Support vector classifier analysis of slope

Abstract

This article examines the potential of support vector machine (SVM) in stability status prediction of slope. Support vector machine achieves good generalization ability by adopting a structural risk minimization (SRM) induction principle that aims at minimizing a bound on the generalization error of a model rather than the minimizing the error on the training data only. This study uses SVM as a classification tool. In this article, the input data for slope stability prediction consist of values of geotechnical and geometric properties of slope. The accuracy of the SVM is 100% for this problem. The developed SVM gives also an equation for prediction of status of slope. This study shows that SVM has the potential to be a useful and practical tool for prediction of slope stability. © 2013 Copyright Taylor and Francis Group, LLC.