A Multivariate Adaptive Regression Spline Approach for Prediction of Maximum Shear Modulus and Minimum Damping Ratio

Pijush Samui, D. P. Kothari

Engineering Journal · 2012 · 17 citations · 20 references

DOIFull text

Open access

Concepts

Abstract

This study uses Multivariate Adaptive Regression Spline (MARS) for determination Maximum Shear Modulus (Gmax) and Minimum Damping Ratio (min) of synthetic reinforced soil. MARS employs confining pressure (, psi), rubber (r, %) and sand (s, %) as input variables. The output of the MARS is Gmax and min. The developed MARS gives equations for determination of Gmax and min. The results of MARS have been compared with the adaptive neuro-fuzzy inference system (ANFIS), multi-layer perceptron (MLP) and multiple regression analysis method (MRM). A sensitivity analysis has been also carried out to determine the effect of each input variable on Gmax and min. This study shows that the developed MARS is a robust model for prediction of Gmax and min.

References

20