都市隧道開挖多以潛盾工法進行，地底工程不確定因素眾多，因此需設置監測系統產生即時資訊預防災害發生或擴大，本研究收集臺北市捷運松山線CG291標潛盾隧道監測資料為基礎，再以專家學者分析之沉陷因素，分別列出沉陷影響因子，並應用統計軟體(SPSS)對影響因子分析，找出輸入(影響潛盾隧道因子)與輸出(沉陷量)關係，建立案例資料庫，作為潛盾隧道沉陷推論模式之基礎，後續應用生物共生演算法結合最小平方差支持向量機(SOS-LSSVM)做訓練，經由準確的預測結果可作為設計階段或施工過程中參考依據，以達到提前預警的目的。
另外本案潛盾隧道沉陷監測數據其警戒值數據比安全值數據少，當不同類別之訓練樣本筆數為不平衡時，會影響人工智慧之分類正確率，本研究將利用「機率分佈資料平衡抽樣法」來平衡資料集，可使預測準確率提升。
本研究除以SOS-LSSVM模式測試外，另外以其他人工智慧程式(ELSIM、SVM、LSSVM、BPNN)比較，最後評估比較各種模式預測成果準確性，確認SOS-LSSVM可獲得最佳的結果，可提供未來實務上之參考應用。

Urban tunnels are mostly excavated with the latent shield method. Underground engineering has many uncertainties, so the establishment of monitoring systems to detect early signs in order to prevent disaster from happening or getting worse are necessary. This study collected the Taipei MRT Songshan Route CG291 standard shield tunneling monitoring data as a basis, as well as the subsidence factors analyzed by the experts and scholars, to list subsidence factors separately. By using statistical software (SPSS) to analyze the factors to find out the relationship between input (factors of influencing shield tunneling) and output (volume of subsidence),and to establish a databank as inference of the shield tunneling subsidence, the SOS and LSSVM methods are applied subsequently to obtain accurate prediction results. Thus, these prediction results can be used as reference in the design stage or as in the construction period to achieve the goal of early warning.
In this particular case, the alert value numbers are less than the safe value numbers. When the different sample numbers have large differences, it will then affect the classification accuracy of artificial intelligence. This study will use the “probability distribution balanced data sampling method " to balance the data set, which will improve the accuracy of predictions.
In addition to SOS-LSSVM model test, other artificial intelligence programs (ELSIM, SVM, LSSVM, BPNN) were being evaluated. The method of SOS - LSSVM provided the optimal results, and are to be used as reference for application on future practices.

[1]M.-Y. Cheng, Doddy Prayogo, Yu-Wei Wu (in preparation). Predicting the Pavement Rutting Behavior of Asphalt Mixtures Using Symbiotic Organisms Search - Least Squares Support Vector Machine Inference Model. Construction and Building Materials，2014。
[2]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。
[3]Yu-Wei Wu，Object-Oriented Evolutionary Support Vector Machine Inference Model (ESIM) for Decision-Making in Construction Management，國立台灣科技大學營建工程研究所，博士論文，2009。
[4]方永壽、陳秋宗，「潛盾隧道施工盾尾孔隙所引致之地盤沉陷」，榮
工技術叢書，1988。
[5]朱旭（1984），“潛盾施工法在國內應用之探討＂，中國土木水利學會七十
三年年會論文集。
[6]大陸工程2003e。
[7]Japan Society of Civil Engineers（1996）,“Japan standard for shield tunneling”,The Third Edition.(in Japanese)。
[8]Peck, R.B.”Deep Excavations and Tunneling in Soft Ground” ,Proc. 7thint. Conf. Soil Mech. Fourid Eng., Mexico City, State of the Art, p.p255~290(1969)。
