簡易檢索 / 詳目顯示

回結果列表
研究生： 黃沁琪
Chin-Chi Huang
論文名稱： 演化式高斯過程推論模式於營建工程與管理決策支援之研究
Evolutionary Gaussian Process Inference Model (EGPIM) for Decision-Making in Construction Engineering and Management
指導教授： 鄭明淵
Min-Yuan Cheng
口試委員: 郭斯傑
Sy-Jye Guo
曾惠斌
Hui-Ping Tserng
王維志
Wei-Chih Wang
姚乃嘉
Nie-Jia Jerry Yau
周瑞生
Jui-Sheng Chou
楊亦東
I-Tung Yang
學位類別： 博士
Doctor
系所名稱： 工程學院 - 營建工程系
Department of Civil and Construction Engineering
論文出版年： 2013
畢業學年度： 101
語文別： 英文
論文頁數： 122
中文關鍵詞： 營建管理 、貝氏推論 、粒子群演算法 、高斯過程
外文關鍵詞： Bayesian inference, Particle swarm optimization, Gaussian process, project success, EGPIM
相關次數： 點閱：371  下載：7 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 營建工程具有複雜、不確定與隨環境變動的特性，因此，在解決相關問題時多仰賴該領域專家經驗與知識進行決策。本研究的主要目的為發展一最佳化預測模式，透過過去案例與經驗，學習歸納專家經驗與分析邏輯，以提昇營建工程與管理決策的有效性。近年來，基於統計原理的人工智慧技術- 高斯過程被廣泛運用於各領域，本研究透過案例學習發展建立一套演化式高斯過程推論模式(Evolutionary Gaussian Process Inference Model, EGPIM)，改善以往高斯過程中，參數選取需耗費過多時間及系統效能的缺點。模式利用高斯過程(Gaussian Process, GP)釐清資料中輸入及輸出值間的映射關係，並利用貝氏推論(Bayesian inference)，結合粒子群演算法(particle swarm optimization, PSO)優化 GP 內共變異函數的超參數，以獲得最佳的推論預測能力。本模式經由實務案例驗證，證明可運用於營建工程與管理相關預測問題，並且對於預測事件給予一期望值與變異數，求得預測之信賴區間，提供決策者較為客觀之決策參考依據。

    Construction decision-making often involves several indefinite factors, where erroneous decisions can lead to large losses and may even cause the construction project to fail.
    Correct policy making is thus very important. Construction decision making generally depends on managerial staff experience and subjective recognition, but this approach is likely to result in errors because of the excessive number of factors involved or biased subjective recognition. To prevent such errors, this study establishes an Evolutionary Gaussian Process Inference Model (EGPIM), which uses a Gaussian process (GP) to sort out the mapping relationship between data input and output. It also uses Bayesian
    inference together with particle swarm optimization (PSO) to optimize the Hyper-parameters of the covariance function in GP to obtain the best inference predictive ability. By making predictions using the model and assigning the events that need to be decided an expected value and a variance; we can establish the data’s confidence interval as a reference for making decisions.
    This study collects data from six construction projects to conduct the experiment
    and uses EGPIM to train, predict, and retest these cases to demonstrate EGPIM’s
    predictive ability. It also shows that the model can be applied to a variety of cases and
    data sets and thus is useful in construction engineering decision making.

