跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 李桔萍
Ragil Purnamasari
論文名稱： 運用SVR智慧型分類器改善工程粗估之研究
Improving Accuracy of Preliminary Cost Estimation Using Support Vector Regression
指導教授： 陳介豪
Jieh-Haur Chen
口試委員:
學位類別： 碩士
Master
系所名稱： 工學院 - 土木系營建管理碩士班
Master's Program in Construction Management, Department of Civil Engineering
論文出版年： 2016
畢業學年度： 104
語文別： 英文
論文頁數： 97
中文關鍵詞： 成本估算 、分類 、支撐向量回歸 、建築工程專案
外文關鍵詞： Cost Estimation, Classification, Support Vector Regression (SVR), Building Construction Project
相關次數： 點閱：10  下載：0 
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

    • 初步的工程估價在工程專案中是ㄧ個重要的階段。在這個階段，承包商與業主要能評估這個專案是否可行。在印度尼西亞，一個典型的建築專案得花上數周來做初步的工程估價，且誤差值的範圍會從-12.97% 到+26.80%。以往的研究指出，有74%的成本超支是由過低的工程估價造成的。因此，本研究的目的在於：1)確立在印度尼西亞的估價因子2)發展一個支撐向量回歸模型，試圖去改善精準度以及減少初步工程估價的工作時間。文獻回顧辨別出了14個影響世界各地所有的建築專案的估價因子。考慮到這些因素做為模型之基礎，資料隨機取樣，蒐集104項包含有效資訊的印尼建築案例供模型使用。在資料修整、分析以及正規劃後，建立出伴隨徑向基函數核(radial basis function kernel)的SRV模型。以5折交叉驗證來預估以及執行模型，並產出平均95.79%正確率之工程專案初步預估。從SVR模型比原始資料提升了8.71%準確率。過往人工計算初期成本需要以周為單位計算，現行則由模型運算以秒為單位處理，由此可看出對於縮減時間亦是相當重要的。由上述可得知，SRV模型在正確率與省時都是相當優異的。

    Preliminary cost estimation is an important stage for construction projects. During the stage, any contractor and owner is able to determine whether his/her project is feasible. A typical preliminary cost estimation for a building construction project in Indonesia may take weeks and have an error rate varying from -12.97% to +26.80%. Previous studies also concluded that 74% of cost overruns are caused due to underestimation. The research objectives, therefore, are (1) to determine factors that influence cost estimation in Indonesia and (2) to develop a Support Vector Regression (SVR) model in an attempt to improve accuracy and to reduce workhours for preliminary cost estimation. Literature review identified 14 factors that influence cost estimation the most for all types of construction projects around the world. Considering these factors as the model bases, data collection randomly gathered 104 building cases in Indonesia containing valid information for the proposed model. The SVR model with the radial basis function kernel was established after data trimming, analysis, and normalization. The model then was evaluated and implemented using the 5-folds cross validation and yielded the average accuracy at 95.79% for preliminary cost estimation of building construction projects. The accuracy has been improved 8.71% between the original data and the results from the SVR model. Time spent for conducting such a preliminary cost estimation has been significantly reduced from weeks by human estimators to less than one second by the model. The SVR model is efficient in both accuracy and time-saving.

