贝叶斯网络中因果链搜索算法及其应用研究

Research on Algorithm for Detecting Cause-and-effect Chains in Bayesian Network and its Applications

将有向无环网络中简单路径的搜索算法用于贝叶斯网络中的因果链搜索。根据因果链上节点的条件概率表,计算出每条因果链中各节点的状态概率,从而完成了概率的传播和更新。本文所提出的因果链上的前向和后向推理方法可用于因果链敏感性分析,为科学决策提供依据。

Applying directed acyclic network＇ simple path detecting algorithm to Bayesian network＇ cause-and-effect chains detecting. According to the nodes＇ conditional probability table of the cause-and-effect chains, we can calculate the nodes＇ status probability and complete the probability＇s spread and renew in each cause-and-effect chains. Applying the onward and backward reason method in this text to the cause-and-effect chains＇ sensitive analysis, it can provide the basis for the sciencal decision.