政府鑑於歷年來之大地震都帶給國中小學校舍嚴重的損害，加上校舍大多使用30年以上，由此可知校舍多屬老舊，普遍有耐震能力不足之疑慮。為提升校舍的耐震能力，教育部委託國家地震工程研究中心擬定一套校舍耐震評估與補強之流程，針對國中小學校舍進行耐震能力評估。
依照校舍耐震評估與補強之流程，校舍需經過初步評估後才決定是否進行詳細評估，再由詳細評估結果決定校舍是否需補強。由於詳細評估所花的時間與金錢相當可觀，因此若在初步評估時能提升其篩選結果之準確率，就可減少因篩選錯誤所耗費之時間與金錢。再者，政府在訂定補強計畫與編列預算時，需要預估整體需補強校舍之數量與工程經費，因此如何在校舍評估初期快速且準確推估校舍是否需補強與校舍補強工程總經費，為一不可忽視的問題。
此外，目前校舍補強耐震能力值只需達最低規範值，因耐震能力值提高太多，校舍補強工程總經費會太高，將造成政府財政負擔與資源浪費。但以生命週期觀點來看，耐震能力值提高，可減少因地震倒塌的機會，進而降低校舍倒塌的地震損害風險成本，因此如何求得校舍補強工程總經費與校舍倒塌的地震損害風險成本的取捨關係，使得校舍生命週期地震風險成本最小，亦為一值得探討的課題。
概括上述，本研究應用演化式支持向量機推論模式與地震危害度曲線，建立校舍生命週期地震風險成本推論模式，解決上述問題。本推論模式可輔助政府針對補強計畫與預算編列做出妥適的決策，以期加速改善現行校舍老舊及耐震能力不足之問題，並確保學校師生安全以建構優質學習環境。

Because the school buildings were always damaged in the big earthquake, the school buildings mostly were used for 30 years. Thus, it may be known the school buildings are old, they had less satisfactory seismic performance. To enhance the seismic performance of school buildings, the Ministry of Education of Taiwan entrusts the National Center of Research on Earthquake Engineering to draw up a set process of seismic performance of school buildings.
According to the process of seismic performance of school buildings, the school building must pass through the preliminary assessment to decide whether go on the detailed assessment. Then through the detailed assessment to decide whether go on the seismic retrofitting. But, the detailed assessment cost much money and took much time. So, if we can promote the accuracy of the preliminary assessment. It may reduce
money and time by the wrong assume. Furthermore, when the government makes up the plan and budget, they need to estimate the quantity of the school buildings which have to retrofit, and the funds of seismic retrofitting. So, it’s an important problem.
In addition, the seismic performance of school buildings only has to reach the lowest standard value. Because the seismic performance enhances much, then the funds of the seismic retrofitting will become too high. But, if the seismic performance enhances much, then the expected value of losses due to seismic total damage will reduce. Therefore, this research considers both the funds of seismic retrofitting and the expected value of losses due to seismic total damage.
Above all, this research applies Evolutionary Support Vector Machine Inference Model and the hazard curve of response spectral accelerations to establish the model of estimating life cycle the expected value of losses due to seismic damage of school buildings. This model can resolve above problems.

[1] 蔡益超、黃炯憲、曾一平、陳威成，學校建築結構耐震能力詳細評估與補強，國家地震工程研究中心，2000。
[2] 黃世建、鍾立來、簡文郁、葉勇凱等，全國中小學校舍耐震評估與補強施行計畫，國家地震工程研究中心，2005。
[3] 許丁友、鍾立來、廖文義、邱建國、簡文郁、周德光，國民中小學典型校舍耐震能力初步評估法，國家地震工程研究中心，2003。
[4] 蔡忠憲，基於資料探勘技術之校舍補強經費與耐震補強結果預測模型，國立台灣科技大學營建工程研究所碩士論文，2013。
[5] 吳育偉、鄭明淵，支持向量機最佳化模式-應用於營建管理決策，第11屆營建工程與管理學術研討會，2007。
[6] 老舊校舍補強專案辦公室，校舍耐震資訊網，http://school.ncree.org.tw/school/home/news.php，國家地震工程研究中心。
[7] Park, Y. J., & Ang, A. H. S. Mechanistic seismic damage model for reinforced concrete. Journal of Structural Engineering, ASCE, 111(4), 722-739, 1985.