    ABSTRACT 2 ACKNOWLEDGEMENTS 4 TABLE OF CONTENTS 5 ABBREVIATIONS AND SYMBOLS 9 LIST OF FIGURES 14 LIST OF TABLES 15 CHAPTER 1 INTRODUCTION 16 1.1 Research Motivation 16 1.2 Research Objective 18 1.3 Scope Definition 19 1.3.1 Boundary Identification 19 1.3.2 Research Hypotheses and Assumptions 20 1.4 Research Methodology 21 1.4.1 Problem Formulation 23 1.4.2 Literature Review 24 1.4.3 Model Construction 25 1.4.4 System Development 25 1.4.5 Assessment 26 1.5 Study Outline 26 CHAPTER 2 BAYESIAN INFERENCE, GAUSSIAN PROCESS (GP), AND PARTICLE SWARM OPTIMIZATION (PSO) 28 2.1 Bayesian Inference 28 2.1.1 Basic Concepts 28 2.1.2 Advantages and Disadvantages 31 2.2 Gaussian process regression 33 2.2.1 Basic Concepts 33 2.2.2 Advantages and Disadvantages 35 2.3 Particle Swarm Optimization algorithm (PSO) 36 2.3.1 Basic Concepts 36 2.3.2 The flowchart of PSO 38 2.3.3 Advantages and disadvantages 40 CHAPTER 3 EVOLUTIONARY GAUSSIAN PROCESS INFERENCE MODEL 41 3.1 Model Architecture 42 3.1.1 Data Input 43 3.1.2 The Gaussian Process and the Bayesian Inference 44 3.1.3 The optimization of Hyper-parameter 46 3.2 Model Application Process 50 3.3 Model Requirements and Limitations 53 3.4 Potential Application Areas 54 CHAPTER 4 EVOLUTIONARY GAUSSIAN PROCESS INFERENCE SYSTEM 54 4.1 Planning Phase 56 4.2 Building Phase 57 4.2.1 System Analysis 57 4.2.2 System Design 61 4.2.3 System Testing 65 4.3 Deploying Phase 65 CHAPTER 5 SYSTEM VALIDATION 69 5.1 Preparation for System Validation 71 5.1.1 Data Preprocessing 71 5.1.2 Performance Evaluation 72 5.1.3 Function Approximation 73 5.1.3.1 Problem Statement 73 5.1.3.2 Model Application 74 5.2 Modeling High Performance Concrete (HPC) 75 5.2.1 Problem Statement 75 5.2.2 Model Application 76 5.3 Wall Deformation Prediction in Deep Excavations 78 5.3.1 Problem Statement 78 5.3.2 Model Application 79 5.4 Strategic Control over Project Cash Flows 85 5.4.1 Problem Statement 85 5.4.2 Progress Control Response Strategies 90 5.4.3 Model Application 91 5.4.4 EGPIM Parameter Settings and Training Results 93 5.4.5 Financial and Progress Response Strategies 95 5.5 Prediction of Project Success 98 5.5.1 Problem Statement 98 5.5.2 Model Application 100 5.5.3 Results and conclusions 106 5.6 Discussions of EGPIS Implementation 111 CHAPTER 6 CONCLUSIONS AND RECOMMENDATIONS 112 6.1 Review the Research Purpose 112 6.2 Research Accomplishments 113 6.3 Conclusions 113 6.4 Research Contributions 115 6.5 Future Research Directions and Recommendation 116 REFERENCES 117 APPENDIX……….............126

    Anayat, S., Ali, A. & Ahmad, H. F. (2004) Using a probable weight based Bayesian approach for spam filtering. Multitopic Conference, 2004. Proceedings of INMIC 2004. 8th International.
    Azadnia, A. & Zahraie, B. (2010) Application of multi-objective particle swarm optimization in operation management of reservoirs with sedimentation problems. Providence, RI.
    Barclay, K. & Savage, J. (2004) Object-Oriented Design with UML and Java, Elsevier Science.
    Bernardo, J. M., Bayarri, J., Dawid, A. P., Berger, J. O., Heckerman, D., Smith, A. F. M. & West, M. (2003) Bayesian Statistics 7: Proceedings of the Seventh Valencia International Meeting, Oxford University Press, USA.
    Bernardo, J. M. & Smith, A. F. M. (1994) Bayesian Theory, John Wiley & Sons.
    Bonilla, E. V., Chai, K. M. A. & Williams, C. K. I. (2009) Multi-task Gaussian Process prediction. 21st Annual Conference on Neural Information Processing Systems, NIPS 2007, December 3, 2007 - December 6, 2007. Vancouver, BC, Canada, Curran Associates Inc.
    Boussabaine, A.H., Kaka, A.P. (1998) A neural networks approach for cost-flow forecasting. Construction Management and Economics 16 (4), 471-479
    Boussabaine, A.H., Elhag, T.M.S. (1999.) Applying fuzzy techniques to cash flow analysis. Construction Management and Economics 17 (6), 745 – 755
    Brahim-Belhouari, S. & Bermak, A. (2004) Gaussian process for nonstationary time series prediction. Computational Statistics and Data Analysis, 47, 705-712.
    Chamberlain, G. & Imbens, G. W. (2003) Nonparametric Applications of Bayesian Inference. Journal of Business & Economic Statistics, 21, 12-18.
    Chan, A. P. C., Scott, D. & Chan, A. P. L. (2004) Factors affecting the success of a construction project. Journal of Construction Engineering and Management, 130, 153-155.
    Cheng, M.-Y., Ko, C.-H. & Lin, Y.-C. (2008) Prediction of diaphragm wall deflection in deep excavations using evolutionary fuzzy neural inference model. Journal of the Chinese Institute of Civil and Hydraulic Engineering, 20, 175-182.
    Cheng, M.-Y., Tsai, H.-C. & Liu, C.-L. (2009) Artificial intelligence approaches to achieve strategic control over project cash flows. Automation in Construction, 18, 386-393.
