Abstract
Machine learning method has been widely used in various geotechnical engineering risk analysis in recent years. However, the overfitting problem often occurs due to the small number of samples obtained in history. This paper proposes the Fuzzy- SVM (support vector machine) geotechnical engineering risk analysis method based on the Bayesian network. The proposed method utilizes the fuzzy set theory to build a Bayesian network to reflect prior knowledge, and utilizes the SVM to build a Bayesian network to reflect historical samples. Then a Bayesian network for evaluation is built in Bayesian estimation method by combining prior knowledge with historical samples. Taking seismic damage evaluation of slopes as an example, the steps of the method are stated in detail. The proposed method is used to evaluate the seismic damage of 96 slopes along roads in the area affected by the Wenchuan earthquake. The evaluation results show that the method can solve the overfitting problem, which often occurs if the machine learning methods are used to evaluate risk of geotechnical engineering, and the performance of the method is much better than that of the previous machine learning methods. Moreover, the proposed method can also effectively evaluate various geotechnical engineering risks in the absence of some influencing factors.
Similar content being viewed by others
Reference
Adafer S, Bensaib M (2014) Seismic vulnerability assessment of road networks. Second European Conference on Earthquake Engeneering and Seismology 25–29. Available online at: http://www.eaee.org/Media/Default/2ECCES/2ecces_eaee/1012.pdf (accessed on 2018-8-3)
Antonucci A, Salvettib A, Zaffalon M (2004) Hazard assessment of debris flows by credal networks. 2nd International Congress on Environmental Modelling and Software. Available online at: https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=3439&context=iemssconference (accessed on 2019-3-23)
Benov DM (2016) The Manhattan Project, the first electronic computer and the Monte Carlo method. Monte Carlo Methods and Applications 22(1): 73–79. https://doi.org/10.1515/mcma-2016-0102
Chen LS (2012) Seismic damage investigation for highway in Wenchuan earthquake, Subgrade. China Communications Press 63-372. (In Chinese)
Cortes C, Vapnik V (1995) Support-vector networks. Machine learning 20(3): 273–297. https://doi.org/10.1007/BF00994018
Kayastha P, Dhital MR, Smedt DE (2013) Application of the analytical hierarchy process (AHP) for landslide susceptibility mapping: a case study from the Tinau watershed, west Nepal. Computers & Geosciences 52: 398–408. https://doi.org/10.1016/j.cageo.2012.11.003
Lam W, Bacchus F (1994) Learning bayesian belief networks: an approach based on the MDL principle. Computational Intelligence 10(3): 269–293. https://doi.org/10.1111/j.1467-8640.1994.tb00166.x
Lauritzen SL, Spiegehalter DJ (1988) Local computations with probabilities on graphical structures and their application to expert systems. Journal of the Royal Statistical Society 50(2): 157–224. https://doi.org/10.2307/2982997
Li XY, Zhang LM, Zhang S (2017) Efficient Bayesian networks for slope safety evaluation with large quantity monitoring information. Geoscience Frontiers 9(1): 1–9. https://doi.org/10.1016/j.gsf.2017.09.009
Lin HM, Chang SK, Wu JH, et al. (2009) Neural networkbased model for assessing failure potential of highway slopes in the Alishan, Taiwan Area: pre-and post-earthquake investigation. Engineering Geology 104(3): 280–289. https://doi.org/10.1016/j.enggeo.2008.11.007
Liu SY, Shao LT, Li HJ (2015) Slope stability analysis using the limit equilibrium method and two finite element methods. Computers & Geotechnics 63: 291–298. https://doi.org/10.1016/j.compgeo.2014.10.008
Mahdevari S, Haghighat HS, Torabi SR (2013) A dynamically approach based on SVM algorithm for prediction of tunnel convergence during excavation. Tunnelling and Underground Space Technology 38: 59–68. https://doi.org/10.1016/j.tust.2013.05.002
Moghaddasi MR, Noorian BM (2018) ICA-ANN, ANN and multiple regression models for prediction of surface settlement caused by tunneling. Tunnelling and Underground Space Technology 79: 197–209. https://doi.org/10.1016/j.tust.2018.04.016
