台灣國家實驗研究院地震工程研究中心（國震中心）在九二一大地震後，與教育部合作執行「加速國中小老舊校舍及相關設備補強整建計畫」等計畫，評估全台灣的各級學校校舍之耐震能力，由於在這些計畫執行的過程中產生了大量的評估與調查資料，因此國震中心便建立了一個校舍耐震能力資料庫來收集各種相關的資料，收集了包括校舍的各種設計參數、材料強度、校舍現況及年齡、技師的評估與補強建議方案、實際補強的金額與補強方法等，資料涵蓋非常多元。此一資料庫所收集的校舍資料數量龐大，故除了當初設計的目的之外，應該還潛藏有其他類型的有用知識，但是難以由人工直接判斷取得，而資料探勘（Data Mining）就是用來分析這種數量龐大的資料，從中找出有用的潛藏知識的相關技術的統稱，本研究之目的即為利用資料探勘技術來發掘潛藏於此校舍耐震資料庫中的知識，從資料探勘的四種主要分析方法：回歸、分類、分群、關聯出發，分別探討各種方法在此資料庫中有何可能的分析方向，有哪些可能的潛藏知識，並進行分析，最後得到了三個有用且可靠度足夠的關係模型，分別為校舍資訊與耐震能力之關係模型、校舍資訊與破壞構件之關係模型以及校舍資訊與補強經費之關係模型。

After the Jiji eqrthquake at Taiwan. Ministry of Education work together with National Center for Research on Earthquake Engineering(NCREE) on a project to improve aseismic ability of every level of schools. During the project process, lots of survey and evaluation data were collected including the geometry design parameters, strength of materials, age and status of buildings, evaluation results, retrofit plans ..etc. The collected data were stored in a database called school aseismic database. The amount of data are huge. It should contain hidden knowledge which is very hard to get just by human brain. Data Mining is a subfield of computer science. The goal of data mining is to discover patterns in an easy to understand form. The data mining technologies are artificial intelligence, machine learning, statistics and database system. The purpose of this research is using data mining technology to discover hidden knowledge from school aseismic database. Nased on four main data mining category: regression, classification, clustering and association rules. We reasearch on the characteristic of these four main category and find knowledge candidates. After the mining and analysis. Three useful and reliable model were discovered: "Model of School Building Geometry Parameter and Aseismic Ability", "Model of School Building Geometry Parameter and Major Crack Component" and "Model of School Building Geometry Parameter and Retrofit Cost".

[1] B. S. S. C. (US) and A. T. Council, NEHRP guidelines for the seismic rehabilitation of buildings, vol. 1. Federal Emergency Management Agency, 1997.
[2] U. Fayyad, G. Piatetsky-Shapiro, and P. Smyth, “From data mining to knowledge discovery in databases,” AI magazine, vol. 17, no. 3, p. 37, 1996.
[3] 張鉅輝, “混凝土橋梁耐震能力評估與資料庫系統之建立,” Master’s thesis, 中華 大學土木工程學系, 2003.
[4] 周武坤, “GPS/GIS 科技應用於高雄都會區地下管線工程管理資料庫系統之建 立與應用,” Master’s thesis, 屏東科技大學土木工程系, 2002.
[5] 侯峻棕, “GPS/GIS 應用於南橫公路〔甲仙至埡口段〕邊坡地工環境災害資料 庫系統之建立研究,” Master’s thesis, 屏東科技大學土木工程系, 2000.
[6] 蘇振綱, “地理資訊系統計畫評估方法之研究─以環境地質資料庫為例,” Master’s thesis, 國立台灣大學建築與城鄉研究所, 1993.
[7] K. H. Law, T. Barsalou, and G. Wiederhold, “Management of complex structural engineering objects in a relational framework,” Engineering with computers, vol. 6, no. 2, pp. 81–92, 1990.
[8] C.-K. Kim, S.-E. Lee, and S.-M. Hong, “A new integrated database model for the design and construction information of building structures,” in International Conference on Information Technology in Construction, pp. 315–324, 2000.
[9] S. Somo and H. Hong, “Modeling error analysis of shear predicting models for rc beams,” Structural safety, vol. 28, no. 3, pp. 217–230, 2006.
