簡易檢索 / 詳目顯示

回結果列表
研究生： DORCAS KORIR
DORCAS KORIR
論文名稱： NOVEL DEEP LEARNING APPROACH FOR SCHEDULE ESTIMATE TO COMPLETION IN CONSTRUCTION PROJECT USING NN-LSTM
NOVEL DEEP LEARNING APPROACH FOR SCHEDULE ESTIMATE TO COMPLETION IN CONSTRUCTION PROJECT USING NN-LSTM
指導教授： 鄭明淵
Min-Yuan Cheng
口試委員: 陳鴻銘
Huang-Ming Chen
吳育偉
Yu-Wei Wu
學位類別： 碩士
Master
系所名稱： 工程學院 - 營建工程系
Department of Civil and Construction Engineering
論文出版年： 2017
畢業學年度： 106
語文別： 英文
論文頁數： 96
中文關鍵詞： Schedule estimate 、inference model 、independent and dependent factors 、neural network- long short-term memory (NN-LSTM)
外文關鍵詞： Schedule estimate, inference model, independent and dependent factors, neural network- long short-term memory (NN-LSTM)
相關次數： 點閱：242  下載：3 
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

    • Estimation of construction project duration is extremely hard during various construction phases due to complexity, uncertainty and limited information available during a project course. Construction managers estimate construction duration according to their previous experience based on budget planning, a method that can be inaccurate and costly. This study developed a novel inference model that accurately estimate project duration factoring in the dependent and independent factors that significantly influence project duration and captures uncertainty involved in construction field. Duration influencing factors were selected based on the previous studies review, and later categorized into time dependent and independent factors. Subsequently, two artificial intelligence approaches were fused, namely neural networks (NN) and the long short-term memory (LSTM) to create a novel Neural Network - Long Short-Term Memory (NN-LSTM) model. The NN-LSTM was applied to estimate schedule to completion (ESTC) for historical cases where NN captured the impact of independent factors in project duration as LSTM captured the long temporal dependency for sequential inputs. After the analysis, 14 influencing factors and 11 historical cases were selected to establish the case database used for learning purposes. 10-cross validation was used to partition the training and testing dataset. The learning results indicated good performance with MAPE of 4% and mean absolute error of 2% proving the model more reliable than the currently prevailing formula. Moreover, upon comparison with other methods, NN-LSTM proved to be superior to SVM, LSSVM, BPNN, ESIM, ELSIM, SOS-LSSVM and the earned value method (EVM). The model qualifies to replace the subjective estimation based on experience alone. It provides project managers with reliable schedule estimates that facilitates proper planning and help in monitoring project’s performance in terms of time, prompting timely actions in case of foreseen delay and making of informed decisions.

    Estimation of construction project duration is extremely hard during various construction phases due to complexity, uncertainty and limited information available during a project course. Construction managers estimate construction duration according to their previous experience based on budget planning, a method that can be inaccurate and costly. This study developed a novel inference model that accurately estimate project duration factoring in the dependent and independent factors that significantly influence project duration and captures uncertainty involved in construction field. Duration influencing factors were selected based on the previous studies review, and later categorized into time dependent and independent factors. Subsequently, two artificial intelligence approaches were fused, namely neural networks (NN) and the long short-term memory (LSTM) to create a novel Neural Network - Long Short-Term Memory (NN-LSTM) model. The NN-LSTM was applied to estimate schedule to completion (ESTC) for historical cases where NN captured the impact of independent factors in project duration as LSTM captured the long temporal dependency for sequential inputs. After the analysis, 14 influencing factors and 11 historical cases were selected to establish the case database used for learning purposes. 10-cross validation was used to partition the training and testing dataset. The learning results indicated good performance with MAPE of 4% and mean absolute error of 2% proving the model more reliable than the currently prevailing formula. Moreover, upon comparison with other methods, NN-LSTM proved to be superior to SVM, LSSVM, BPNN, ESIM, ELSIM, SOS-LSSVM and the earned value method (EVM). The model qualifies to replace the subjective estimation based on experience alone. It provides project managers with reliable schedule estimates that facilitates proper planning and help in monitoring project’s performance in terms of time, prompting timely actions in case of foreseen delay and making of informed decisions.

