臺灣博碩士論文加值系統

In construction management, successful in cost control during construction stage is critical to the general contractor survival. The reason is that the bottom line of construction management is to ensure the project carried out within the planned budget. Cost overrun may lead to profit damage, occasionally even bring about project failure. To deal with such issue, this research utilizes Estimate at Completion (EAC) and Time-dependent Evolutionary Fuzzy Support Vector Machine (EFSIMT) to form the model (EAC-EFSIMT) uniquely for EAC prediction. In EAC-EFSIMT, the Support Vector Machines is utilized as a supervised learning instrument, in order to infer the causal relationship between multiple attributes in the input space and EAC as the single output in the output space. The fuzzy logic is used to emphasize the approximate reasoning. Moreover, to address the feature of time-dependent data, the inference model employs 3 types of time series functions (Linear, Quadratic, and Exponential) to weight training data points. The effect of each time series function on the model performance is investigated individually. This research work has proved that integration of time series function can meliorate the outcome of EAC prediction. Through the training, testing and results comparison process, the Exponential function has been identified as the preferable time series function for EAC problem. Moreover, the capability of EAC-EFSIMT in real-world situation is demonstrated. It is shown that newly proposed model is an effective replacement for previous methods in construction project cost control.

In construction management, successful in cost control during construction stage is critical to the general contractor survival. The reason is that the bottom line of construction management is to ensure the project carried out within the planned budget. Cost overrun may lead to profit damage, occasionally even bring about project failure. To deal with such issue, this research utilizes Estimate at Completion (EAC) and Time-dependent Evolutionary Fuzzy Support Vector Machine (EFSIMT) to form the model (EAC-EFSIMT) uniquely for EAC prediction. In EAC-EFSIMT, the Support Vector Machines is utilized as a supervised learning instrument, in order to infer the causal relationship between multiple attributes in the input space and EAC as the single output in the output space. The fuzzy logic is used to emphasize the approximate reasoning. Moreover, to address the feature of time-dependent data, the inference model employs 3 types of time series functions (Linear, Quadratic, and Exponential) to weight training data points. The effect of each time series function on the model performance is investigated individually. This research work has proved that integration of time series function can meliorate the outcome of EAC prediction. Through the training, testing and results comparison process, the Exponential function has been identified as the preferable time series function for EAC problem. Moreover, the capability of EAC-EFSIMT in real-world situation is demonstrated. It is shown that newly proposed model is an effective replacement for previous methods in construction project cost control.

ABSTRACT........I
ACKNOWLEDGEMENTS........III
TABLE OF CONTENTS.......IV
ABBREVIATIONS AND SYMBOLS.......VIII
LIST OF FIGURES.........XII
LIST OF TABLES..........XV
CHAPTER 1 INTRODUCTION..........1
1.1 Research Motivation.........1
1.2 Research Objectives.........5
1.3 Scope Definition and Basic Assumption.......6
1.4 Research Methodology........6
1.4.1 Problem Formulation.......7
1.4.2 EAC Forecasting Model.......7
1.4.3 EAC Prediction and Result Comparison.......7
1.4.4 Model Application.......8
1.5 Study Outline.......8
CHAPTER 2 LITERATURE REVIEW.......12
2.1 Estimate at Completion.......13
2.2 Time Series Forecasting Techniques.......17
2.3 Fuzzy Logic.......23
2.4 Weighted Support Vector Machine.......25
2.5 Fast Messy Genetic Algorithm.......29