[10] E. Cuenca, P. Serna, and G. Plizzari, “Shear database for reinforced and prestressed beams made with fiber reinforced concrete,” in Proceedings of the 8th International Conference on Fracture Mechanics of Concrete and Concrete Structures, FraMCoS 2013, pp. 1089–1100, 2013.
[11] J. Hodková, A. Lupíšek, Š. Mančík, L. Vochoc, and T. Žd’ára, “Envimat. cz–online database of environmental profiles of building materials and structures,” in Environmental Software Systems. Frameworks of eEnvironment, pp. 272–279, Springer, 2011.
[12] P. B. Lourenço, D. V. Oliveira, J. C. Leite, J. Ingham, C. Modena, and F. da Porto, “Simplified indexes for the seismic assessment of masonry buildings: International database and validation,” Engineering Failure Analysis, vol. 34, pp. 585–605, 2013.
[13] D. Duthinh and W. P. Fritz, “Nonlinear database-assisted design leads to”greener” steel buildings,” in Structures Congress 2006: Structural Engineering and Public Safety, pp. 1–17, ASCE, 2006.
[14] American Society of Civil Engineers (ASCE), Minimum design loads for buildings and other structures. ASCE 7-02, 2002.
[15] E. M. Golafshani, A. Rahai, and M. H. Sebt, “Artificial neural network and genetic programming for predicting the bond strength of gfrp bars in concrete,” Materials and Structures, pp. 1–22, 2014.
[16] ACI Committee 440, “Guide for the design and construction of concrete reinforced with frp bars (aci 440.1 r-06),” American Concrete Institute, Detroit, Michigan, 2006.
[17] M. H. Arslan, “An evaluation of effective design parameters on earthquake performance of rc buildings using neural networks,” Engineering Structures, vol. 32, no. 7, pp. 1888–1898, 2010.
[18] M.Azadi,S.Pourakbar,andA.Kashfi,“Assessmentofoptimumsettlementofstruc- ture adjacent urban tunnel by using neural network methods,” Tunnelling and under- ground space technology, vol. 37, pp. 1–9, 2013.
[19] A.A.Elshafey,N.Dawood,H.Marzouk,andM.Haddara,“Predictingofcrackspacing for concrete by using neural networks,” Engineering Failure Analysis, vol. 31, pp. 344–359, 2013.
[20] M. Sarıdemir, “Prediction of compressive strength of concretes containing metakaolin and silica fume by artificial neural networks,” Advances in Engineering Software, vol. 40, no. 5, pp. 350–355, 2009.
[21] İ. B. Topçu and M. Sarıdemir, “Prediction of rubberized concrete properties using artificial neural network and fuzzy logic,” Construction and Building Materials, vol. 22, no. 4, pp. 532–540, 2008.
[22] R.Ince,“Predictionoffractureparametersofconcretebyartificialneuralnetworks,” Engineering Fracture Mechanics, vol. 71, no. 15, pp. 2143–2159, 2004.
[23] 張玉瑛, “以支援向量機預測台灣地區營造工程物價指數之研究,” Master’s thesis, 朝陽科技大學營建工程所, 2007.
[24] J.-H. Chen and J.-Z. Lin, “Developing an svm based risk hedging prediction model for construction material suppliers,” Automation in Construction, vol. 19, no. 6, pp. 702–708, 2010.
[25] D. Tuhus-Dubrow and M. Krarti, “Genetic-algorithm based approach to optimize building envelope design for residential buildings,” Building and Environment, vol. 45, no. 7, pp. 1574–1581, 2010.
[26] A. Kaveh, B. Farahmand Azar, A. Hadidi, F. Rezazadeh Sorochi, and S. Talatahari, “Performance-based seismic design of steel frames using ant colony optimization,” Journal of Constructional Steel Research, vol. 66, no. 4, pp. 566–574, 2010.
[27] H.-M.ChenandW.-K.Kao,“Computer-aidedmodelgenerationfornonlinearstructural analysis using a structural component model database,” Journal of Computing in Civil Engineering, vol. 22, no. 5, pp. 312–324, 2008.
