Samui, Pijush and Sitharam, TG and Kurup, Pradeep U (2008) OCR Prediction Using Support Vector Machine Based on Piezocone Data. In: Journal of Geotechnical and Geoenvironmental Engineering, 134 (6). pp. 894-898.
GetPDFServlet1.pdf - Published Version
Restricted to Registered users only
Download (91Kb) | Request a copy
The determination of the overconsolidation ratio (OCR) of clay deposits is an important task in geotechnical engineering practice. This paper examines the potential of a support vector machine (SVM) for predicting the OCR of clays from piezocone penetration test data. SVM is a statistical learning theory based on a structural risk minimization principle that minimizes both error and weight terms. The five input variables used for the SVM model for prediction of OCR are the corrected cone resistance (qt), vertical total stress (sigmav), hydrostatic pore pressure (u0), pore pressure at the cone tip (u1), and the pore pressure just above the cone base (u2). Sensitivity analysis has been performed to investigate the relative importance of each of the input parameters. From the sensitivity analysis, it is clear that qt=primary in situ data influenced by OCR followed by sigmav, u0, u2, and u1. Comparison between SVM and some of the traditional interpretation methods is also presented. The results of this study have shown that the SVM approach has the potential to be a practical tool for determination of OCR.
|Item Type:||Journal Article|
|Additional Information:||Copyright of this article belongs to American Society of Civil Engineers.|
|Department/Centre:||Division of Mechanical Sciences > Civil Engineering|
|Date Deposited:||25 Mar 2010 10:58|
|Last Modified:||19 Sep 2010 05:58|
Actions (login required)