透過您的圖書館登入
IP:18.190.156.80
  • 學位論文

以模糊理論建置貝氏認知網路風險評估模型

Using Fuzzy Theory to create Bayesian belief network for risk assessment

指導教授 : 徐煥智

摘要


本研究透過模糊理論整合貝氏認知網路建置風險評估模型進行風險評估。將所要推估之風險事件的觀察值運用模糊理論進行處理及量化成一個模糊數,並設置模糊規則表以建立貝氏認知網路中所需之條件機率表。根據此方法,可輕易地建置基於貝氏認知網路的風險評估模型。為了驗證本研究所提出之模型的可行性,本研究建立飛航風險評估模型,並透過數個實際案例進行評估。

並列摘要


This study integrates fuzzy theory and Bayesian belief network (BBN) to create a risk assessment model. The observed value in an event is defined as a Fuzzy number. Rule tables are conducted to create conditional probability tables in a BBN model. According to the proposed methodology, the risk assessment model based on BBN can be developed easily. To verify the feasibility of our proposed model, a flight risk assessment model has been created, and several practical cases have been evaluated.

參考文獻


[2] 葉鎰維,《基於雲端運算的飛航作業風險評估架構》,碩士論文,淡江大學資訊管理學系,2012。
[4] 黃永福,《以模糊專家系統實作軟體專案調適準則》,碩士論文,國立中央大學資訊管理研究所,2007。
[7] Balaram Das., "Generating Conditional Probabilities for Bayesian Networks," Computing Research Repository, 2004.
[8] Booker, J. M., and M. A. Meyer., "Uncertainty Quantification: Methods and Examples from Probability and Fuzzy Theories," Automation Congress, 2002 Proceedings of the 5th Biannual World, pp. 135-140, 2002.
[9] Borsuk, M. E., C. A. Stow, and K. H. Reckhow., "A Bayesian Network of Eutrophication Models for Synthesis, Prediction, and Uncertainty Analysis," Ecological Modelling (173:2–3), 4/1, pp. 219-239, 2004.

延伸閱讀