    ABSTRACT i ACKNOWLEDGEMENT iii TABLE OF CONTENTS iv LIST OF TABLES vi LIST OF FIGURES vii LIST OF ABBREVIATIONS viii LIST OF SYMBOLS x CHAPTER 1: INTRODUCTION 1 1.1 Research motivation 1 1.2 Research objectives 4 1.3 Scope Definition and Basic Assumption 5 1.4 Research Methodology 6 1.4.1 Introduction 9 1.4.2 Literature Review 10 1.4.3 Model Construction 10 1.4.4 Model Validation 10 1.4.5 Model Application 11 1.4.6 Conclusion and recommendation 11 1.5 Study Outline 11 CHAPTER 2: LITERATURE REVIEW 13 2.1 Delay in construction projects 13 2.2 Methodology 16 2.2.1 Earned Value Management (EVM) 16 2.2.2 Support Vector Machine (SVM) 20 2.2.3 Least Squares Support Vector Machine (LSSVM) 22 2.2.4 Back Propagation Neural Networks (BPNN) 24 2.2.5 Evolutionary Support Vector Machine Inference Model (ESIM) 25 2.2.6 Evolutionary Least Support Vector Machine (ELSIM) 26 2.2.7 The Symbiotic Organisms Search-Least Squares Support Vector Machine (SOS-LSSVM) 27 2.2.8 Neural Networks 28 2.2.9 Long Short-Term Memory 29 CHAPTER 3: ESTIMATE SCHEDULE TO COMPLETION INFERENCE MODEL- NN-LSTM 33 3.1 Model architecture 33 3.2 Model Adaptation Process 35 CHAPTER 4: PREDICTION OF ESTIMATE SCHEDULE TO COMPLETION 43 4.1 Selection of the duration factors 43 4.2 Data collection 47 4.3 Data processing 50 4.4 Cross Validation 52 4.5 Model training 53 4.6 Model testing 54 4.7 Result comparison 56 4.7.1 Earned Value Management 56 4.7.2 Other AI methods 58 CHAPTER 5: MODEL APPLICATION 62 5.1 Case study 62 5.2 Data preparation 64 5.3 ESTC prediction 66 5.4 Calculation of ESAC 68 5.5 Decision-making 70 CHAPTER 6: CONCLUSION AND RECOMMENDATION 72 6.1 Research objectives review summary 72 6.2 Conclusion 73 6.3 Recommendations 75 REFERENCES 76

    Alex Graves, Abdel-rahman Mohamed, & Hinton, G. (2013). SPEECH RECOGNITION WITH DEEP RECURRENT NEURAL NETWORKS. in Proc. ICASSP, 6885– 6889.
    Anbari, F. (2003). Earned value project management method and extensions. Project Management Journal, 34(4), 12-23.
    Assaf, S. A., & Al-Hejji, S. (2006). Causes of delay in large construction projects. International Journal of Project Management, 24(4), 349-357. doi:http://dx.doi.org/10.1016/j.ijproman.2005.11.010
    Aziz, R. F., & Abdel-Hakam, A. A. (2016). Exploring delay causes of road construction projects in Egypt. Alexandria Engineering Journal, 55(2), 1515-1539. doi:https://doi.org/10.1016/j.aej.2016.03.006
    Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning Long-Term Dependencies with Gradient Descent is Difficult. IEEE Transactions on neural networks, 5(2).
    Boussabaine, A. H., & Kaka, A. P. (1998). A neural networks approach for cost flow forecasting. Construction Management and Economics, 16(4), 471-479. doi:10.1080/014461998372240
    Chan, D. W. M., & Kumaraswamy, M. M. (1996). An evaluation of construction time performance in the building industry. Building and Environment, 31(6), 569-578. doi:http://dx.doi.org/10.1016/0360-1323(96)00031-5
    Chan, W.-m. (1998). “Modelling construction duration for public housing projects in Hong Kong”. Doctoral dissertation

