Method based on support vector machine and sequential backward selection for seismic liquefaction potential evaluation
DOI:
https://doi.org/10.18311/ijprvd/2021/30043Keywords:
Seismic liquefaction potential evaluation, support vector machine, sequential backward selection, cross validationAbstract
In the paper, the support vector machine (SVM) is utilized to evaluate the earthquake-induced site liquefaction potential, and an optimization algorithm based on cross validation and sequential backward selection(SBS) is proposed to improve the generalization ability of the classifier for seismic liquefaction potential evaluation(SLPE). Usually, the accuracy of SLPE using the SVM varies greatly when the training dataset and test dataset change, so the classifier is not reliable enough in practice. Because cross validation is more convincing for evaluating the classifier performance in machine learning, the algorithm in the paper tries to reduce the maximum error of cross validation through adopting SBS to determine the input variables of the SVM. The performance of the classifier is assessed by the area under the curve (AUC) on the basis of confusion matrix. As shown by data validation, the algorithm can reduce the maximum error of cross validation and the variation of accuracy in SLPE while maintaining good performance of the classifier. In conclusion, a method that can improve the reliability of SVMs for classification in SLPE is put forward in the paper.Downloads
Metrics
Downloads
Published
How to Cite
Issue
Section
Accepted 2022-04-24
Published 2022-04-24
References
Huang, Y. and Yu, M.(2013): “Review of soil liquefaction characteristics during major earthquakes of the twenty-first century”, Natural Hazards, Vol. 65(3), p 2375-2384
Porcino, D. and Diano,V. (2016): “Laboratory study on pore pressure generation and liquefaction of lowplasticity silty sandy soils during the 2012 earthquake in Italian”, Journal of Geotechnical and Geoenvironmental Engineering, Vol. 142(10)
Cubrinovski, M., Bray, J.D, Torre, C. de la., Olsen, M.J., Bradley,B.A., Chiaro,G., Stocks, E. and Wotherspoon, L.(2017): “Liquefaction effects and associated damages observed at the Wellington centreport from the 2016 Kaikoura earthquake”, Bulletin of the New Zealand Society for Earthquake Engineering, Vol. 50(2), p 152-173
Chen, L.W. Chen, Yuan, X.M., Cao, Z.Z., Hou,L.Q., Sun, R., Dong, L.,Wang, W.M., Meng, F.C. and Chen, H.J. (2009): “Liquefaction macrophenomena in the great Wenchuan earthquake”, Earthquake Engineering and Engineering Vibration, Vol. 8(2), p 219-229
Verdugo, R. and Gonzalez, J.(2015): “Liquefactioninduced ground damages during the 2010 Chile earthquake”, Soil Dynamics and Earthquake Engineering, Vol. 79, p 280-295
Seed, H.B.(1966): “Liquefaction of saturated sands during cyclic loading”, Journal of the Soil Mechanics and Foundation Engineering Division, Vol. 92(SM6), p 105-134
Adamidis, O. and Madabhushi, S.P.G (2018): “Experimental investigation of drainage during earthquake-induced liquefaction”, Geotechnique, Vol. 68(8), p 655-665
Clement,C., Toussaint, R., Stojanova, M. and Aharonov, E.(2018): “Sinking during earthquakes: Critical acceleration criteria control drained soil liquefaction”, Physical Review E, Vol. 97(2)
Unjoh, S., Kaneko, M, Kataoka, S., Nagaya, K. and Matsuoka,K.(2012): “Effect of earthquake ground motions on soil liquefaction”, Soils and Foundations, Vol. 52(5), p 830-841
Akkaya, I., Ozvan, A., Akin, M., Akin, M.K. and Ovun, U.(2018): “Comparison of SPT and V-s-based liquefaction analyses: a case study in Ercis (Van, Turkey)”, Acta Geophysica, Vol. 66(1), p 21-38
Isik, A., Unsal, N., A. Gurbuz, A. and Sisman, E.(2016): “Assessment of liquefaction potential of fethiye based on spt and shear wave velocity”, Journal of the Faculty of Engineering and Architecture of Gazi University, Vol. 31(4), p 1027-1037
Zhao, X.L. and Cai, G.J. (2015): “SPT-CPT correlation and its application for liquefaction evaluation in China”, Marine Georesources & Geotechnology, Vol. 33(3), p 272-281
Seo, M.W., Olson, S.M., Sun, C.G. and Oh, M.H. (2012): “Evaluation of liquefaction potential index along western coast of South Korea using SPT and CPT”, Marine Georesources & Geotechnology, Vol. 30(3), p 234-260