Pearl J (1986) Fusion, propagation, and structuring in belief networks. Artificial Intelligence 29(3): 241–288. https://doi.org/10.1016/0004-3702(86)90072-X
Platt J C (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in Large Margin Classifiers 10(4): 61–74. Available online at: https://www.cs.colorado.edu/~mozer/Teaching/syllabi/6622/papers/Platt1999.pdf (accessed on 2018-3-6)
Price D, Knerr S, Personnaz L, et al. (1994) Pairwise neural network classifiers with probabilistic outputs. International Conference on Neural Information Processing Systems 1109–1116. Available online at: http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=6A72B82942A78DFA4404165982342596?doi=10.1.1.48.8886&rep=rep1&type=pdf, (accessed on 2018-3-6)
Sinha AK (1989) Expert system approach to slope stability. Mining Science & Technology 8(1): 21–29. https://doi.org/10.1016/S0167-9031(89)90880-3
Song YQ, Gong JH, Gao S, et al. (2012) Susceptibility assessment of earthquake-induced landslides using Bayesian network: a case study in Beichuan, China. Computers & Geosciences 42(5): 189–199. https://doi.org/10.1016/j.cageo.2011.09.011
Straub D, Faber MH (2010) Computational aspects of riskbased inspection planning. Computer-Aided Civil and Infrastructure Engineering 21(3): 179–192. https://doi.org/10.1111/j.1467-8667.2006.00426.x
Su YH, He MC, Sun XM (2007) Equivalent characteristic of membership function type in rock mass fuzzy classification. Journal of University of Science and Technology Beijing 29(7): 670–675. (In Chinese) https://doi.org/10.1360/yc-007-0745
Subramanian J, Simon R (2013) Over fitting in prediction models - Is it a problem only in high dimensions? Contemporary Clinical Trials 36(2): 636–641. https://doi.org/10.1016/j.cct.2013.06.011
Technical Committee for Earthquake Geotechnical Engineering, TC4, ISSMGE (1993) Manual for zonation on seismic geotechnical hazard. The Japanese Society of Soil Mechanics and Foundation Engineering 47–70.
Xie HT (2012) Fault bayesian network based method for risk assessment of slope collapse accident. Journal of Safety and Environment 12(6): 237–241. (In Chinese)
Yazdi M (2019) A review paper to examine the validity of Bayesian network to build rational consensus in subjective probabilistic failure analysis. International Journal of System Assurance Engineering and Management 10(1): 1–18. https://doi.org/10.1007/s13198-018-00757-7
Zadeh LA (1965) Fuzzy sets*. Information and Control 8(3): 338–353. https://doi.org/10.1016/S0019-9958(65)90241-X
Zarei E, Khakzad N, Cozzani V, et al. (2019a) Safety analysis of process systems using Fuzzy Bayesian Network (FBN). Journal of Loss Prevention in the Process Industries 57: 142–155. https://doi.org/10.1016/j.jlp.2018.10.011
Zarei E, Yazdi M, Abbassi R, et al. (2019b) A hybrid model for human factor analysis in process accidents: FBN-HFACS. Journal of Loss Prevention in the Process Industries 57: 142–155. https://doi.org/10.1016/j.jlp.2018.11.015
Zhang GF, Cai YX, Zheng Z, et al. (2016) Integration of the statistical index method and the analytic hierarchy process technique for the assessment of landslide susceptibility in Huizhou, China. Catena 142: 233–244. https://doi.org/10.1016/j.catena.2016.03.028
Zheng XZ, Li HF, Wei XW, et al.(2013) Application of Bayesian network in probability assessment of risk for rocky slope excavation. Water Resources & Power 31(7): 130–132. (In Chinese)
Zhou XP, Cheng H (2015) The long-term stability analysis of 3D creeping slopes using the displacement-based rigorous limit equilibrium method. Engineering Geology 195: 292–300. https://doi.org/10.1016/j.enggeo.2015.06.002
Acknowledgments
This research was supported by the National Key Research and Development Program (Grant No. 2017YFC0504901), Sichuan Traffic Construction Science and Technology Project(Grant No. 2016B2-2) and Doctoral Innovation Fund Program of Southwest Jiaotong University(Grant No. D-CX201804). And we are grateful to the anonymous reviewers and editors for their valuable comments on the earlier version of the manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liu, Y., Zhang, Jj., Zhu, Ch. et al. Fuzzy-support vector machine geotechnical risk analysis method based on Bayesian network. J. Mt. Sci. 16, 1975–1985 (2019). https://doi.org/10.1007/s11629-018-5358-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11629-018-5358-7