Determination of Compression Index for Marine Clay: A Relevance Vector Machine Approach

Abstract

This study investigates the feasibility of Relevance Vector Machine (RVM) for determination of Compression Index (C-c) of marine clay. RVM allows computation of the prediction intervals taking into account uncertainties of both the parameters and the data. It provides much sparser regressors without compromising performance, and kernel bases give a small but worthwhile improvement in performance. The input parameters of RVM are natural water content (omega(n)), liquid limit (omega(1)), initial void ratio (e(0)), and dry density (gamma(d)). Equations have also been developed for the prediction of C-c of marine clay. The developer RVM model gives variance of the predicted C-c. A comparative study has also been done between the developed RVM and regression models. The results indicate that RVM is a useful technique for predicting C-c of marine clay.