Your browser version is outdated. We recommend that you update your browser to the latest version.

Manuscript Title: Utilization of Multivariate Adaptive Regression Splines (MARS) for Prediction of Pull Out Capacity of Small Ground Anchor

Author : Pijush Samui, and Ishan Saini

Email :pijush.phd@gmail.com,ishansaini92@gmail.com 

Abstract: 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.

Keywords: Artificial Neural Network; Multi Adaptive Regression Spline; Pull Out Capacity, Small Ground Anchor.

 Vol 5 (1)