台灣地區山高水急，主要河川21 條，次要河川29 條，普通河川79 條，多河地形使得橋梁成為台灣重要交通設施之一。民國98 年莫拉克颱風造成全台9 座橋梁沖毀，使政府對橋梁工程加倍重視。廠商想要取得公共工程必需參與政府舉辦的招標作業，由於政府採購法中對於承包商參與公開招標有設投標期限，使得營造廠商必需快速且精準的估算出工程成本及決定投標金額，過去營造廠商投標大多依預算金額配合經驗法則估算決標金額，此方法雖可快速推估底價，但並無實際科學理論依據。關於投標決策已有學者使用風險概念發展投標決策理論供競標者參考，在理論中牽涉許多影響決策的因素，本研究使用科學方法所預測的「決標金額」可做為廠商進行投標決策的參考因素之一。研究方法係採用迴歸分析(MRA)、類神經網路(ANNs)與案例式推理(CBR)，針對決標金額進行預測，並驗證模型預測準確性。研究先由政府電子採購網中取得橋梁標案計275 筆專案，進行資料預處理與敘述性統計分析，並採用基因演算法(GA)結合「非線性迴歸」及「尋找與常態分配之轉換關係再進行線性迴歸」兩種方式處理。在以非線性迴歸方法尋找最佳解方程式，使得「平均絕對誤差率(MAEE)與其標準差」線性組合最小化；線性迴歸則找尋符合卡方檢定值的轉換，其中可為log轉換或冪次轉換。類神經部份則使用GA 代替最陡坡降法尋找最佳解，搜尋過程中之動態界限可適當調整；CBR則使用GA尋找權重，再代入CBR過程。驗證方法係採用交叉驗證法，以MAEE 作為模式評估準則。

The construction projects under the government surveillance always use bid system to find the best contractor to do the project. Since the tender from the government project requires uncertainties like the lowest of the total cost for the project, decision makers try to adopt and use the concept of risk to develop the decision theory. Henceforth, the decision maker can choose the option based on the concept of this calculation and get the lowest cost value for the project.
In this framework, we construct multiple regression analysis, artificial neural network and case-based reasoning to predict the amount of the award and verify the model accuracy. Additionally, we use genetic algorithm to find the optimum solution within these parameters using cross validation within mean absolute estimation error. The analytical results expect to help the decision maker determine the bidding price in addition to their subjective judgment.

[1] J.-S. Chou, Applying AHP-Based CBR to Estimate Pavement Maintenance Cost, Tsinghua Science and Technology 13 (1007-0214) (2008) 114-120.
[2] J.-S. Chou, Generalized linear model-based expert system for estimating the cost of transportation projects, Expert Systems with Applications 36 (3, Part 1) (2009) 4253-4267.
[3] H.K. Cigizoglu, M. Alp, Generalized regression neural network in modelling river sediment yield, Advances in Engineering Software 37 (2) (2006) 63-68.
[4] D. Delen, G. Walker, A. Kadam, Predicting breast cancer survivability: A comparison of three data mining methods, Artificial Intelligence in Medicine 34 (2) (2005) 113-127.
[5] J. Han, M. Kamber, Data Mining:Concepts and Techniques, Elsevier, Singapore, 2008.
[6] B.A. Kitchenham, L. Pickard, S. Linkman, P. Jones, A framework for evaluating a software bidding model, Information and Software Technology 47 (11) (2005) 747-760.
[7] I. Krivý, J. Tvrdík, R. Krpec, Stochastic algorithms in nonlinear regression, Computational Statistics & Data Analysis 33 (3) (2000) 277-290.
[8] D. Lönn, Ø. Fyllingen, L. Nilssona, An approach to robust optimization of impact problems using random samples and meta-modelling, International Journal of Impact Engineering 37 (6) (2010) 723-734.
[9] D. Liu, Y. Yuan, S. Liao, Artificial neural network vs. nonlinear regression for gold content estimation in pyrometallurgy, Expert Systems with Applications 36 (7) (2009) 10397-10400.
[10] J.P. Martino, 技術預測方法與實例, 美商麥格羅。希爾國際股份有限公司 台灣分公司, 台北, 2005.
[11] W. McCulloch, W. Pitts, A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biology 52 (1) (1990) 99-115.
[12] S.K. Pal, S.C.K. Shiu, Foundations of Soft Case-Based Reasoning, 2004.
[13] S. Russell, P. Norvig, 人工智慧-現代方法, 全華, 台北, 2006.
[14] S.L. Salzberg, On Comparing Classifiers: Pitfalls to Avoid and a Recommended Approach, Data Mining and Knowledge Discovery 1 (1997) 317–327.
[15] K.-K. Seo, A methodology for estimating the product life cycle cost using a hybrid GA and ANN model, Vol. 4131 LNCS - I, Springer Verlag, Athens, Greece, 2006, pp. 386-395.
[16] T.P. Williams, Predicting final cost for competitively bid construction projects using regression models, International Journal of Project Management 21 (8) (2003) 593-599.
[17] N.-J. Yau, J.-B. Yang, Case-Based Reasoning in Construction Management, Computer-Aided Civil & Infrastructure Engineering, Vol. 13, Blackwell Publishing Limited, 1998, p. 143.
[18] M. Yazdanmehr, S.H.M. Anijdan, A. Bahrami, Using GA-ANN algorithm to optimize soft magnetic properties of nanocrystalline mechanically alloyed Fe-Si powders, Computational Materials Science 44 (4) (2009) 1218-1221.
[19] 王麗華, 底價的訂定與決標金額預測之研究-以X機關未達公告金額購案為例, 國防管理學院後勤管理研究所, 國防大學, 2006.
[20] 余炳盛, 曹永德, 王玉瑞, 台灣的橋梁, 遠足文化, 台北, 2007.
[21] 周鵬程, 遺傳演算法原理與應用-活用Matlab, 全華科技圖書, 台北市, 2005.
[22] 莊英略, 多階段投標決策輔助系統之研究, 土木工程系, 國立交通大學, 2001.
[23] 陳順宇, 迴歸分析, 三民書局, 台南, 2009.
[24] 陳維東, 潘南飛, 劉述舜, 虞順逸, 應用迴歸分析預測道路工程之最低標價, 技術學刊 20 (2005) 387-397.
[25] 葉怡成, 類神經網路模式應用與實作, 儒林, 台北市, 2009.