Estimating California Bearing Ratio Using Decision Tree Regression Analysis Using Soil Index and Compaction Parameters

Keywords: California Bearing Ratio, Regression, Decision Trees, Machine Learning

Abstract

California Bearing Ratio is used as an index of soil strength and bearing capacity. In the machine learning theory, a decision tree algorithm can help us to define preferences, risks, benefits and targets. In this study, decision tree algorithm was employed for estimating California Bearing Ratio from the soil index and compaction parameters. There were seven inputs and one output in the study. In the analysis, we employed gravel, sand, fine grain, liquid limit, plastic limit, maximum dry unit weight and optimum water as inputs and California Bearing Ratio as output. The number of data was 124. In the decision tree algorithm, data were divided two for train and test groups.  And, 10-fold cross validation process was applied to data in the analysis. Consequently, fine grain values used as input in the study were carried out to be very determinative for regression analysis. Decision tree regression analysis estimation indicated strong correlation (R = 0.89) between the output and target. It has been shown that the correlation equations obtained as a result of regression analysis are in satisfactory agreement with the test results.

Downloads

Download data is not yet available.

References

S. F. Brown, “Soil mechanics in pavement engineering,” Géotechnique, vol. 46, no. 3, pp. 383–426, 1996.

B. Yildirim and O. Gunaydin, “Estimation of California bearing ratio by using soft computing systems,” Expert Syst. Appl., vol. 38, no. 5, pp. 6381–6391, May 2011.

E. Alpaydın, Introduction to Machine Learning. Cambridge, Massachusetts London England, 2004.

L. Yang, S. Liu, S. Tsoka, and L. G. Papageorgiou, “A regression tree approach using mathematical programming,” Expert Syst. Appl., vol. 78, pp. 347–357, Jul. 2017.

H. Sun and X. Hu, “Attribute selection for decision tree learning with class constraint,” Chemom. Intell. Lab. Syst., vol. 163, no. February, pp. 16–23, 2017.

M. Czajkowski and M. Kretowski, “The role of decision tree representation in regression problems - An evolutionary perspective,” Appl. Soft Comput. J., vol. 48, pp. 458–475, 2016.

B. Yildirim, “Kaliforniya Taşıma Oranının Regesyon Analizleri ve Yapay Sinir Ağları ile Belirlenmesi,” Nigde Unviersity, 2009.

T. Taskiran, “Prediction of California bearing ratio (CBR) of fine grained soils by AI methods,” Adv. Eng. Softw., vol. 41, no. 6, pp. 886–892, 2010.

M. Aytekin, Soil mechanics. Trabzon, Turkey: Academy Publishing house, 2000.

D. A. 1883-99, “Standard test method for CBR of laboratory-compacted soils,” 2003.

S. K. Das and P. Basudhar, “Prediction of residual friction angle of clay artificial neural network,” Eng. Geol., pp. 142–145, 2008.

Ş. E. Şeker, “Karar Ağacı Öğrenmesi,” pp. 1–7, 2017.

Published
2019-03-20
How to Cite
[1]
O. Gunaydin, A. Ozbeyaz, and M. Soylemez, “Estimating California Bearing Ratio Using Decision Tree Regression Analysis Using Soil Index and Compaction Parameters”, IJISAE, vol. 7, no. 1, pp. 30-33, Mar. 2019.
Section
Research Article