Extended Belief Rule Base Inference Methodology

摘要：

A belief Rule-base Inference Methodology usingthe Evidential Reasoning approach(RIMER)has beendeveloped recently,which is an extension of traditionalrule based systems and is capable of representingmore complicated causal relationships using differenttypes of information with uncertainties.A rule-base inRIMER is designed with belief degrees embedded in allpossible consequents of a rule,where it is assumedthat all the consequents are independent of each otherin order to accommodate the assumption imposed onthe evidential reasoning(ER)algorithm being used.Toovercome this limitation,in the paper,we extend theRIMER approach to the case of fuzzy consequents,thatis,each consequent can be defined as a fuzzy linguisticterm because of vagueness and inexactness,in suchcases,the intersection of adjacent two fuzzy sets is nolonger an empty set,which results in the above ERalgorithm inapplicable during the inference process,instead,the inference of the belief rule-based system isimplemented using an extended fuzzy ER algorithm.This work extends the applieality and feasibility of theRIMER approach.

作者: Jun Liu Luis Martinez Ying-Ming Wang

作者单位: School of Computing and Mathematics,Univ.of Ulster at Jordanstown Northern Ireland,UK School of Computing,Dept.of Computer Science,University of Jaen,23071 Jaen,Spain School of Public Administration,Fuzhou University Fuzhou,China

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 1415-1420

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）