簡易檢索 / 詳目顯示

回結果列表
研究生： 羅安和
Flores, Oswaldo Agenor Roa
論文名稱： 利用知識本體論解析營建作業特徴並建構專案排程風險控制資料來源之架構
An Ontology-based Construction Operations Feature Extraction Framework for Building Project Schedule Risk Monitoring Dataset
指導教授： 馮重偉
Feng, Chung-Wei
學位類別： 碩士
Master
系所名稱： 工學院 - 土木工程學系
Department of Civil Engineering
論文出版年： 2018
畢業學年度： 106
語文別： 英文
論文頁數： 110
外文關鍵詞： Schedule risk monitoring, Risk management, Feature extraction, Text understanding, Ontology
相關次數： 點閱：75  下載：4 
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

    • The Schedule Risk Monitoring is a challenge constantly present in the daily life of construction project; its complexity involves the understanding of the schedule risk factor, their causes and symptoms, and the mechanisms display to identify their occurrence and proper management. Recently, machine learning algorithms, potentiated by Deep Learning methods, have achieved unprecedented performance in many domains; especially, in Natural language processing; thus, it constitutes a strong tool for text understanding of raw data. Regarding the risk schedule monitoring’s raw data, there are not available datasets for feeding machine learning algorithms; thus, they need to be built from scratches. This paper presents the development of an ontology-based construction operations’ features extraction framework oriented to build those datasets from construction operational documents, and thus its final purpose is to contribute in the creation of schedule risk monitoring system based in a machine learning classifier model. This framework was built under the ontology development methodology and combines the explicit representation of the knowledge of previous work in the risk management domain, with the knowledge extracted from the construction operational documents. The results of the data collection contextualized the selected Contractor operations in alignment with previous studies; moreover, the validation of the framework consists of competency questions test and a case study, the test proofs the framework sufficient coverage of target knowledge, and the case study’s result proofs the ontology knowledge capacity to identify the features that evidence the risk factors’ trigger events and their impact on the project schedule.

    CHAPTER 1 INTRODUCTION 1 1.1 Overview of the Schedule Risk Monitoring 1 1.2 Motivation 2 1.3 Objectives and Limitations 3 1.3.1 Objectives: 3 1.3.2 Limitations 3 1.4 Procedure 4 1.5 Thesis Structure 5 CHAPTER 2 Problem Statement 6 2.1 Project Schedule Monitoring(PSM) 6 2.1.1 Project Schedule Monitoring (SM) Methodologies 7 2.1.2 Project Schedule Monitoring in the practice 8 2.2 Risk Management 9 2.2.1 Risk Planning 9 2.2.2 Risk Identification 9 2.2.3 Risk Assessment 10 2.2.4 Risk Response planning 10 2.2.5 Risk monitoring and control 11 2.2.6 Risk management gap in construction 11 2.2.7 Construction Project Schedule in Risk Management 12 2.3 Machine Learning 13 2.3.1 Machine Learning overview 13 2.3.2 Machine learning workflow 14 2.3.3 Application of Machine learning in Schedule Risk Management 15 2.3.4 Deep learning 17 2.4 Natural language processing (NLP) 18 2.4.1 Machine learning approaches to text understanding 19 2.5 SRM System Development Requirements 20 2.5.1 Schedule Risk Monitoring raw data 20 2.5.2 Preprocessing process 22 2.5.3 The Datasets for the SRM system 23 2.6 Problem statement summary 24 CHAPTER 3 Literature Review 30 3.1 Data science 30 3.1.1 Learning model variables (Features) 31 3.2 Ontology Models 32 3.2.1 Scope definition 35 3.2.2 Review of the domain authority 35 3.2.3 Extraction of the important concept 35 3.2.4 Organization of concepts into hierarchies 36 3.2.5 Implementation 36 3.2.6 Validation 37 3.2.7 Ontological models in Construction Risk Management 37 3.3 Literature Review Summary 38 CHAPTER 4 Methodology 41 4.1 Scope Definition 41 4.1.1 Domain Definition 41 4.1.2 Scope Delimitation 41 4.1.3 Competency Question 44 4.1.4 Ontology Specification 44 4.2 Review Domain Authorities 47 4.3 Data Collection 49 4.3.1 Expert’s interviews 49 4.3.2 Document Sampling Analysis 50 4.4 Ontology development 52 4.5 An ontology for schedule risk and COD features (SR&CODF) 53 4.5.1 Risk 53 4.5.2 Risk Factors 55 4.5.3 Observable Variables 56 4.5.4 Operational Document 58 4.5.5 Documents’ Section 58 4.5.6 Text Element 59 4.5.7 Feature 63 CHAPTER 5 Result and Validation 67 5.1 Results discussion 67 5.1.1 Construction operational data mapping 68 5.1.2 Project Performance Features 84 5.2 Framework Validation 86 5.2.1 Competency Question Test 86 5.2.2 Expert Interview 87 5.2.3 Schedule Risk and COD features study case analysis 88 CHAPTER 6 Conclusion and Future work 93 References 95 Appendices 98 Appendix A: Risk Hierarchy 98 Appendix B: Risk Factors Hierarchy 98 Appendix C: Observable Variables Hierarchy 100 Appendix D: Operational Documents Hierarchy 103 Appendix E: Document’s Sections Hierarchy 103 Appendix F: Text Element Hierarchy 104 Appendix G: COF Hierarchy 106