    Chen, G. (2016). A Gentle Tutorial of Recurrent Neural Network with Error Backpropagation.
    Cheng, M.-Y., & Cao, M.-T. (2014). Accurately predicting building energy performance using evolutionary multivariate adaptive regression splines. Applied Soft Computing, 22, 178-188. doi:http://dx.doi.org/10.1016/j.asoc.2014.05.015
    Cheng, M.-Y., & Hoang, N.-D. (2014). Risk Score Inference for Bridge Maintenance Project Using Evolutionary Fuzzy Least Squares Support Vector Machine. Journal of Computing in Civil Engineering, 28(3), 04014003. doi:10.1061/(asce)cp.1943-5487.0000275
    Cheng, M.-Y., Hoang, N.-D., & Wu, Y.-W. (2015). Cash flow prediction for construction project using a novel adaptive time-dependent least squares support vector machine inference model. Journal of Civil Engineering and Management, 21(6), 679-688. doi:10.3846/13923730.2014.893906
    Cheng, M.-Y., K., W. D., Prayogo, D., & Roy, A. F. V. (2015). "Predicting productivity loss caused by change orders using the evolutionary fuzzy support vector machine inference model". Journal of Civil Engineering and Management, 21, 881-892.
    Cheng, M.-Y., Peng, H.-S., Wu, Y.-W., & Chen, T.-L. (2010). Estimate at Completion for construction projects using Evolutionary Support Vector Machine Inference Model. Automation in Construction, 19(5), 619-629. doi:https://doi.org/10.1016/j.autcon.2010.02.008
    Cheng, M.-Y., & Prayogo, D. (2014). Symbiotic Organisms Search: A new metaheuristic optimization algorithm. Computers & Structures, 139, 98-112. doi:http://dx.doi.org/10.1016/j.compstruc.2014.03.007
    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(4), 386-393. doi:http://dx.doi.org/10.1016/j.autcon.2008.10.005
    Cheng, M.-Y., & Wu, Y.-W. (2009). Evolutionary support vector machine inference system for construction management. Automation in Construction, 18(5), 597-604. doi:http://doi.org/10.1016/j.autcon.2008.12.002
    Chou, J.-S., & Thedja, J. P. P. (2016). Metaheuristic optimization within machine learning-based classification system for early warnings related to geotechnical problems. Automation in Construction, 68, 65-80. doi:http://dx.doi.org/10.1016/j.autcon.2016.03.015
    Cortes, C., & Vapnik, V. N. (1995). Support Vector Networks (Vol. 20).
    Daniel Castro-Lacouture, Gürsel A. Süer, Julian Gonzalez-Joaqui, & Yates, J. K. (2009). Construction Project Scheduling with Time, Cost,
    and Material Restrictions Using Fuzzy Mathematical
    Models and Critical Path Method. Journal of Construction Engineering and Management, 135(10). doi:10.1061//ASCE/0733-9364/2009/135:10/1096
    Doloi, H., Sawhney, A., Iyer, K. C., & Rentala, S. (2012). Analysing factors affecting delays in Indian construction projects. International Journal of Project Management, 30(4), 479-489. doi:http://dx.doi.org/10.1016/j.ijproman.2011.10.004
    Henderson, K. (2003). Earned Schedule: A Breakthrough Extension to Earned Value Management. The Measurable News, 13-7(summer).
    Huawang, S., & Wanqing, L. (2009). “The Grey Relational Analysis on Building Construction Duration Cases”. International Conference on Future BioMedical Information Engineering, 358-361.
    Isaac Mensah, Gabriel Nani, & Adjei-Kumi, T. (2016). Development of a Model for Estimating the Duration of Bridge Construction Projects in Ghana. International Journal of Construction Engineering and Management, 5(2), 55-66. doi:10.5923/j.ijcem.20160502.03
    Jacob, D. S., & Kane, M. (2004). Forecasting schedule completion using earned value metrics revisited (Vol. 1).
    Jha, K., & Chockalingam, C. T. (2011). Prediction of schedule performance of Indian construction projects using an artificial neural network (Vol. 29).
    Jian, K. Q. (2004). "Using fuzzy neural network and fast messy genetic algorithms to forecast project duration". Master’s thesis. National Cheng Kung University.
    Jyh-Bin Yang, & Wei, P.-R. (2010). Causes of Delay in the Planning and Design Phases for Construction Projects Journal of Architectural Engineering, 6(2). doi:10.1061//ASCE/1076-0431/2010/16:2/80
    Kaming, P. F., Olomolaiye, P. O., Holt, G. D., & Harris, F. C. (2010). Factors influencing construction time and cost overruns on high-rise projects in Indonesia. Construction Management and Economics, 15(1), 83-94. doi:10.1080/014461997373132
    Kim, E., Wells, W. G., & Duffey, M. R. (2003). A model for effective implementation of Earned Value Management methodology. International Journal of Project Management, 21(5), 375-382. doi:10.1016/s0263-7863(02)00049-2