    TABLE OF CONTENT ABSTRACT i 摘要 ii ACKNOWLEDGEMENT iii TABLE OF CONTENT iv LIST OF FIGURES vi LIST OF TABLES vii CHAPTER I: INTRODUCTION 1 1.1 Research Background 1 1.2 Research Objectives 3 1.3 Research Scope and Limitations 4 1.4 Research Flowchart 4 1.5 Thesis Organization 5 CHAPTER II: LITERATURE REVIEW 6 2.1 Cost Estimation 6 2.1.1 Overview of Cost Estimation 6 2.1.2 Accuracy of Cost Estimation 11 2.1.3 Previous Study of Cost Estimation 13 2.2 Factors Affecting the Cost Estimate 13 2.3 Factor Affecting Cost Estimate in Indonesia 14 2.4 Factor Affecting Cost Estimate Considered in Other Countries 14 2.4.1 Factors for Consideration in Predicting the Accuracy of Project Cost Estimation 16 2.4.2 Previous Studies of Factors Affecting the Cost Estimate 17 2.5 Support Vector Machine 18 2.5.1 Overview of Support Vector Machine 18 2.5.2 Support Vector Machine Classification 19 2.5.3 Support Vector Machine Regression 20 2.5.4 Kernel 23 2.5.5 Previous Study of SVM Regression 24 2.6 WEKA 24 CHAPTER III: DATA COLLECTION AND ANALYSIS 27 3.1 Research Framework 27 3.2 Data Analysis 29 3.2.1 Overview Data 29 3.2.2 Project Characteristic 30 3.2.3 Complexity Project 32 3.2.4 Location Characteristic 33 3.2.5 Project Specification 35 3.2.6 Contract Information 37 3.3 Factor Analysis 38 CHAPTER IV: MODEL DEVELOPMENT 41 4.1 Model Development 41 4.1.1 Support Vector Machine Regression Model 41 4.1.2 Arranging the datasets 42 4.1.3 Setting the parameters 45 4.1.4 Examining model outcomes 46 4.1.5 Recurrence process for potential results 46 4.1.6 WEKA 46 4.2 Model Implementation and Evaluation 47 4.3 Prediction Result and Discussions 57 CHAPTER V: CONCLUSION 60 5.1 Conclusion 60 5.2 Research Recommendation 61 REFERENCES 62 APPENDIX A: DATA REQUEST PERMISSION LETTER 65 APPENDIX B: DATA 66 APPENDIX C: PARAMETER RESULT 86 APPENDIX D: MODEL RESULT 93