Maxwell, A.E., Warner T.A. and Fang, F. (2018): “Implementation of machine-learning classification in remote sensing: an applied review”, International Journal of Remote Sensing, Vol. 39(9), p 2784-2817
Venkatesh, K, Kumar, V. and Tiwari,R.P. (2013): “Appraisal of liquefaction potential using neural network and neuro fuzzy approach”, Applied Artificial Intelligence, Vol. 27(8), p 700-720
Xue, X.H. and Liu, E.L. (2017): “Seismic liquefaction potential assessed by neural networks”, Environmental Earth Sciences, Vol. 76(5), p 1-15
Tang, X.W., Bai, X, Hu, J.L. and Qiu, J.N.(2018): “Assessment of liquefaction-induced hazards using bayesian networks based on standard penetration test data”, Natural Hazards and Earth System Sciences, Vol. 18(5), p 1451-1468
Gandomi, A.H., Fridline, M.M. and Roke, D.A. (2013): “Decision tree approach for soil liquefaction assessment”, Scientific World Journal, Vol.2013,p1-8
Kohestani, V.R., Hassanlourad, M, and Ardakani, A. (2015): “Evaluation of liquefaction potential based on CPT data using random forest”, Natural Hazards, Vol. 79(2), p 1079-1089
Xue, X.H. and Yang, X.G.(2016): “Seismic liquefaction potential assessed by support vector machines approaches”, Bulletin of Engineering Geology and the Environment, Vol. 75(1), p 153-162
Fernandez-Delgado, M., Cernadas, E., Barro, S. and Amorim, D. (2014): “Do we need hundreds of classifiers to solve real world classification problems?”, Journal of Machine Learning Research, Vol. 15, p 3133-3181
Wong, T.T. and Yang, Y.Y.(2017): “Dependency analysis of accuracy estimates in k-fold cross validation”, IEEE Transactions on Knowledge and Data Engineering, Vol. 29(11), p 2417-2427
Rodriguez, J.D., Perez, A. and Lozano, J.A.(2010): “Sensitivity analysis of k-fold cross validation in prediction error estimation”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32(3), p 569-575
Hu, J.L., Tang, X.W. and Qiu,J.N. (2016): “Assessment of seismic liquefaction potential based on bayesian network constructed from domain knowledge and history data”, Soil Dynamics and Earthquake Engineering, Vol. 89, p 49-60
Juang,C.H., Yuan,H., Lee, D.H. and Lin, P.S. (2003): “Simplified cone penetration test-based method for evaluating liquefaction resistance of soils”, Journal of Geotechnical & Geoenvironmental Engineering, Vol. 129(1),p 66-80
Samui, P.(2011): “Least square support vector machine and relevance vector machine for evaluating seismic liquefaction potential using SPT”, Natural Hazards, Vol. 59(2),p 811-822
Samui, P.(2008): “Support vector machine applied to settlement of shallow foundations on cohesionless soils”, Computers and Geotechnics, Vol. 35(3), p 419- 427
Zhou,Y., Su,W., Ding, L., Luo, H. and Love, P.E.D.(2017): “Predicting safety risks in deep foundation pits in subway infrastructure projects: Support vector machine approach”, Journal of Computing in Civil Engineering, Vol. 31(5)
Chang, C.C. and Lin, C.J. (2011): “LIBSVM: A library for support vector machines”, ACM Transactions on Intelligent Systems and Technology, Vol. 2(3),p27:1- 27:27
Romero, E. and Sopena, J.M. (2008): “Performing feature selection with multilayer perceptrons”, IEEE Transactions on Neural Networks, Vol. 19(3), p 431- 441
Rahman, M.M., Imtiaz, S.A. and Hawboldt, K. (2016): “A hybrid input variable selection method for building soft sensor from correlated process variables”, Chemometrics and Intelligent Laboratory Systems, Vol. 157, p 67-77
Chen, L.H. and Chang, C.J. (2018): “Approaches to select suitable subset of explanatory variables for establishing fuzzy regression models”, Journal of Intelligent & Fuzzy Systems, Vol. 34(1), p 437-457
Alpaydin, E. (2014): “Introduction to machine learning”, 3rd ed. 2014, Cambridge, Massachusetts,USA: MIT Press.
Idriss, I.M. and R.W. Boulanger, R.W. (2008): “Soil liquefaction during earthquakes”, Oakland, California, USA: Earthquake Engineering Research Institute.
Hosmer, D.W., Lemeshow, S. and Sturdivant, R.X. (2013): “Applied logistic regression”,3rd ed. 2013, Hoboken, New Jersey,USA: John Wiley & Sons, Inc.