Choquet模糊积分的粗糙性及信息融合  

Roughness of Choquet Fuzzy Integral and Information Fusion

作　　者：管涛[1] 冯博琴[1] 

机构地区：[1]西安交通大学电子与信息工程学院,西安710049

出　　处：《西安交通大学学报》2004年第12期1251-1255,共5页Journal of Xi'an Jiaotong University

基　　金：国家高技术研究发展计划资助项目 (2 0 0 3AA1Z2 6 10 )

摘　　要：在分析现有模糊积分理论的基础上 ,提出了Choquet上、下模糊积分的概念和粗糙区间数的积分形式 ,给出了Choquet模糊积分的粗糙特性 ,建立了基于粗糙Choquet模糊积分形式和信息融合方法 .该方法在存在各种外界干扰因素的多传感器融合环境中 ,可以较好地实现区间数传感器的选择和融合 .所给Cho quet上、下模糊积分是经典Choquet模糊积分在粗糙意义下的扩展形式 ,能处理粗糙区间数数据源和信息系统的对象 .Based on the analysis of existed fuzzy integral theories, the notions of the Choquet upper and lower fuzzy integral and rough interval numbers' integral form were proposed; the rough properties of Choquet fuzzy integral and an information fusion method based on rough Choquet fuzzy integral were given. The method can properly carry out the selection and fusion of interval number sensors in multi-sensor fusion environment in which various disturbance factors exist. The Choquet upper and lower fuzzy integral is the extended form of the classical Choquet one in a sense of roughness, which can deal with the data sources of rough intervals and objects of information systems. The simulated experiments have validated the effectiveness of the method.

关 键 词：模糊积分 粗糙集 信息融合 区间数 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]