    REFERENCES

    1. Barzandeh, M., Accuracy of estimating techniques for predicting residential construction costs–a case study of an Auckland residential construction company. 2011.
    2. Transportation, W.S.D.o., Cost Estimating Manual for Projects. 2015.
    3. Shah, R.S., Support Vector Machines for Classification and Regression. 2007, McGill University.
    4. Santosa, B., Tutorial Support Vector Machine. Teknik Idustri, ITS.[Online]. Tersedia: http://www. google. co. id/url, 2010.
    5. Lam, K.C., E. Palaneeswaran, and C.-y. Yu, A support vector machine model for contractor prequalification. Automation in Construction, 2009. 18(3): p. 321-329.
    6. Parrella, F., Online support vector regression. Master's Thesis, Department of Information Science, University of Genoa, Italy, 2007.
    7. Yasin, H., A. Prahutama, and T.W. Utami, PREDIKSI HARGA SAHAM MENGGUNAKAN SUPPORT VECTOR REGRESSION DENGAN ALGORITMA GRID SEARCH. MEDIA STATISTIKA, 2014. 7(1): p. 29-35.
    8. An, S.-H., Park, U.Y., Kang, K.I., Cho, M.Y., Cho, H.H., Application of support vector machines in assessing conceptual cost estimates. Journal of Computing in Civil Engineering, 2007. 21(4): p. 259-264.
    9. Trost, S.M. and G.D. Oberlender, Predicting accuracy of early cost estimates using factor analysis and multivariate regression. Journal of Construction Engineering and Management, 2003. 129(2): p. 198-204.
    10. Sudiarta, I.K., Estimasi Biaya Konseptual Konstruksi Gedung dengan Faktor Kapasitas Biaya. 2011, Denpasar: Universitas Udayana.
    11. INDRAWAN, G.S., ESTIMASI BIAYA PEMELIHARAAN JALAN DENGAN ”COST SIGNIFICANT MODEL” STUDI KASUS PEMELIHARAAN JALAN KABUPATEN DI KABUPATEN JEMBRANA. 2011.
    12. Aptiyasa, P.A.A., COST MODEL ESTIMASI KONSEPTUAL UNTUK BANGUNAN GEDUNG RUMAH SAKIT. 2015, UAJY.
    13. Morrison, N., The accuracy of quantity surveyors' cost estimating. Construction Management and Economics, 1984. 2(1): p. 57-75.
    14. Akintoye, A., Analysis of factors influencing project cost estimating practice. Construction Management & Economics, 2000. 18(1): p. 77-89.
    15. Enshassi, A., Mohamed, S., Mustafa, Z.A., Mayer, P.E., Factors affecting labour productivity in building projects in the Gaza Strip. Journal of Civil Engineering and Management, 2007. 13(4): p. 245-254.
    16. Odusami, K.T. and H.N. Onukwube, Factors affecting the accuracy of a pre-tender cost estimate in Nigeria. Cost engineering, 2008. 50(9): p. 32-35.
    17. Aibinu, A.A. and T. Pasco, The accuracy of pre‐tender building cost estimates in Australia. Construction Management and Economics, 2008. 26(12): p. 1257-1269.
    18. Popescu, C.M., K. Phaobunjong, and N. Ovararin, Estimating building costs. 2003: CRC Press.
    19. Bank, A.D., Preparing and Presenting Cost Estimates for Projects and Programs Financed by the Asian Development Bank. 2014.
    20. Peter Christensen, C.L.R.D., CCC, Cost Estimate Classification System - As Applied in Engineering, Procurement, and Construction for The Process Industries. 2005.
    21. Ashworth, A., Cost studies of buildings. 2004: Pearson Education.
    22. Skitmore, M., The accuracy of construction price forecasts. 1990: University of Salford.
    23. Liu, L. and K. Zhu, Improving cost estimates of construction projects using phased cost factors. Journal of Construction Engineering and Management, 2007. 133(1): p. 91-95.
    24. Williams, T.P., Predicting changes in construction cost indexes using neural networks. Journal of Construction Engineering and Management, 1994.
    25. Oladokun, M.G., A.A. Oladokun, and I.A. Odesola, Accuracy of Pre-Tender Cost Estimates of Consultant Quantity Surveyors in Nigeria. Journal of International Real Estate and Construction Studies ISSN, 2010. 2153: p. 6813.
    26. Soemardi, B.W. and R.G. Kusumawardani, Studi Praktek Estimasi Biaya Tidak Langsung pada Proyek Konstruksi. Konferensi Nasional Teknik Sipil, 2010. 4: p. 2-3.
    27. Bari, N.A.A., Yusuff R., Ismail N., Jaapar A., Ahmad N., Factors Influencing the Construction Cost of Industrialised Building System (IBS) Projects. Procedia-Social and Behavioral Sciences, 2012. 35: p. 689-696.
    28. AKINTOYE, A., FACTORS INFLUENCING THE PROJECT COST ESTIMATING DECISION.
    29. OYEDELE, O.A., Evaluation of Factors Affecting Construction Cost Estimation Methods in Nigeria. 2015.
    30. Joachims, T., Learning to classify text using support vector machines: Methods, theory and algorithms. 2002: Kluwer Academic Publishers.
    31. Wang, Y.-R., C.-Y. Yu, and H.-H. Chan, Predicting construction cost and schedule success using artificial neural networks ensemble and support vector machines classification models. International Journal of Project Management, 2012. 30(4): p. 470-478.
    32. Naguib, I.A. and H.W. Darwish, Support vector regression and artificial neural network models for stability indicating analysis of mebeverine hydrochloride and sulpiride mixtures in pharmaceutical preparation: A comparative study. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2012. 86: p. 515-526.
    33. Shirzad, A., M. Tabesh, and R. Farmani, A comparison between performance of support vector regression and artificial neural network in prediction of pipe burst rate in water distribution networks. KSCE Journal of Civil Engineering, 2014. 18(4): p. 941-948.
    34. Smola, A.J. and B. Schölkopf, A tutorial on support vector regression. Statistics and computing, 2004. 14(3): p. 199-222.
    35. Scholkopf, B. and A.J. Smola, Learning with kernels: support vector machines, regularization, optimization, and beyond. 2001: MIT press.
    36. Chen, J.-H. and J.-Z. Lin, Developing an SVM based risk hedging prediction model for construction material suppliers. Automation in Construction, 2010. 19(6): p. 702-708.
    37. Field, A., Discovering statistics using SPSS. 2009: Sage publications.
    38. Shane, J.S., Molenaar K.R., Anderson S., Schexnayder C., Construction project cost escalation factors. Journal of Management in Engineering, 2009. 25(4): p. 221-229.

    QR CODE
    :::