基于贝叶斯网络的突发事件影响度研究  

Research on influence degree of emergent events based on Bayesian network

作　　者：鞠彦兵[1] 王爱华[2] 

机构地区：[1]北京理工大学管理与经济学院,北京100081 [2]北京大学教育学院,北京100871

出　　处：《自然灾害学报》2011年第5期40-46,共7页Journal of Natural Disasters

基　　金：国家自然科学基金委员会与中国民用航空总局联合资助(60672180);国家自然科学基金资助(70972007);北京市自然科学基金(9102015)

摘　　要：不确定性的知识表示和推理是突发事件影响度评估中需要解决的重要问题。针对突发事件评估信息的多样性、不确定性及模糊性,利用贝叶斯网络易于进行不确定性推理的优点,提出了采用贝叶斯网络对突发事件影响度进行评价,建立了评价模型,给出了推理决策方法,并且对该方法进行了算例分析。算例表明,基于贝叶斯网络的突发事件影响度评价模型能够提高评估的准确度及对突发事件的响应能力。Knowledge denotation and deduction of uncertainty are important issue to be solved in evaluating influ- ence degree of emergent events. Aim at the diversity, uncertainty and fuzziness of assessment information about emergent event, based on the merit of Bayesian network in dealing with uncertainty influence, the Bayesian network emergent event influence assessment model and corresponding deductive decision-making method were presented in this paper. The results show that the assessment model can improve the assessment accuracy and ability of the response to the influence of emergent event.

关 键 词：贝叶斯网络 突发事件 影响度 

分 类 号：X43[环境科学与工程—灾害防治]