[8] 黃世建、鍾立來、葉勇凱、簡文郁、蕭輔沛等，校舍結構耐震評估與補強技術手冊，國家地震工程研究中心，2008。
[9] 邱建國、林宜鋒，劣化鋼筋混凝土建築物生命週期地震風險評估研究，建築學報，台灣建築學會，第87期，第67-91頁，2014。
[10] Kim, J. H.，田中浩平，糸井達哉，高田毅士。地震ハザード曲線の直線近似に基づいた破壊確率評価法の有効性(信頼性(3)，安全性，構造 I ) 。学術講演梗概集. B-1, 構造 I, 荷重・信頼性,応用力学・構造解析,基礎構造,シェル・立体構造・膜構，日本建築学会，pp. 29-30，2010。
[11] 邱永芳、林雅雯、胡啟文、邱建國、鄭明淵等，橋梁殘餘壽齡與保全評估決策模式之研發（3/4），交通部運輸研究所，2014。
[12] ATC-13. Earthquake Damage Evaluation Data for California. CA, USA: Applied Technology Council, 1985.
[13] FEMA. Earthquake Loss Estimation Methodology – Hazus 99 Technical Manual, Vol. 3. Washington, D. C. : Federal Emergency Management Agency, 1999.
[14] Ko, C. H. Computer aided decision support system for disaster prevention of hillside residents, MS thesis, National Taiwan University of Science and Technology, Taipei, Taiwan, 1999.
[15] Fukahori, K. and Kubota, Y. Consistency evaluation of landscape design by a decision support system, Computer-Aided Civil and Infrastructure Engineering, 15(5), 342-354, 2000.
[16] Sundin, S., and Braban-Ledoux, C. Artificial intelligence-based decision support technologies in pavement management, Computer-Aided Civil and Infrastructure Engineering, 16(2), 143-157, 2001.
[17] Cheng Min-Yuan and Ko Chien-Ho, Object-Oriented Evolutionary Fuzzy Neural Inference System for Construction Management, Journal of Construction Engineering and Management, ASCE, Vol. 129, No. 4, pp.461-469, 2003.
[18] Martino, J. P. Technological Forecasting for Decision Making. 3rd ed., New York, McGraw-Hill, 251-252, 1993.
[19] Davis, D. (1996). Business research for decision making, 4th ed., Belmont, Duxbury Press, 4.
[20] 鄧乃楊等，數據挖掘的新方法-支持向量機，科學出版社，中國，2004。
[21] 楊智民，劉廣利，不確定性支持向量機原理及應用，科學出版社，中國，2006。
[22] D.E. Goldberg, K. Deb, H. Kaegupta, G. Harik, Rapid, accurate optimization of difficult problems using fast messy genetic algorithms, Proceedings of the Fifth International Conference on Genetic Algorithms, pp. 56- 64, 1993.
[23] D. Knjazew, G.A. Ome, A Competent Genetic Algorithm for Solving Permutation and Scheduling Problems, Kluwer Academic Publishers, Boston, 2003.
[24] 許淑婷，利用快速混雜基因演算法與模擬機制建立設計專案作業程序最佳化之研究，國立成功大學碩士論文，2006。
[25] 簡崑棋、馮重偉，結合模糊類神經模式與快速混雜基因演算法於專案工期之預測，國立成功大學碩士論文，2003。
[26] Thorsten Joachims, http://svmlight.joachims.org/svm_struct.html
[27] 張家榮，同時考慮餘弦角度及距離的群集方法，國立台灣科技大學營建工程所碩士論文，2014。
[28] 譚克平，極端值判斷方法簡介，台東大學教育學報，第十九卷第一期，第131-150頁，2008。
[29] B. G. Tabachnick, and L. S. Fidell. Using Multivariate Statistics (5th Edition), Allyn & Bacon, Boston, 2007.
[30] J. I. Maletic, and A. Marcus, Data Cleansing: A Prelude to Knowledge Discovery, Data Mining and knowledge Discovery Handbook, O. Maimon, and L. Rokach, eds., Springer US, 19-32, 2010.
[31] C.D. Lewis, Industrial and Business Forecasting Method. London: Butterworth-Heinemann, 1982.
[32] 101年度中央政府總預算編製作業手冊共同性費用編列標準表，行政院主計處公務預算局。