    Cheng, M.-Y., Wu, Y.-W. & Wu, C.-F. (2010) Project success prediction using an evolutionary support vector machine inference model. Automation in Construction, 19, 302-307.
    Chi, S.Y., Chern, J.C. & Lin, C.C. (2001). Optimized back-analysis for tunneling-induced ground movement using equivalent ground loss model. Tunnelling and Underground Space Technology, 16 (3), 159-165.
    Chu, W. & Ghahramani, Z. (2005) Gaussian processes for ordinal regression. Journal of Machine Learning Research, 6.
    Clough, G. and Hansen, L.A. (1981). Clay anisotropy and braced wall behavior. Journal of the Geotechnical Engineering Division, 107 (7), 893-913.
    D'Souza, D. F. & Wills, A. C. (1999) Objects, components, and frameworks with UML: the catalysis approach, Addison-Wesley Longman Publishing Co., Inc.
    Der Kiureghian, A. (2008) Analysis of structural reliability under parameter uncertainties. Probabilistic Engineering Mechanics, 23, 351-358.
    Duy, N.-T. & Peters, J. (2008) Local Gaussian process regression for real-time model-based robot control. Intelligent Robots and Systems, 2008. IROS 2008. IEEE/RSJ International Conference on.
    Eberhart, R. & Kennedy, J. (1995) A new optimizer using particle swarm theory.
    Eberhart, R. C. & Shi, Y. (2000) Comparing inertia weights and constriction factors in particle swarm optimization. Evolutionary Computation, 2000. Proceedings of the 2000 Congress on.
    Ghosal, S. & van der Vaart, A. (2008) Theory of Nonparametric Bayesian Inference, Cambridge University Press.
    Gioda, G. & Sakurai, S. (1987), Back analysis procedures for the interpretation of field measurements in geomechanics. International Journal for Numerical and Analytical Methods in Geomechanics, 11 (6), 555-583.
    Gordon, Y., Litvak, A. E., Mendelson, S. & Pajor, A. (2007) Gaussian averages of interpolated bodies and applications to approximate reconstruction. J. Approx. Theory, 149, 59-73.
    Griffith, A. F., Gibson Jr, G. E., Hamilton, M. R., Tortora, A. L. & Wilson, C. T. (1999) Project success index for capital facility construction projects. Journal of Performance of Constructed Facilities, 13, 39-45.
    Harvey, C. R. & Zhou, G. (1990) Bayesian inference in asset pricing tests. Journal of Financial Economics, 26, 221-254.
    Hsu, C. W. & Lin, C. J. (2002) A simple decomposition method for support vector machines. Machine Learning, 46, 291-314.
    Hwang, S., L., Liu, Y. (2005) Proactive Project Control Using Productivity Data and Time Series Analysis, Computing in Civil Engineering 2005, In: Proceedings of the 2005 ASCE International Conference on Computing in Civil Engineering (pp. 12-15). Mexico.
    Ishigami, H., Fukuda, T., Shibata, T. & Arai, F. (1995) Structure optimization of fuzzy neural network by genetic algorithm. Fuzzy Sets and Systems, 71, 257-264.
    Jacobson, I. & Bylund, S. (2000) The Road to the Unified Software Development Process, Cambridge University Press.
    Jan, J. C., Hung, S.-L., Chi, S. Y. & Chern, J. C. (2002) Neural network forecast model in deep excavation. Journal of Computing in Civil Engineering, 16, 59-65.
    Kennedy, J. & Eberhart, R. (1995) Particle swarm optimization. Perth, Aust, IEEE.
    Khosravi, S. & Afshari, H. (2011) A Success Measurement Model for Construction Projects. 2011 International Conference on Financial Management and Economics Singapore, IACSIT Press.
    Ko, C.-H. & Cheng, M.-Y. (2003) Hybrid use of AI techniques in developing construction management tools. Automation in Construction, 12, 271-281.
    Khosrowshahi, F., Kaka, A. P. (2007) A Decision Support Model for Construction Cash Flow Management. Computer-Aided Civil and Infrastructure Engineering, 22 (7), 527-539
    Ko, C.-H. & Cheng, M.-Y. (2003) Hybrid use of AI techniques in developing construction management tools. Automation in Construction, 12, 271-281.
    Ko, C.-H. & Cheng, M.-Y. (2007) Dynamic prediction of project success using artificial intelligence. Journal of Construction Engineering and Management, 133, 316-324.