[28] C.-S. Chen, M.-Y. Cheng, and Y.-W. Wu, “Seismic assessment of school buildings in taiwan using the evolutionary support vector machine inference system,” Expert Systems with Applications, vol. 39, no. 4, pp. 4102–4110, 2012.
[29] L. de Santoli, F. Fraticelli, F. Fornari, and C. Calice, “Energy performance assess- ment and a retrofit strategies in public school buildings in rome,” Energy and Build- ings, vol. 68, pp. 196–202, 2014.
[30] S. SATO and K. MINANI, “Damage analysis of existing public school buildings in hiroshima prefecture due to 2001 geiyo earthquake,” The Memoirs of the Faculty of Engineering,Fukuyama University., vol. 28, pp. 81–91, Dec 2004.
[31] R. Jafarzadeh, J. M. Ingham, and S. Wilkinson, “A seismic retrofit cost database for buildings having a framed structure,” Earthquake Spectra, 2014.
[32] R. Jafarzadeh, Seismic retrofit cost modelling of existing structures. PhD thesis, The University of Auckland, 2012.
[33] R. Jafarzadeh, S. Wilkinson, V. González, J. Ingham, and G. G. Amiri, “Predicting seismic retrofit construction cost for buildings with framed structures using multilinear regression analysis,” Journal of Construction Engineering and Management, vol. 140, no. 3, 2013.
[34] R. Jafarzadeh, J. Ingham, S. Wilkinson, V. González, and A. Aghakouchak, “Application of artificial neural network methodology for predicting seismic retrofit construction costs,” Journal of Construction Engineering and Management, vol. 140, no. 2, 2013.
[35] 許丁友, 鍾立來, 廖文義, 邱建國, 簡文郁, and 周德光, “國民中小學典型校舍耐 震能力初步評估法,” Tech. Rep. NCREE-03-049, 國家地震工程研究中心, Dec 2003.
[36] Applied Technology Council (ATC), Seismic evaluation and retrofit of concrete buildings. Report No. SSC 96-01: ATC-40, 1996.
[37] FederalEmergencyManagementAgency(FEMA),ImprovementofNonlinearStatic Seismic Analysis Procedures. FEMA-440, 2005.
[38] C. Shearer, “The crisp-dm model: the new blueprint for data mining,” Journal of data warehousing, vol. 5, no. 4, pp. 13–22, 2000.
[39] K. Jensen, “CRISP-DM Process Diagram,” Apr 2012. http://commons. wikimedia.org/wiki/File:CRISP-DM_Process_Diagram.png.
[40] B. Mabey, “Pca for the uninitiated,” 2013. http://benmabey.com/ presentations/pca-tutorial/#12.
[41] J. A. Nelder and R. W. M. Wedderburn, “Generalized Linear Models,” Journal of the Royal Statistical Society. Series A (General), vol. 135, no. 3, pp. 370–384, 1972.
[42] W. S. McCulloch and W. Pitts, “A logical calculus of the ideas immanent in nervous activity,” The Bulletin of Mathematical Biophysics, vol. 5, no. 4, pp. 115–133, 1943.
[43] P. Werbos, Beyond regression: New tools for prediction and analysis in the behavioral sciences. PhD thesis, Harvard University, 1974.
[44] D. Rummelhart, “Learning representations by back-propagating errors,” Nature, vol. 323, no. 9, pp. 533–536, 1986.
[45] D. T. Larose, Discovering knowledge in data: an introduction to data mining. John Wiley & Sons, 2005.
[46] J. H. Holland, Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence. U Michigan Press, 1975.
[47] H. Minshui, L. Jie, and Z. Hong-ping, “Study on construction of objective function for damage identification using improved genetic algorithm,” in Natural Computation, 2009. ICNC’09. Fifth International Conference on, vol. 4, pp. 430–435, IEEE, 2009.
[48] D. Šešok and R. Belevičius, “Global optimization of trusses with a modified genetic algorithm,” Journal of Civil Engineering and management, vol. 14, no. 3, pp. 147–154, 2008.
[49] J. R. Koza, Genetic programming: on the programming of computers by means of natural selection, vol. 1. MIT press, 1992.
