一种基于核集与相似性的模糊推理方法

在稀疏规则库条件下,当给定的输入落入规则"间隙"时,采用传统的模糊推理方法是得不到任何结论的.学者已经证明模糊推理本质上就是插值器.Koczy和Hirota首先提出了KH线性插值推理方法,然而推理结果存在着无法保证凸性和正规性等问题.为了能有一个较好的插值推理结果,本文提出了一种基于核集与相似性的模糊插值推理方法,并把此方法扩展到多维变量的情况,该方法不仅推理简单,推理结果较好,并且能很好地保证推理结果的凸性和正规性.这为智能系统中的模糊推理提供了一个非常有用的工具.

Fuzzy Interpolative Reasoning Method Based on Center Set and Similarity

When rule base is sparse,we cannot get any reasoning result by traditional fuzzy reasoning method for an observation is in the gap between two neighboring antecedents.Authors have proved that fuzzy reasoning is really equal to a interpolation.Hence Koczy and Hirota first proposed KH linear interpolative reasoning method.But its consequence does not always keep convexity and normality.So this paper presents a fuzzy interpolative method based on center set and similarity.And it is extended to handle the multidimensional variables fuzzy reasoning.Reasoning is simple by the method;moreover it can keep the convexity of the reasoning consequence.