    Kocijan, J., Murray-Smith, R., Rasmussen, C. E. & Girard, A. (2004) Gaussian process model based predictive control. Proceedings of the 2004 American Control Conference (AAC), June 30, 2004 - July 2, 2004. Boston, MA, United states, Institute of Electrical and Electronics Engineers Inc.
    Korenaga, T., Hatanaka, T. & Uosaki, K. (2006) Improvement of Particle Swarm Optimization for High-Dimensional Space. SICE-ICASE, 2006. International Joint Conference.
    Larman, C. (1998) Applying UML and patterns: an introduction to object-oriented analysis and design, Prentice Hall PTR.
    Lawrence, N. D. & Moore, A. J. (2007) Hierarchical Gaussian process latent variable models. Proceedings of the 24th international conference on Machine learning. Corvalis, Oregon, ACM.
    Lee, P. M. (2012) Bayesian Statistics: An Introduction, Wiley.
    Li, T., Fu, Q. & Meng, F. (2010) Research on partial least-squares regression model based on particle swarm optimization and its application. Wuhan.
    Liu, C.L. (2006) Prediction Cash Flow for Construction Projects using Evolutionary Fuzzy Neural Inference Model, MS. Thesis, Department of Construction Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, (in Chinese)
    Long, M. (2001). “Database for retaining wall and ground movements due to deep excavations.” Journal of Geotechnical and Geoenvironmental Engineering, 127 (3), 203-224.
    Maes, M. A. (2007) Exchangeable condition states and Bayesian reliability updating. Kobe.
    Mahdavi Adeli, M., Deylami, A., Banazadeh, M. & Alinia, M. M. (2011) A Bayesian approach to construction of probabilistic seismic demand models for steel moment-resisting frames. Scientia Iranica, 18, 885-894.
    Markvardsen, A. J. (2004) Bayesian probability theory applied to the space group problem in powder diffraction. AIP Conference Proceedings, 735, 219-226.
    Matthias, S. (2004) Gaussian Processes for Machine Learning.
    Money, E. S., Reckhow, K. H. & Wiesner, M. R. (2012) The use of Bayesian networks for nanoparticle risk forecasting: Model formulation and baseline evaluation. Science of the Total Environment, 426, 436-445.
    Moreno, E., Bertolino, F. & Racugno, W. (2003) Bayesian Inference Under Partial Prior Information. Scandinavian Journal of Statistics, 30, 565-580.
    Ng, G. H. & Tiong, R. L. K. (2002) Model on cash flow forecating and risk analysis for contraction films. International Journal of Project Management 20(5), 351-363
    Nguyen-Tuong, D., Peters, J. & Seeger, M. (2009a) Local Gaussian process regression for real time online model learning and control. 22nd Annual Conference on Neural Information Processing Systems, NIPS 2008, December 8, 2008 - December 11, 2008. Vancouver, BC, Canada, Curran Associates Inc.
    Nguyen-Tuong, D., Seeger, M. & Peters, J. (2009b) Model Learning with Local Gaussian Process Regression. Advanced Robotics, 23, 2015-2034.
    Osoba, O., Mitaim, S. & Kosko, B. (2011) Bayesian Inference With Adaptive Fuzzy Priors and Likelihoods. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 41, 1183-1197.
    Ou, C.Y. & Tang, Y.G., (1994). Soil parameter determination for deep excavation analysis by optimization. Journal of the Chinese Institute of Engineers, Transactions of the Chinese Institute of Engineers, Series A/Chung-kuo Kung Ch'eng Hsuch K'an, 17 (5), 671-688. (In Chinese)
    Park, H.K., Han, S.H., Russell, J.S. (2005) Cash Flow Forecasting Model for General Contractors Using Moving Weights of Cost Categories. Journal of Management in Engineering 21 (4), 164-172
    Peng, C.-H., Yeh, I. C. & Lien, L.-C. (2009) Modeling strength of high-performance concrete using genetic operation trees with pruning techniques. Computers and Concrete, 6, 203-223.
    Perelman, L. & Ostfeld, A. (2012) Bayesian networks for estimating contaminant source and propagation in a water distribution system using cluster structure. Tucson, AZ.
    Poggio, T. & Girosi, F. (1990) Networks for approximation and learning. Proceedings of the IEEE, 78, 1481-1497.
    Powrie, W. & Li, E.S.F. (1991). Finite element analysis of an in situ wall propped at formation level. Geotechnique, 41 (4), 499-514.
    Ragg, T., Menzel, W., Baum, W. & Wigbers, M. (2002) Bayesian learning for sales rate prediction for thousands of retailers. Neurocomputing, 43, 127-144.
    Rasmussen, C. E. & Williams, C. K. I. (2006) Gaussian processes for machine learning, Cambridge; London, The MIT Press.
