment of information system,and the concept of the neighborhood tolerance information entropy is further introduced.Finally,a combination measurement method is proposed by combining the mixed approximation roughness with the neighborhood tolerance information entropy,and the related properties are studied.Experimental results of UCI showthat the proposed method has better uncertainty measurement effect in neighborhood information system with hybrid value.Therefore,the proposed uncertainty measurement method has a certain superiority,and the feasibility of the proposed method is also proved theoretically.