期刊名称：International Journal of Advances in Soft Computing and Its Applications
印刷版ISSN：2074-8523
出版年度：2013
卷号：5
期号：1
出版社：International Center for Scientific Research and Studies
摘要：This article examines the capability of Multivariate Adaptive Regression Spline (MARS) for prediction of pull out capacity (Q) of small ground anchor. MARS is a technique to estimate general functions of high-dimensional arguments given sparse data. The input variables of MARS are anchor diameter (Deq), embedment depth (L), average cone resistance (qc) along the embedment depth, average sleeve friction (fs) along the embedment depth and installation technique (IT). Q is the output of MARS. The results of MARS have been compared with the Artificial Neural Network (ANN) model. This study shows that the developed MARS is a robust model for determination of Q of small ground anchor
关键词：Artificial Neural Network; Multi Adaptive Regression Spline; ;Pull Out Capacity; Small Ground Anchor
