跳到主要內容

臺灣博碩士論文加值系統

(44.213.60.33) 您好!臺灣時間:2024/07/17 04:03
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:裴光雅
研究生(外文):Quang-Nha Bui
論文名稱:ANovelBayesianNetworkConstructionMethodforEngineeringRiskAssessment
論文名稱(外文):A Novel Bayesian Network Construction Method for Engineering Risk Assessment
指導教授:呂守陞呂守陞引用關係
指導教授(外文):Sou-Sen Leu
學位類別:碩士
校院名稱:國立臺灣科技大學
系所名稱:營建工程系
學門:工程學門
學類:土木工程學類
論文種類:學術論文
論文出版年:2010
畢業學年度:98
語文別:英文
論文頁數:152
中文關鍵詞:Expert KnowledgeStructural LearningBayesian NetworkRisk analysis
外文關鍵詞:Expert KnowledgeStructural LearningBayesian NetworkRisk analysis
相關次數:
  • 被引用被引用:0
  • 點閱點閱:225
  • 評分評分:
  • 下載下載:4
  • 收藏至我的研究室書目清單書目收藏:0
Assessment of risk events in construction project plays a key role for project success. One novel approach for risk assessment in construction project is the application of Bayesian network (BN), which incorporates existing knowledge into a probabilistic model for risk estimation, has been proven to be efficient. However, one bottleneck in using Bayesian network is that learning BN often requires a large amount of training data, which is impracticable in most of engineering fields, including construction engineering. On the other hand, BN which is merely established with support from domain experts based on their experience is often inaccurate due to bias assessments. This research proposes a generalized framework for Bayesian network construction for risk assessment in construction industry in particular, and in other engineering domains in general. Our model will combine both limited historical data and knowledge from experts into BN learning process, which simultaneously learning the structure and parameters of BN. The resulted methodology is then applied to assess reliability in a Hydro Power Plant as an illustrative case study. Our preliminary results show that incorporating prior knowledge from experts into Bayesian learning can help discover causal relationships present in the network as well as improve accuracy of risk assessment.
Assessment of risk events in construction project plays a key role for project success. One novel approach for risk assessment in construction project is the application of Bayesian network (BN), which incorporates existing knowledge into a probabilistic model for risk estimation, has been proven to be efficient. However, one bottleneck in using Bayesian network is that learning BN often requires a large amount of training data, which is impracticable in most of engineering fields, including construction engineering. On the other hand, BN which is merely established with support from domain experts based on their experience is often inaccurate due to bias assessments. This research proposes a generalized framework for Bayesian network construction for risk assessment in construction industry in particular, and in other engineering domains in general. Our model will combine both limited historical data and knowledge from experts into BN learning process, which simultaneously learning the structure and parameters of BN. The resulted methodology is then applied to assess reliability in a Hydro Power Plant as an illustrative case study. Our preliminary results show that incorporating prior knowledge from experts into Bayesian learning can help discover causal relationships present in the network as well as improve accuracy of risk assessment.
ACKNOWLEDGEMENTS II
Abstract IV
Table of Contents V
List of Figures VIII
List of Tables XII
Notations XIV
Chapter 1 INTRODUCTION 1
1.1 Research Background 1
1.2 Research Objective 3
1.3 Research Scope 4
1.3.1 Boundary Identification 4
1.3.2 Research assumptions 5
1.4 Research Outline 5
Chapter 2 LITERATURE REVIEW 8
2.1 Bayesian network in engineering risk assessment 8
2.2 Learning Bayesian Network 11
2.3 Problem of learning with incomplete data 16
Chapter 3 RESEARCH METHODOLOGY 19
3.1 Life Cycle of a Bayesian Network: From construction to application 19
3.2 Bayesian Networks 23
3.3 Joint probability distribution in Bayesian network 26
3.4 Inference in Bayesian Network 29
3.4.1 Fundamental of inference techniques in BN 29
3.4.2 Exact Inference in BN 31
