Vector machine techniques for modeling of seismic liquefaction data

Abstract

This article employs three soft computing techniques, Support Vector Machine (SVM); Least Square Support Vector Machine (LSSVM) and Relevance Vector Machine (RVM), for prediction of liquefaction susceptibility of soil. SVM and LSSVM are based on the structural risk minimization (SRM) principle which seeks to minimize an upper bound of the generalization error consisting of the sum of the training error and a confidence interval. RVM is a sparse Bayesian kernel machine. SVM, LSSVM and RVM have been used as classification tools. The developed SVM, LSSVM and RVM give equations for prediction of liquefaction susceptibility of soil. A comparative study has been carried out between the developed SVM, LSSVM and RVM models. The results from this article indicate that the developed SVM gives the best performance for prediction of liquefaction susceptibility of soil.

Keywords

• Support Vector Machine
• Least Square Support Vector Machine
• Relevance Vector Machine
• Liquefaction
• Probability