    Längkvist, M., Karlsson, L., & Loutfi, A. (2014). A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognition Letters, 42(Supplement C), 11-24. doi:https://doi.org/10.1016/j.patrec.2014.01.008
    Lin, M.-C., Tserng, H. P., Ho, S.-P., & Young, D.-L. (2011). Developing a Construction-Duration Model Based on a Historical Dataset for Building Project. Journal of Civil Engineering and Management, 17(4), 529-539. doi:10.3846/13923730.2011.625641
    Lipke, W., Zwikael, O., Henderson, K., & Anbari, F. (2009). Prediction of project outcome: The application of statistical methods to earned value management and earned schedule performance indexes. International Journal of Project Management, 27(4), 400-407. doi:http://dx.doi.org/10.1016/j.ijproman.2008.02.009
    López-Martín, C., & Abran, A. (2015). Neural networks for predicting the duration of new software projects. Journal of Systems and Software, 101(Supplement C), 127-135. doi:https://doi.org/10.1016/j.jss.2014.12.002
    Ma, X., Tao, Z., Wang, Y., Yu, H., & Wang, Y. (2015). Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transportation Research Part C: Emerging Technologies, 54, 187-197. doi:http://dx.doi.org/10.1016/j.trc.2015.03.014
    Maravas, A., & Pantouvakis, J.-P. (2012). Project cash flow analysis in the presence of uncertainty in activity duration and cost. International Journal of Project Management, 30(3), 374-384. doi:http://dx.doi.org/10.1016/j.ijproman.2011.08.005
    Marcus Liwicki, Alex Graves, Horst Bunke, & Schmidhuber, J. u. (2007). “A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks". in Proc. ICDAR, 367–371. .
    Marzouk, M. M., & El-Rasas, T. I. (2014). Analyzing delay causes in Egyptian construction projects. Journal of Advanced Research, 5(1), 49-55. doi:http://dx.doi.org/10.1016/j.jare.2012.11.005
    Nkado, R. N. (1995). ”Construction time-influencing factors: the contractor’s perspective”. Construction Management and Economics, 13(1), 81-89.
    Petroutsatou, K., Georgopoulos, E., Lambropoulos, S., & Pantouvakis, J. P. (2012). Early Cost Estimating of Road Tunnel Construction Using Neural Networks. Journal of Construction Engineering and Management, 138(6), 679-687. doi:10.1061/(asce)co.1943-7862.0000479
    Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning Representations by Back-Propagating Errors. Nature, 323, 533-536.
    Sapankevych, N., & Sankar, R. (2009). Time Series Prediction Using Support Vector Machines: A Survey. IEEE Computational Intelligence Magazine, 4(2), 24-38. doi:10.1109/mci.2009.932254
    Sepp Hochreiter, & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.
    SMOLA, A. J., & SCHOLKOPF, B. (2004). A tutorial on support vector regression. Statistics and Computing, 199–222.
    Sou-Sen, L., & Hsien-Chuang, L. (2004). Neural-network-based regression model of ground surface settlement induced by deep excavation. Automation in Construction, 13(3), 279-289. doi:http://dx.doi.org/10.1016/S0926-5805(03)00018-9
    Suykens J.A.K., & J., V. (1999). "Least Squares Support Vector Machine Classifiers". Neural Processing Letters, 9, 293-300.
    Sweis, G., Sweis, R., Abu Hammad, A., & Shboul, A. (2008). Delays in construction projects: The case of Jordan. International Journal of Project Management, 26(6), 665-674. doi:http://dx.doi.org/10.1016/j.ijproman.2007.09.009
    Tinoco, J., Gomes Correia, A., & Cortez, P. (2014). Support vector machines applied to uniaxial compressive strength prediction of jet grouting columns. Computers and Geotechnics, 55, 132-140. doi:10.1016/j.compgeo.2013.08.010
    Tu, J. V. (1996). Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. Journal of Clinical Epidemiology, 49(11), 1225-1231. doi:https://doi.org/10.1016/S0895-4356(96)00002-9
    Vandevoorde, S., & Vanhoucke, M. (2006). A comparison of different project duration forecasting methods using earned value metrics. International Journal of Project Management, 24(4), 289-302. doi:10.1016/j.ijproman.2005.10.004
    Vapnik, V., Golowich, S. E., & Smola, A. J. (1997). Support vector method for function approximation, regression estimation and signal processing. Paper presented at the Advances in neural information processing systems.
    Venkatesh, K., Ravi, V., Prinzie, A., & Poel, D. V. d. (2014). Cash demand forecasting in ATMs by clustering and neural networks. European Journal of Operational Research, 232(2), 383-392. doi:http://dx.doi.org/10.1016/j.ejor.2013.07.027

    QR CODE