[50] I. Yeh, L.-C. Lien, et al., “Knowledge discovery of concrete material using genetic operation trees,” Expert Systems with Applications, vol. 36, no. 3, pp. 5807–5812, 2009.
[51] H.-C. Tsai, “Using weighted genetic programming to program squat wall strengths and tune associated formulas,” Engineering Applications of Artificial Intelligence, vol. 24, no. 3, pp. 526–533, 2011.
[52] H.-C. Tsai and Y.-H. Lin, “Predicting high-strength concrete parameters using weighted genetic programming,” Engineering with Computers, vol. 27, no. 4, pp. 347–355, 2011.
[53] G. V. Kass, “An exploratory technique for investigating large quantities of categorical data,” Applied statistics, pp. 119–127, 1980.
[54] B.E.Boser,I.M.Guyon,andV.N.Vapnik,“Atrainingalgorithmforoptimalmargin classifiers,” in Proceedings of the 5th Annual Workshop on Computational Learning Theory (COLT’92) (D. Haussler, ed.), (Pittsburgh, PA, USA), pp. 144–152, ACM Press, Jul 1992.
[55] T. Verplancke, S. Van Looy, D. Benoit, S. Vansteelandt, P. Depuydt, F. De Turck, and J. Decruyenaere, “Support vector machine versus logistic regression modeling for prediction of hospital mortality in critically ill patients with haematological malignancies,” BMC Medical Informatics and Decision Making, vol. 8, no. 1, p. 56, 2008.
[56] H. Drucker, C. J. Burges, L. Kaufman, A. Smola, and V. Vapnik, “Support vector regression machines,” Advances in neural information processing systems, vol. 9, pp. 155–161, 1997.
[57] J. MacQueen, “Some methods for classification and analysis of multivariate observations,” in Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, vol. 1, pp. 281–297, 1967.
[58] T. Zhang, R. Ramakrishnan, and M. Livny, “Birch: an efficient data clustering method for very large databases,” in ACM SIGMOD Record, vol. 25, pp. 103–114, ACM, 1996.
[59] S. Geisser, “The predictive sample reuse method with applications,” Journal of the American Statistical Association, vol. 70, no. 350, pp. 320–328, 1975.
[60] J. Aldrich, “Correlations genuine and spurious in pearson and yule,” Statistical Science, pp. 364–376, 1995.
[61] 內政部營建署編輯委員會, 建築物耐震設計規範及解說. 營建雜誌社, 2005.
[62] 蘇耕立, “台灣中小學校舍結構耐震能力初步評估方法之探討,” Master’s thesis,
國立台灣大學土木系, Jul 2008.
[63] IBM,“SPSSModeler.”http://www-01.ibm.com/software/analytics/spss/
products/modeler/.
[64] MathWorks Inc., “Matlab.” http://www.mathworks.com/products/matlab/.
[65] 國家地震工程研究中心, “高中職及國中小校舍結構耐震能力補強設計作業規 範,” Oct 2013.
[66] 國家地震工程研究中心, “國中小校舍「補強工程」之經費支用範圍及參考單 價計價方式 (修正版)【方案 c】,” Jun 2010.
[67] 黃世建, 葉勇凱, 鍾立來, 簡文郁, 陳鴻銘, 趙宜峰, 周德光, 沈文成, and 高偉 格, “全國中小學校舍結構耐震評估與補強資料庫建置(一),” Tech. Rep. NCREE-08-035, 國家地震工程研究中心, Dec 2008.
[68] 葉勇凱, 蕭輔沛, 沈文成, 楊耀昇, and 黃世建, “鋼筋混凝土建築物耐震能力詳 細評估分析方法(推垮分析),” Tech. Rep. NCREE-09-015, 國家地震工程研究 中心, Jun 2009.
[69] 葉勇凱, 趙宜峰, 陳鴻銘, 高偉格, 沈文成, 翁樸文, 鍾立來, 簡文郁, and 黃世 建, “全國中小學校舍結構耐震評估與補強資料庫建置(二),” Tech. Rep. NCREE-09-026, 國家地震工程研究中心, Dec 2009.