[9]Fang, Y. S., J. S. Lin and C. S. Su (1994) An Estimation of Ground Settlement due toShield Tunneling by the Peck-Fujita Method.” Canadian Geotechnical Journal, Vol. 31, pp.431-443。
[10]Clough, G.W. and Schmidt, B. “Design and Performance of Excavationand Tunnels in Soft Clay”, in Soft Clay Engineering, Elsevier(1981)。
[11]O’Reilly, M. P. and B. M. New (1982) Settlements above Tunnels in the United Kingdom – TheirMagnitude and Prediction, Tunneling, Vol. 82, pp. 173-181。
[12]Attewell, P.B and Woodman, J. P., 1982, “Predicting the dynamics of ground settlement and its derivateives caused by tunneling in soil, ”Ground Engineering, pp.13-20.。
[13]Loganathan, N. and H. G. Poulos (1998) Analytical Prediction for Tunneling-inducedGround Movements in Clays, Journal of Geotechnical and Geoenvironmental Engineering,ASCE, Vol. 124, No. 9, pp. 846-856。
[14]Fujita, K.,“Prediction of surface settlements caused by shield tunnelling,”Proceedings, International Conference on Soil Mechanics, MexicoCity, Vol. 1, pp. 239-246 (1982)。
[15]Kanji, M. A. (1979). “Surface Displacement as a Consequence of ExcavationActivities.” General Report of International Congress in Rock Mechanics,Montreal, Vol. 3.。
[16]Cording, E. J. and W. H. Hansmire (1975) Displacement around Soft Ground Gunnels, GeneralReport: Session IV, Tunnels in soil.” Proceedings of 5th Pan American Conference on Soil。
[17]Hoyaux, B. and Ladanyi, B. (1970). "Gravitational Stress Field Around a Tunnelin Soft Ground," Canadian Geotechnical Journal,Vol. 7。
[18]Atkinson, J.H. and Potts, D.M.,“Subsidence above shallow tunnels in softground,”Journal of Geotechnical Engineering, ASCE, Vol. 103, No. 4,pp. 307-325 (1977).
[19]廖惠生、賴慶和、余明山，台北盆地潛盾隧道施工引致之沉陷，萬鼎工程。
[20]楊國榮、楊鵬飛、范陳柏，多重潛盾施工所導致之地表沉陷，第二屆結構與地基國際學術研究討會，1997。
[21]方永壽，台北捷運中和線潛盾隧道施工引致之地盤沉陷，1999。
[22]陳堯中、賴建宏、黃南輝、林國楨，「潛盾施工引致孔隙水壓變化之
量測與分析」，地工技術，第六十期。
[23]驥樹勇、林金成、陳錦清，間系參數模式在潛盾隧道地盤位移之應用-I:最佳化回饋分析，中興工程第66期，2001。
[24]陳秋宗，台北市潛盾隧道施工對地盤沈陷之影響，國立交通大學研究所，碩士論文1988。
[25]林照順，以Peck-Fujita經驗方法估算潛盾隧道施工所引致之地表沉陷，國立交通大學研究所碩士論文，1992。
[26]蘇啟鑫，台北市捷運系統潛盾隧道施工造成之地盤沈陷，國立交通大學土木工程研究所，碩士論文，1991。
[27]Chawla, N. V., K. W. Bowyer, L. O. Hall and W. P. Kegelmeyer. "SMOTE: Synthetic Minority Over-sampling Technique." Journal of Artificial Intelligence Research 16: 321-357., 2002.。
[28]林以真，針對不平衡資料鑑別分析之二項隨機子空間分類法，天主教輔仁大學統計資訊研究所，碩士論文，2013。
[29]陳隆昇、林立為，植基倒傳遞類神經網路之不平衡資料處理機制，朝陽科技大學資訊工程系，2007。
[30]吳家慧，考量歷史案例機率分佈於解決不平衡資料之問題，國立台灣科技大學營建工程研究所，碩士論文，2015。
[31]張德豐，MATLAB在機率與統計上的應用，第四章統計估計及統計特徵，五南圖書出版股份有限公司。
[32]潘南飛、郭斯傑、呂淑鈴，工程統計，全威圖書有限公司。
[33]Min-Yuan Cheng and Nhat-Duc Hoang, 2012, Evolutionary Least Squares Support Vector Machine – Userguide, Technical Report, CIC Lab, National Taiwan Univ. of Sci. and Tech.。
[34]UC Irvine Machine Learning Repository, Blood Transfusion Service Center Data Set, http://archive.ics.uci.edu/ml/datasets/Blood+Transfusion+Service+Center.。