3.5 Sampling data from Bayesian Network 38
3.6 Learning Bayesian Network 40
3.6.1 The Expectation-Maximization (EM) Algorithm 42
3.6.2 Structural Expectation Maximization (SEM) 43
3.6.3 Scoring functions for BN structure learning 45
Chapter 4 Expert Based Structural EM Learning 50
4.1 Generalized Ex-SEM framework for construction risk assessment 50
4.2 Data collection and preprocessing 53
4.2.1 Observation data 53
4.2.2 Initial Bayesian network 54
4.2.3 Bayesian networks by experts 55
4.3 New score function based on observation data and expert knowledge 56
4.4 Ex-SEM learning with expert’s BN structures 59
4.5 Ex-SEM II learning with complete information from Experts’ BNs 68
Chapter 5 MODEL VALIDATION 72
5.1 Experiment design 72
5.2 Performance measures 75
5.2.1 Structural difference 75
5.2.2 KL divergence (cross entropy) 76
5.2.3 Negative Log-likelihood 77
5.3 Experiment results and comparison 77
5.3.1 Sensitivity analysis with parameters setup 77
5.3.2 Results comparison with SEM and K2 84
Chapter 6 CASE STUDY 94
6.1 Overview of Shih-men Hydro Power Plant 95
6.1.1 Location 95
6.1.2 Plant Facilities 96
6.2 Data collection and preprocessing 98
6.2.1 Initial BN 98
6.2.2 Observation data 100
6.2.3 Data from experts elicitation 101
6.3 Model Implementation 103
6.3.1 Parameters setup 103
6.3.2 Performance measure 103
6.3.3 Results 105
Chapter 7 CONCLUSION 111
7.1 Conclusion 111
7.2 Future research direction 112
Bibliography 113
Appendix A i
Appendix B viii
Appendix C xiv
Appendix D xix
Ahn, J.-H. and K. J. Ezawa (1997). "Decision support for real-time telemarketing operations through Bayesian network learning." Decision Support Systems 21(1): 17-27.
Antal, P., G. Fannes, et al. (2004). "Using literature and data to learn Bayesian networks as clinical models of ovarian tumors." Artificial Intelligence in Medicine 30(3): 257-281.
Bai, C.-G. (2005). "Bayesian network based software reliability prediction with an operational profile." Journal of Systems and Software 77(2): 103-112.
Boudali, H. and J. B. Dugan (2005). "A discrete-time Bayesian network reliability modeling and analysis framework." Reliability Engineering & System Safety 87(3): 337-349.
Campos, L. M. d. (2006). "A Scoring Function for Learning Bayesian Networks based on Mutual Information and Conditional Independence Tests." J. Mach. Learn. Res. 7: 2149-2187.
Chickering, D. M., D. Heckerman, et al. (2004). "Large-Sample Learning of Bayesian Networks is NP-Hard." J. Mach. Learn. Res. 5: 1287-1330.
Chou, J.-S. (2009). "Generalized linear model-based expert system for estimating the cost of transportation projects." Expert Systems with Applications 36(3, Part 1): 4253-4267.
Clarotti, C. A. and D. V. Lindley, Eds. (1988). Accelerated Life Testing and Experts' Opinions in Reliability.
Cooper, G. F. and E. Herskovits (1992). "A Bayesian method for the induction of probabilistic networks from data." Machine Learning 9(4): 309-347.
de Campos, L. M., J. M. Fernández-Luna, et al. (2002). "Ant colony optimization for learning Bayesian networks." International Journal of Approximate Reasoning 31(3): 291-311.
Dempster, A. P., N. M. Laird, et al. (1977). "Maximum Likelihood from Incomplete Data via the EM Algorithm." Journal of the Royal Statistical Society. Series B (Methodological) 39(1): 1-38.
Doguc, O. and J. E. Ramirez-Marquez (2009). "A generic method for estimating system reliability using Bayesian networks." Reliability Engineering & System Safety 94(2): 542-550.
Elidan, G. and N. Friedman (2005). "Learning Hidden Variable Networks: The Information Bottleneck Approach." J. Mach. Learn. Res. 6: 81-127.
Elidan, G., M. Ninio, et al. (2002). Data perturbation for escaping local maxima in learning. Eighteenth national conference on Artificial intelligence. Edmonton, Alberta, Canada, American Association for Artificial Intelligence: 132-139.
Friedman, N. (1998). "The Bayesian structural EM algorithm". In UAI.
Giudici, P. and R. Castelo (2003). "Improving Markov Chain Monte Carlo Model Search for Data Mining." Machine Learning 50(1): 127-158.
Heckerman, D. (2008). A Tutorial on Learning with Bayesian Networks: 33-82.
