DSmT相关证据模型及反问题近似解求法  

A Dependent Evidence Model of DSmT and the Approximate Solution of the Inverse Problem

作　　者：王进[1] 孙怀江[1] 

机构地区：[1]南京理工大学计算机科学与技术学院,南京210094

出　　处：《计算机科学》2007年第9期200-202,244,共4页Computer Science

基　　金：南京理工大学青年学者基金资助(编号NJUST200304)

摘　　要：介绍了一种新的信息融合理论——DSmT(Dezert-Srnarandache Theory)。在DSmT下,鉴于实际处理的证据经常是相关证据,提出了一种新的模型表示相关证据。其中两个相关证据各自由一个独立源证据和一个相关源证据正交和合成,相关证据的合成就归结为这两个独立源证据和这个相关源证据的正交和合成。辨识独立源证据是一个反问题,该反问题可能不存在唯一精确解,此时采用了粒子群优化算法求其近似解。A new information fusion theory--Dezert-Smarandache Theory is introduced. In this framework a new model is proposed to represent dependent evidences for the case that the evidences we usually have are dependent. In this model, two dependent evidences are considered resulted from orthogonal sum of one dependent original evidence and two independent original evidences, respectively. Combining the two dependent evidences can be reduced to an orthogonal sum of the two independent original evidences and the dependent original evidence. Identifying the independent original evidences is an inverse problem. The inverse problem does not always have a unique exact solution, and the PSO arithmetic is adopted for the approximate solution of the inverse problem.

关 键 词：DEZERT-SMARANDACHE理论 证据理论 智能系统 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]