[35]Huaxiang Zhang, Mingfang Li, RWO-Sampling: A random walk over-sampling approach to imbalanced data classification, Information Fusion, Volume 20, November 2014, Pages 99-116, ISSN 1566-2535.。
[36]Silvia Cateni, Valentina Colla, Marco Vannucci, A method for resampling imbalanced datasets in binary classification tasks for real-world problems, Neurocomputing, Volume 135, 5 July 2014, Pages 32-41, ISSN 0925-2312.。
[37]Wikipedia-the free encyclopedia, Artificial Intelligence(AI), internet,https://en.wikipedia.org/wiki/Artificial_intelligence.。
[38]D.E. Goldberg, K. Deb, H. Kaegupta, and G. Harik, 1993, Rapid, accurate optimization of difficult problems using fast messy genetic algorithms.。
[39]Suykens, J., et al., 2002, Least Square Support Vector Machines. World Scientific Publishing Co. Pte. Ltd.。
[40]Min-Yuan Cheng and Nhat-Duc Hoang，「Evolutionary Least Squares Support Vector Machine - Userguide」，Technical Report, CIC Lab, National Taiwan Univ. of Sci. and Tech.，2012。
[41]M.-Y. Cheng, N.-D. Hoang, Y.-W. Wu, 2013, Hybrid intelligence approach based on LS-SVM and Differential Evolution for construction cost index estimation: A Taiwan case study. Automation in Construction, 35: 306-313.。
[42]M.-Y. Cheng, D. Prayogo, Prayogo D., 2014, Symbiotic Organisms Search: A new metaheuristic optimization algorithm. Computers & Structures, 139: 98-112.2014
[43] D. Prayogo, An Innovative Parameter-Free Symbiotic Organisms Search (SOS) for Solving Construction-Engineering Problems, PhD thesis, Department of Construction Engineering, National Taiwan University of Science and Technology, 2015.
[44]A. Panda, S. Pani, 2016, A Symbiotic Organisms Search algorithm with adaptive penalty function to solve multi-objective constrained optimization problems. Applied Soft Computing, 46: 344-360.。
[45]D.-H. Tran, M.-Y. Cheng, D. Prayogo, 2016, A novel Multiple Objective Symbiotic Organisms Search (MOSOS) for time–cost–labor utilization tradeoff problem. Knowledge-Based Systems, 94: 132-145.
[46]S. Duman, 2016, Symbiotic organisms search algorithm for optimal power flow problem based on valve-point effect and prohibited zones. Neural Computing and Applications: 1-15.
[47]捷運工程叢書第48冊，捷運松山線潛盾隧道鄰近構造設計與施工。
[48]Lewis, C. D., 1982, International and Business Forecasting Methods. London: Butterwo。
[49]林明傑、董子毅，危險評估中ROC 曲線在預測2×2表上與敏感度及特異度之關係，亞洲家庭暴力與性侵害期刊，第四卷第二期，64 -74 頁，2008。
[50]葉宗諺，利用ROC曲線評估色差量尺，大同大學，光電工程研究所，碩士論文，2014。
[51]Wikipedia-the free encyclopedia, Receiver operating characteristic(ROC curve), internet, https://en.wikipedia.org/wiki/Receiver_operating_characteristic.。
[52]Fawcett, Tom; An introduction to ROC analysis, Pattern Recognition Letters, 27, 861–874., 2006。
[53]張毓珊，發展處理類別不平衡問題之資料探勘模式，朝楊科技大學資訊管理學系，碩士論文，2009。
[54]吳秉儒，黏性土層中隧道開挖引致之地盤沉陷與破壞機制，國立中央大學土木工程學系，博士論文，2002。
[55]張皓貞，以經驗方法評估潛盾隧道施工引致之地表沉陷，國立交通大學土木工程研究所，碩士論文，2007。
[56]黃閔邑，雙圓淺盾隧道開挖造成之地盤沉陷，國立交通大學木工程研究所碩士論文，2011。
[57]黃南輝、黃亦祥、黃姿連、楊鵬飛，潛盾施工所導致之沉陷槽分析，地工技術雜誌第60期，1997。
[58]內湖CB420標潛盾隧道穿越松山機場自動及人工監測系統應用。
[59]達欣工程股份有限公司安全監測系統施工計畫書。
[60]臺北市政府捷運工程局大地資料庫。