Prediction of compaction parameters of coarse grained soil using multivariate adaptive regression splines (MARS)

Khuntia, Sunil, Mujtaba, Hassan, Patra, Chittaranjan, Farooq, Khalid, Sivakugan, Nagaratnam, and Das, Braja M. (2015) Prediction of compaction parameters of coarse grained soil using multivariate adaptive regression splines (MARS). International Journal of Geotechnical Engineering, 9 (1). pp. 79-88.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website: http://dx.doi.org/10.1179/1939787914Y.00...
 
4
1


Abstract

In this paper, different models are developed to estimate the compaction parameters of sandy soil using artificial neural network (ANN), least square support vector machine (LS-SVM), and multivariate adaptive regression splines (MARS). The experimental database of Mujtaba et al. (2013) is used for the analysis. The above techniques have been used to improve the regression results. The model equations are established and compared with the regression equation. The MARS model results found to be more accurate and it improved the coefficient of determination to more acceptable levels of 0·88 and 0·81 for the prediction of compaction parameters maximum dry density (γdmax) and optimum moisture content (ωopt), respectively. The results showed that variation between experimental and predicted values of γdmax is within ±4% and that of the ωopt is within ±13% at 95% confidence level. Sensitivity analysis is carried out to evaluate the parameters affecting the output.

Item ID: 37009
Item Type: Article (Research - C1)
ISSN: 1939-7879
Keywords: ANN, LS-SVM, MARS, compaction energy, grain size
Date Deposited: 17 Jun 2015 02:00
FoR Codes: 09 ENGINEERING > 0905 Civil Engineering > 090501 Civil Geotechnical Engineering @ 100%
SEO Codes: 87 CONSTRUCTION > 8702 Construction Design > 870201 Civil Construction Design @ 100%
Downloads: Total: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page