CHAPTER 3 ESTIMATE AT COMPLETION USING TIME-DEPENDENT EVOLUTIONARY FUZZY SUPPORT VECTOR MACHINE INFERENCE MODEL FRAMEWORK.......32
3.1 Training Data.......32
3.2 Weighting Data Using Time Series Functions.......37
3.3 Fuzzification.......40
3.4 Weighted Support Vector Machine.......40
3.5 Defuzzification.......41
3.6 fmGA Parameter Searching.......42
3.7 Fitness Evaluation.......45
3.8 Termination Criteria....... 46
3.9 Optimal Prediction Model.......46
CHAPTER 4 ESTIMATE AT COMPLETION AND RESULT COMPARISON.......48
4.1 Training Process.......49
4.1.1 Training Process Using Linear Time Series Function....... 50
4.1.2 Training Process Using Quadratic Time Series Function.......54
4.1.3 Training Process Using Exponential Time Series Function.......57
4.1.4 Summary of Training Error.......60
4.2 Testing Process.......61
4.2.1 Training Process on Dataset L.......61
4.2.2 Training Process on Dataset M.......68
4.3 Result Comparison.......70
4.3.1 Comparison between EAC-EFSIMT and Traditional Methods....... 70
4.3.2 Comparison between EAC-EFSIMT and ESIM.......72
CHAPTER 5 APPLICATION OF ESTIMATE AT COMPLETION USING TIME- DEPENDENT EVOLUTIONARY FUZZY SUPPORT VECTOR MACHINE INFERENCE MODEL.......79
5.1 Utilization of EAC-EFSIMT in Construction Project.......79
5.1.1 Application of EAC for Various Stages in Construction Project.......79
5.1.2 Project Cost Influencing Indices Analysis.......80
5.1.3 Project Cost Diagram Analysis.......84
5.2 Application of EAC-EFSIMT for Actual Project.......84
CHAPTER 6 CONCLUSION.......90
6.1 Review of Research Purpose.......90
6.2 Summary.......91
6.3 Conclusion.......92
6.4 Future Recommendations.......93
REFERENCE.......95
APPENDIX.......A-1

Abba, 1997. Earned value management: reconciling government and commercial practices. Program Manager.
Bao, Y.K. , Liy, Z.T., Guo, L., & Wang, W. (2005). Forecasting Composite Index by Fuzzy Support Vector Machines Regression. In: Proceedings of Fourth International Conference on Machine Learning and Cybernetic (pp. 3535-3540). Guangzhou.
Bilongo, R., Carbone, R. 2003 Adaptive model-based seasonal adjustment of time series : An Empirical Comparison with XII-ARIMA and SIGEX. International Journal of Forecasting Volume 1, Issue 2, 1985, Pages 165-177
Bojadziev, G., Bojadziev, M., 2007. Fuzzy logic for business, finance, and management, second ed. World Scientific, Singapore.
Bolles, D., Fahrenkrog, S., 2004. A Guide to the Project Management Body of Knowledge (PMBOK Guide), 3rd Ed, Project Management Institute, Newtown Square.
Chang, C. C., Lin., C.J., 2001. LIBSVM : a library for support vector machines, Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
Chakraborty, K., Mehrotra, K., Mohan, K., Ranka, S., 1992. Forecasting the behavior of multivariate time series using neural networks. Neural Networks Volume 5, Issue 6, November-December 1992, Pages 961-970
Chen , T. L., 2008. Estimate at Completion 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).
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, 619-629
Cheng, M.Y., Roy, A.F.V., 2010. Evolutionary fuzzy decision model for cash flow prediction using time-dependent support vector machines, International Journal of Project Management, article in Press.
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
Cheng, M.Y., Wu, Y.W., 2009. Evolutionary support vector machine inference system for construction management, Automation in Construction 18 (5), 597-604
Chou, J.S., Chen, H.M., Hou, C.C., Lin, C.W., 2010. Visualized EVM system for assessing project performance, Automation in Construction 19, 596–607.
Christensen, D.S., 1993. Determining an accurate Estimate at Completion, National Contract Management Journal 25, 7-25
Christensen, D.S., Antolini, R.C., McKinney, J.W., 1995. A review of estimate at completion research. Journal of Cost Analysis and Management, 41-62.
Deb, K., Goldberg, D.E., 1991. mGA in C: A Messy Genetic Algorithm in C. IlliGAL Technical Report 91008, Department of General Engineering, University of Illinois at Urbana-Champaign, Urbana, Illinois.
