Estimating maximum shear modulus (G0) using adaptive neuro-fuzzy inference system (ANFIS)

Abstract

Realistic estimation of soil behavior is dependent on considering very small and small strain domains. Lengthy formulas proposed in the literature have limited predictive power for estimation of maximum shear modulus, G0. The aim of this study is to overcome this drawback. Theoretical aspects of fuzzy sets and adaptive neuro-fuzzy inference system (Anfis) are presented. Then, Anfis is implemented within a logical platform that adapts itself with available data to estimate and describe G0.