Prediction of Ultimate Capacity of Laterally Loaded Piles in Clay: A Relevance Vector Machine Approach

Samui, Pijush and Bhattacharya, Gautam and Choudhury, Deepankar (2009) Prediction of Ultimate Capacity of Laterally Loaded Piles in Clay: A Relevance Vector Machine Approach. In: 12th Online World Conference on Soft Computing in Industrial Applications (WFSC 12), OCT 16-26, 2007, England.

PDF fulltext.pdf31.pdf - Published Version Restricted to Registered users only Download (320kB) | Request a copy

Abstract

This study investigates the potential of Relevance Vector Machine (RVM)-based approach to predict the ultimate capacity of laterally loaded pile in clay. RVM is a sparse approximate Bayesian kernel method. It can be seen as a probabilistic version of support vector machine. It provides much sparser regressors without compromising performance, and kernel bases give a small but worthwhile improvement in performance. RVM model outperforms the two other models based on root-mean-square-error (RMSE) and mean-absolute-error (MAE) performance criteria. It also stimates the prediction variance. The results presented in this paper clearly highlight that the RVM is a robust tool for prediction Of ultimate capacity of laterally loaded piles in clay.

Item Type:	Conference Paper
Publisher:	Springer
Additional Information:	Copyright of this publications belongs to Springer.
Keywords:	pile;clay;relevance vector machine;ultimate capacity.
Department/Centre:	Division of Mechanical Sciences > Civil Engineering
Date Deposited:	09 Feb 2010 11:23
Last Modified:	19 Sep 2010 05:31
URI:	http://eprints.iisc.ac.in/id/eprint/19986

Actions (login required)

View Item