Regression Analysis of Soil Compaction Parameters Using Support Vector Method

Abstract

Some challenging studies are experimentally applied for characterizing parameters in Proctor compactiontests. Compression of a fill is mechanically done in Compaction process. Compaction is a physical processwhich gets the soil into a dense state. Improving the shear strength and decreasing the compressibility andpermeability of the soil can be done with this physical process. Support Vector Machine (SVM) is apopular method due to its performance today. This method is commonly employed in the regressionanalysis as well as being used in the classification process. In this study, SVM was employed to predict ofcompaction parameters (maximum dry unit weight and optimum moisture content) without making anyexperiments in a soil laboratory. In the study, more than a hundred compaction data collected from thesmall dams in central Anatolia region was employed. In the study, R errors are satisfied (0.92 and 0.89) forSVM models. Consequently, the proposed regression analysis with SVM is useful for model design of theprojects in where there are limitations as financial and temporal