摘要
针对影响图在实际应用中的参数建模困难问题,提出了一种扩展的影响图.引入credal集作为影响图的概率参数,以表达专家的不精确和不完整信度,集成多来源的定性和定量信息.引入credal集后,影响图的推理难度进一步加大.提出了将其转化为credal网络求解的思路,并给出了一种基于路径选择的求解算法.最后用一个实例验证了算法的有效性.
As it is usually difficult to specify precise probabilities when using influence diagrams in practice , an extended influence diagram with credal set as its parameter is proposed, in which credal set is used to represent experts＇ imprecise belief. Then the extended influence diagram is evaluated by being changed into credal networks and an algorithm based on path selection is proposed. Finally, an example is given to show the effectiveness of the evaluation algorithm.
出处
《数学的实践与认识》
CSCD
北大核心
2011年第17期162-167,共6页
Mathematics in Practice and Theory
基金
北京市教育委员会科研基地建设项目(WYJD200902)
北京市属高等学校人才强教计划资助项目(PHR200906210)
北京物资学院青年基金项目(2011XJQN002)