    Roy, A. F. V. (2009) Evolutionary Fuzzy Decision Model for Construction Management using Weighted Support Vector Machine. Department of Construction Engineering. National Taiwan University of Science and Technology.
    Russell, J.S., (1991) Contractor Failure: Analysis. Journal of Performance of Constructed Facilities, 5 (3), 163-180
    Russell, J. S., Jaselskis, E. J. & Lawrence, S. P. (1997) Continuous Assessment of Project Performance. Journal of Construction Engineering and Management, 123, 64-71.
    Sander, J., Heizmann, M., Goussev, I. & Beyerer, J. (2009) A local approach for focussed Bayesian fusion. 73450N-73450N.
    Sanvido, V., Grobler, F., Parfitt, K., Guvenis, M. & Coyle, M. (1992) Critical success factors for construction projects. Journal of Construction Engineering and Management, 118, 94-111.
    Schmidt, D. M., George, J. S. & Wood, C. C. (1998) Bayesian inference applied to the neural electromagnetic inverse problem. Proceedings of the 1998 32nd Asilomar Conference on Signals, Systems & Computers. Part 1 (of 2), November 1, 1998 - November 4, 1998. Pacific Grove, CA, USA, IEEE Comp Soc.
    Seeger, M. W., Kakade, S. M. & Foster, D. P. (2008) Information consistency of nonparametric Gaussian process methods. IEEE Transactions on Information Theory, 54, 2376-2382.
    Seng, K. N. K. (2008) Non-linear dynamics identification using Gaussian process prior models within a Bayesian context. Department of Electronic Engineering. National University of Ireland Maynooth.
    Su, G. S. & Xiao, Y. L. (2011) Gaussian process method for slope reliability analysis. Yantu Gongcheng Xuebao/Chinese Journal of Geotechnical Engineering, 33, 916-920.
    Vanhatalo, J. (2010) SPEEDING UP THE INFERENCE IN GAUSSIAN PROCESS MODELS. School of Science and Technology. Aalto University.
    Wang, T. & Hua, Z. (2008) Research on construction projects decision based on Life cycle engineering model. 2008 International Conference on Risk Management and Engineering Management, ICRMEM 2008, November 4, 2008 - November 6, 2008. Beijing, China, Inst. of Elec. and Elec. Eng. Computer Society.
    Warszawski, A. (1985) DECISION MODELS AND EXPERT SYSTEMS IN CONSTRUCTION MANAGEMENT. Building and Environment, 20, 201-210.
    Wooley, J. C., Computing, N. R. C. C. o. F. a. t. I. o., Biology & Lin, H. (2005) Catalyzing Inquiry at the Interface of Computing And Biology, National Academies Press.
    Whittle, A.J., Hashash, Y.M.A., and Whitman, R.V., (1993). Analysis of deep excavation in Boston. Journal of Geotechnical Engineering, 119 (1), 69-90.
    Yan, S., Shih, Y. L. & Lee, W. T. (2011a) A particle swarm optimization-based hybrid algorithm for minimum concave cost network flow problems. Journal of Global Optimization, 49, 539-559.
    Yan, Z., Su, G. & Yan, L. (2011b) Classification of surrounding rocks in tunnel based on Gaussian process machine learning. Lushan.
    Yau, N.-J. & Yang, J.-B. (1998) Case-based reasoning in construction management. Computer-Aided Civil and Infrastructure Engineering, 13, 143-150.
    Yeh, I. C. (2006) Generalization of strength versus water-cementitious ratio relationship to age. Cement and Concrete Research, 36, 1865-1873.
    Yeh, I. C. (2008) Prediction of workability of concrete using design of experiments for mixtures. Computers and Concrete, 5, 1-20.
    Yeh, I. C. & Lien, L.-C. (2009) Knowledge discovery of concrete material using Genetic Operation Trees. Expert Systems with Applications, 36, 5807-5812.
    Yekutieli, D. (2008) Adjusted Bayesian inference for selected parameters.
    Zachman, J. A. (1999) A framework for information systems architecture. IBM Syst. J., 38, 454-470.
    Zhang, W. & Liu, X. (2010) Gaussian Process meta-modeling and comparison of GP training methods. Logistics Systems and Intelligent Management, 2010 International Conference on.
    Zhao, F., Zhang, Q. & Yang, Y. (2006) A scheduling holon modeling method with petri net and its optimization with a novel PSO-GA algorithm. 2006 10th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2006, May 3, 2006 - May 5, 2006. Nanjing, China, Inst. of Elec. and Elec. Eng. Computer Society.

    QR CODE