Heckerman, D., D. Geiger, et al. (1995). "Learning Bayesian networks: The combination of knowledge and statistical data." Machine Learning 20(3): 197-243.
Henrion, M. (1986). "Propagating uncertainty in bayesian networks by probabilistic logic sampling". UAI.
Henrion, M. (1987). "Practical Issues in Constructing a Bayes' Belief Network". Proceedings of the Proceedings of the Third Conference Annual Conference on Uncertainty in Artificial Intelligence-UAI-87, New York, NY, Elsevier Science.
Jan, M., zcaron, et al. (2006). "A simulated annealing-based method for learning Bayesian networks from statistical data." International Journal of Intelligent Systems 21(3): 335-348.
Jones, B., I. Jenkinson, et al. (2010). "The use of Bayesian network modelling for maintenance planning in a manufacturing industry." Reliability Engineering & System Safety 95(3): 267-277.
Korb, K. B. and A. E. Nicholson (2003 ). Bayesian Artificial Intelligence CRC Computer Science & Data Analysis, Chapman & Hall.
Krishnamurthy, S. and A. P. Mathur (1997). "On The Estimation Of Reliability Of A Software System Using Reliabilities Of Its Components." Proceedings of the Eighth International Symposium on Software Reliability Engineering, IEEE Computer Society: 146.
Kullback, S. and R. A. Leibler (1951). "On Information and Sufficiency." The Annals of Mathematical Statistics 22(1): 79-86.
Luu, V. T., S.-Y. Kim, et al. (2009). "Quantifying schedule risk in construction projects using Bayesian belief networks." International Journal of Project Management 27(1): 39-50.
Mani, S., M. Valtorta, et al. (2005). "Building bayesian network models in medicine: The MENTOR experience." Applied Intelligence 22(2): 93-108.
Marsh, W. and G. Bearfield (2008). "Representing Parameterised Fault Trees Using Bayesian Networks". Computer Safety, Reliability, and Security: 120-133.
Murphy, K. (2001). "The Bayes Net Toolbox for MATLAB." Computing Science and Statistics 33.
P. Leray and O. Francois (2005). "Bayesian Network Structural Learning and Incomplete Data". Proceedings of the International and Interdisciplinary Conference on Adaptive Knowledge Representation and Reasoning ({AKRR 2005}). Espoo, Finland, 2a-ConfInt: 33-40.
Pearl, J. (1988). "Probabilistic reasoning in intelligent systems: networks of plausible inference", Morgan Kaufmann Publishers Inc.
Peña, J. M., J. A. Lozano, et al. (2000). "An improved Bayesian structural EM algorithm for learning Bayesian networks for clustering." Pattern Recognition Letters 21(8): 779-786.
Ramoni, M. and P. Sebastiani (2001). "Robust Learning with Missing Data." Mach. Learn. 45(2): 147-170.
Schulte, O., G. Frigo, et al. (2009). "A new hybrid method for Bayesian network learning With dependency constraints." Computational Intelligence and Data Mining, 2009. CIDM '09. IEEE Symposium on.
Simon, C., P. Weber, et al. (2008). "Bayesian networks inference algorithm to implement Dempster Shafer theory in reliability analysis." Reliability Engineering & System Safety 93(7): 950-963.
Tam, C. M., S. X. Zeng, et al. (2004). "Identifying elements of poor construction safety management in China." Safety Science 42(7): 569-586.
Verma, T. and J. Pearl (1992). An Algorithm for Deciding if a Set of Observed Independencies Has a Causal Explanation. Proc. of the Eighth Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann.
Wai, L. (1998). "Bayesian network refinement via machine learning approach." Pattern Analysis and Machine Intelligence, IEEE Transactions on 20(3): 240-251.
Wang, X. R. and F. T. Ramos (2005). Applying structural em in autonomous planetary exploration missions using hyperspectral image spectroscopy. 2005 IEEE International Conference on Robotics and Automation, April 18, 2005 - April 22, 2005, Barcelona, Spain, Institute of Electrical and Electronics Engineers Inc.
Wong, M. L. and Y. Y. Guo (2008). "Learning Bayesian networks from incomplete databases using a novel evolutionary algorithm." Decision Support Systems 45(2): 368-383.
Zhou, Q., D. Fang, et al. (2008). "A method to identify strategies for the improvement of human safety behavior by considering safety climate and personal experience." Safety Science 46(10): 1406-1419.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top