    Asadi, A., Alsubaey, M., &Makatsoris, C. (2015). A machine learning approach for predicting delays in construction logistics. International Journal of Advanced Logistics, 4(2), 115–130.
    [2] Banaitiene Nerija, B. A. (2012). Risk management in construction projects. Risk Management - Current Issues and Challenges, 429–448.
    [3] Carr, V., &Tah, J. H. . (2001). A fuzzy approach to construction project risk assessment and analysis: construction project risk management system. Advances in Engineering Software, 32(10–11), 847–857.
    [4] Cheng, W., Kasneci, G., Graepel, T., Stern, D., &Herbrich, R. (2011). Automated feature generation from structured knowledge. Proceedings of the 20th ACM International Conference on Information and Knowledge Management (CIKM 2011), 1395.
    [5] Conneau, A., Schwenk, H., Barrault, L., &Lecun, Y. (2016). Very Deep Convolutional Networks for Text Classification, (2001).
    [6] Cook, B., &Williams, P. (2004). Construction Planning Programming and Control.
    [7] Dong Chen; Hartman, F. T. (2000). A Neural Network Approach to Risk Assessment and Contingency Allocation. AACE International Transactions, RI7A.
    [8] Dubois, A., &Gadde, L. E. (2002). The construction industry as a loosely coupled system: Implications for productivity and innovation. Construction Management and Economics, 20(7), 621–631.
    [9] El-Diraby, T. E., &Zhang, J. (2006). A semantic framework to support corporate memory management in building construction. Automation in Construction, 15(4), 504–521.
    [10] Eshtehardian, E., &Khodaverdi, S. (2016). A Multiply Connected Belief Network approach for schedule risk analysis of metropolitan construction projects. Civil Engineering and Environmental Systems, 33(3), 227–246.
    [11] Eybpoosh, M., Dikmen, I., &Birgonul, M. T. (2011). Identification of risk paths in international construction projects using structural equation modeling. Journal of Construction …, 137(12), 1164–1175.
    [12] Falquet, G., Métral, C., Teller, J., &Tweed, C. (2011). Ontologies in Urban Development Projects (Vol. 1).
    [13] Fensel, D. (2004). Ontologies: A Silver Bullet for Knowledge Management and Electronic Commerce. Organizacija znanja (Vol. 7). https://doi.org/10.1007/978-3-662-09083-1
    [14] Fidan, G., Dikmen, I., Tanyer, A. M., &Birgonul, M. T. (2011). Ontology for Relating Risk and Vulnerability to Cost Overrun in International Projects. Journal of Computing in Civil Engineering, 25(4), 302–315.
    [15] Foucart, A., &Frenck-Mestre, C. (2015). Language processing. The Cambridge Handbook of Second Language Acquisition, 349(6245), 394–416.
    [16] Frome, A., Corrado, G. S., Shlens, J., Bengio, S., Dean, J., Ranzato, M. A., &Mikolov, T. (2013). DeViSE: A Deep Visual-Semantic Embedding Model, 1–9.
    [17] Ghahramani, Z. (2015). Probabilistic machine learning and artificial intelligence. Nature, 521(7553), 452–459.
    [18] Goldberg, Y. (2016). Neural Network Methods in Natural Language Processing.
    [19] Gray, C. F., &Larson, E. W. (2000a). Cross Reference of Project Management Body of Knowledge ( PMBOK ) Concepts to Text Topics.
    [20] Gray, C. F., &Larson, E. W. (2000b). Project Management The Managerial process (fifth edit).
    [21] Grüninger, M., &Fox, M. (1995). Methodology for the Design and Evaluation of Ontologies. In IJCAI’95, Workshop on Basic Ontological Issues in Knowledge Sharing, April 13, 1995.
    [22] Jin Wang Zhongyuan Wang, D. Z. J. Y. (2017). Combining Knowledge with Deep Convolutional Neural Networks for Short Text Classification. Ijcai, 2915–2921.
    [23] Kanter, J. M. (2015). Deep Feature Synthesis:Towards Automating Data Science Endeavors, 1–10.
    [24] Kim, H., Soibelman, L., &Grobler, F. (2008). Factor selection for delay analysis using Knowledge Discovery in Databases. Automation in Construction, 17(5), 550–560.
    [25] Kimble, C., Hildreth, P., &Wright, P. (2001). Communities of practice: going virtual, Knowledge Management and Business Model Inn. Communities of practice: going virtual, Knowledge Management and Business Model Inn. Idea Group Publishing, Hershey, USA.
    [26] Kothari, C., Kumar, R., &Uusitalo, O. (2014). Research Methodology. New Age International.
    [27] Lecun, Y., Bengio, Y., &Hinton, G. (2015). Deep learning.
    [28] Luu, V. T., Kim, S. Y., Tuan, N.Van, &Ogunlana, S. O. (2009). Quantifying schedule risk in construction projects using Bayesian belief networks. International Journal of Project Management, 27(1), 39–50.
