Modeling of SPT Seismic Liquefaction Data Using Minimax Probability Machine

被引：4

作者：

Samui P. ^{[1
]}

Hariharan R. ^{[2
]}

机构：

[1] Centre for Disaster Mitigation and Management, VIT University, Vellore

[2] Department of Computer Science, Annai Mira College of Engineering and Technology, Arapakam, Vellore

来源：

Geotechnical and Geological Engineering | 2014年 / 32卷 / 3期

关键词：

Classification; Liquefaction; Minimax Probability Machine; Standard Penetration Test;

D O I：

10.1007/s10706-014-9749-4

中图分类号：

学科分类号：

摘要：

The determination of seismic liquefaction potential of soil is an important task in geotechnical engineering. This article uses Minimax Probability Machine (MPM) for determination of seismic liquefaction potential of soil based on Standard Penetration Test value (N). MPM is developed based on the use of hyperplanes. It is a discriminant classifier. This study uses MPM as a classification tool. MPM uses the database collected from Chi-Chi earthquake. Two models (MODEL I and MODEL II) have been developed. MODEL I uses Cyclic Stress Ratio and N as input variables. Peck Ground Acceleration and N have been adopted as inputs for MODEL II. The performance of MODEL I and MODEL II are 97.67 and 96.51 % respectively. The performance of MODEL II is 94.11 % for the global data. The developed MPM shows good generalization capability. The results show that the developed MPM has ability for determination of seismic liquefaction potential of soil. © 2014 Springer International Publishing Switzerland.

引用

页码：699 / 703

页数：4

共 26 条

[1]

Andrus R.D., Stokoe K.H., Liquefaction resistance of soils from shear wave velocity, J Geotech Geoenviron Eng ASCE, 126, 11, pp. 1015-1025, (2000)

[2]

Goh A.T.C., Seismic liquefaction potential assessed by neural network, J Geotech Geoenviron Eng, 120, 9, pp. 1467-1480, (1994)

[3]

Goh A.T.C., Neural-network modeling of CPT seismic liquefaction data, J Geotech Eng, 122, 1, pp. 70-73, (1996)

[4]

Goh A.T.C., Goh S.H., Support vector machines: their use in geotechnical engineering as illustrated using seismic liquefaction data, Comput Geotech, 34, 5, pp. 410-421, (2007)

[5]

Hwang J.H., Yang C.W., Verification of critical cyclic strength curve by Taiwan Chi-Chi earthquake data, Soil Dyn Earthq Eng, 21, pp. 237-257, (2001)

[6]

Javadi A.A., Rezania M., Nezhad M.M., Evaluation of liquefaction induced lateral displacements using genetic programming, Comput Geotech, 33, pp. 222-233, (2006)

[7]

Kayadelen C., Soil liquefaction modeling by genetic expression programming and neuro-fuzzy, Expert Syst Appl, 38, 4, pp. 4080-4087, (2011)

[8]

Kecman V., Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models, (2001)

[9]

Lanckriet G., El Ghaoui L., Jordan M., Robust novelty detection with single-class MPM, Advances in Neural Information Processing Systems 15, (2003)

[10]

Najjar Y.M., Ali H.E., CPT-based liquefaction potential assessment: a neuronet approach, Geotech Spec Publ ASCE, 1, pp. 542-553, (1998)

← 1 2 3 →