基于钟型函数的基本信度指派生成方法  

A Generation Method of Basic Belief Assignment Based on Bell Function

作　　者：郭威[1] 朱珂[1] 吴毅涛 肖二宁 吕平[1] 宋克[1] 

机构地区：[1]国家数字交换系统工程技术研究中心,河南郑州450002

出　　处：《电子学报》2016年第4期926-932,共7页Acta Electronica Sinica

基　　金：国家973重点基础研究发展计划(No.2012CB315901)

摘　　要：针对认知目标属性为单点值情况下,利用模糊相似度生成证据理论的基本信度指派(Basic Belief Assignment,BBA)存在悖论的问题,本文提出一种基于钟型函数(Bell Function,Bell-F)的相似度确定方法和相应的BBA生成算法.该方法避免了上述悖论算例与实际相左的情况,且能够细粒度刻画相似度评估模型,进一步提高了认知描述的准确性.通过对鸢尾花数据集进行识别实验,结果证明了该方法的有效性,并且对已知样本数量不足的非确定环境具备较好的适应能力.In this paper, a method to determine similarity and the basic belief assignment （BBA） generation based on bell function （Bell-F） is proposed in order to solve the problem that the fuzzy similarity used in BBA of evidence theory ex- ist paradox when the cognitive objective is a single point. This method can avoid the paradox which is inconsistent with the actual result in common sense, and can more granularly describe similarity evaluation model to improve the accuracy of cog- nitive description further. The results of a recognition experiment performed for data set of Iris, demonstrate the effectiveness of this method. Furthermore, this method still has good adaptability in uncertain environment when the number of known samples is insufficient.

关 键 词：证据理论 基本信度指派 钟型函数 相似度评估模型 认知描述 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]