    [29] Mikolov, T., Chen, K., Corrado, G., &Dean, J. (n.d.). 5021-Distributed-Representations-of-Words-and-Phrases-and-Their-Compositionality, 1–9.
    [30] Mikolov, T., Chen, K., Corrado, G., &Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space, 1–12.
    [31] Mizoguchi, R., Ikeda, M., &Sinitsa, K. (1997). Roles of Shared Ontology in AI-ED Research. Artifical Intelligence in Education, (3), 537–544. Retrieved from
    [32] Muhwezi, L., Acai, J., &Otim, G. (2014). An assessment of the factors causing delays on building construction projects in Uganda. Construction Engineering and Management, 3(1), 13–23.
    [33] Norvig, P. (1987). Inference in text understanding. AAAI, 561–565.
    [34] Noy, N. F., &McGuinness, D. L. (2001). Ontology Development 101: A Guide to Creating Your First Ontology. Stanford Knowledge Systems Laboratory, 25.
    [35] Olawale, Y., &Sun, M. (2015). Construction project control in the UK: Current practice, existing problems and recommendations for future improvement. International Journal of Project Management, 33(3), 623–637.
    [36] Owalabi, J. D., Amusan, L. M., Oloke, C. O., Olusanya, O., Tunji-Olayeni, P., OwolabiDele, …OmuhIganatious. (2014). Causes and effects of delay on project construction delivery time. International Journal of Education and Research, 2(4), 197–208.
    [37] Pandit, A., &Zhu, Y. (2007). An ontology-based approach to support decision-making for the design of ETO (Engineer-To-Order) products. Automation in Construction, 16(6), 759–770. Project Management Institute Inc. (2000). A guide to the project management body of knowledge (PMBOK® guide). Book.
    [38] Prot, U., Horridge, M., Knublauch, H., Rector, A., Stevens, R., Wroe, C., …Brandt, S. (2011). A Practical Guide To Building OWL Ontologies Using Protégè 4 and CO-ODE Tools Edition 1.3. Matrix, 0–107.
    [39] Provost, F., &Fawcett, T. (2013). Data Science for Business. What You Need to Know about Data Mining and Data-analytic Thinking.
    [40] Raschka, S. (2015). Python Machine Learning.
    [41] Schwarz, J., &Sandoval-Wong, J.A., Sánchez, P. . (2015). Implementation of artificial intelligence into risk management decision-making processes in construction projects, 361–362.
    [42] Science, E. D. (2017). Best practices for feature engineering.
    [43] Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van DenDriessche, G., …Hassabis, D. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587), 484–489.
    [44] Soderland, S. G. (2001). Building a Machine Learning Based Text Understanding System Information Extraction from Free Text. In Proc. IJCAI-2001 Workshop on Adaptive Text Extraction and Mining, 64–70.
    [45] Tah, J. H. ., &Carr, V. (2001). Towards a framework for project risk knowledge management in the construction supply chain. Advances in Engineering Software, 32(10–11), 835–846.
    [46] Taroun, A. (2014). Towards a better modelling and assessment of construction risk: Insights from a literature review. International Journal of Project Management, 32(1), 101–115.
    [47] Tserng, H. P., Yin, S. Y. L., Dzeng, R. J., Wou, B., Tsai, M. D., &Chen, W. Y. (2009). A study of ontology-based risk management framework of construction projects through project life cycle. Automation in Construction, 18(7), 994–1008.
    [48] Vanhoucke, M. (2013). Project Management with Dynamic Scheduling.
    [49] Vijayakumar, K., &Arun, C. (2017). Automated risk identification using NLP in cloud based development environments. Journal of Ambient Intelligence and Humanized Computing, 0(0), 0.
    [50] Yang, J., Park, M. W., Vela, P. A., &Golparvar-Fard, M. (2015). Construction performance monitoring via still images, time-lapse photos, and video streams: Now, tomorrow, and the future. Advanced Engineering Informatics, 29(2), 211–224.
    [51] Zhang, X., &LeCun, Y. (2015). Text Understanding from Scratch.
    [52] Zhong, B., &Li, Y. (2015). An Ontological and Semantic Approach for the Construction Risk Inferring and Application. Journal of Intelligent and Robotic Systems: Theory and Applications, 79(3–4), 449–463.
    [53] Zou, Y., Kiviniemi, A., &Jones, S. W. (2017). Retrieving similar cases for construction project risk management using Natural Language Processing techniques. Automation in Construction, 80(September 2016), 66–76.

    下載圖示 校內：立即公開
    校外：立即公開
    QR CODE