Fan, H., Ramamohanarao, K., 2005. A weighting scheme based on emerging patterns for weighted support vector machines. In: Proceeding IEEE International Conference on Granular Computing, 2 (2), 435- 440
Feng, C. W., Wu, H.T., 2006. Integrated fmGA and CYCLONE to Optimize Schedule of Dispatching RMC Trucks. Automation in Construction 15,186-199
Gen, M., Cheng, R., 1997. Genetic Algorithms and Engineering Design. John Wiley & Sons, New York.
Hussain, A., Knowles, A., Lisboa, P., El-Deredy, Al-Jumeily, 2008, Financial time series prediction using polynomial pipelined neural networks. Expert Systems with Applications: An International Journal Volume 35, Issue 3 (October 2008), 1186-1199
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
Jagdisha Hiray, 2008. Time-series methods of forecasting. All about Business and management.
Kharbanda, O. P., 1980. Project cost control in action. Gower Publisher.
Khemchandani R., Jayadeva, Chandra S., 2009. Regularized least square fuzzy support vector regression for financial time series forecasting. Expert System with Applications 36 (1), 132-138
Khosrowshahi, Farzad, Alani, Amir (2003). A model for smoothing time-series data in construction. Construction Management and Economics, 21: 5, 483 — 494
Klir, G. J., Yuan, B., 1995. Fuzzy sets and fuzzy logic: Theory and applications. Prentice Hall PTR, Upper Saddle River, New Jersey.
Knight K., Fayek A.R., 2002. Use of Fuzzy Logic for Predicting Design Cost Overruns on Building Projects. Journal of Construction Engineering and Management, 128 (6), 503-512
Ko, C. H., 2002. Evolutionary Fuzzy Neural Inference Model (EFNIM) for Decision-Making in Construction Management, Ph.D. Thesis, Department of Construction Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan.
Kumar V. S. S., Reddy, G.C.S., 2005. Fuzzy logic approach to forecast duration in construction projects. In: Proceeding Construction Research Congress: Boarding Perspective, American Society of Civil Engineers.
Li J., Moselhi O., Alkass S., 2006. Forecasting Project Status by Using Fuzzy Logic. Journal of Construction Engineering and Management 132 (11), 1193–1202.
Lin, C.F., Wang, S.D., 2002. Fuzzy Support Vector Machines. IEEE Transactions on Neural Networks 13 (2), 464-471
Martinez, C., Castillo, O., Montiel, O., 2008. Comparison between Ant Colony and Genetic Algorithms for Fuzzy System Optimization. Soft Computing for Hybrid Intel. Systems. Springer-Verlag, Berlin Heidelberg. pp. 71-86.
Muller, K., Smola, J., Ratsch, G., Scholkopf, B., Kolhmorgen, J., Vapnik,. V., 1997. Predicting time series with support vector machine. Proceedings of ICANN 97, Springer LNCS, p. 999-1004.
Nicholas I. Sapankevych et al., 2009. Time Series Prediction Using Support Vector Machine A Survey, Computational Intelligence Magazine. Vol 4, No 2, p. 24-38.
Schlkopf, B., Smola, A.J., 2002. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond (Adaptive Computation and Machine Learning), Cambridge-Massachusetts: MIT-Press.
Smola, A.J., Schölkopf, B., 2004. A tutorial on support vector regression, Statistics and Computing 14, 199-222
Tah, J.H.M., Carr V., 2000. A proposal for construction project risk assessment using fuzzy logic, Construction Management and Economics 18 (4), 491–500
Vandevoorde, S., Vanhoucke, M., 2005. A comparison of different project duration forecasting methods using earned value metrics, Vlerick Leuven Gent Working Paper Series 2005/16.
Zeng, J, An, M., Smith, N.J., 2007. Application of a fuzzy based decision making methodology to construction project risk assessment. International Journal of Project Management 25, 589–600