Support Vector Machine for Regression Model of Soft Soil Foundation Settlement
Guang Zhang, Gabriel Xiao-Guang Yue, Jingxi Chen, Juan Yang, Jing Wang · International Journal of Applied Mathematics & Statistics/International journal of applied mathematics and statistics · 2014
In order to predict the soft soil foundation settlement, the basic concepts of soil foundation settlement are discussed; the related research situation and research methods are analyzed; soft soil foundation settlement prediction method based on support vector machine for regression has been put forward. First, relevant data are selected from the engineering example; second, test set and prediction set are generated; third, support vector machine for regression model and BP neural network model are created and trained by using Matlab; finally, experiment simulation has been finished. The results show that, support vector machine for regression is an effective method for soft soil foundation settlement prediction, and the performance of support vector regression is better than BP neural network model.