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

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, the 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. In addition, 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.

Uzun-Kısa Süreli Bellek Ağı Kullanarak Global Güneş Işınımı Zaman Serileri Tahmini

“…Güneş ışınımı değerlerinin tahmini için önerilen LSTM algoritmasından elde edilen sonuçların performansını ve doğruluğunu karşılaştırmak amacıyla literatürde var olan bazı makine öğrenmesi algoritmaları seçilmiştir. Seçilen makine öğrenmesi algoritmaları şunlardır; Rastgele Orman Regresyon (Random Forest Regression) [24], K-En Yakın Komşu (K-Nearest Neighbor) [25], Gradyan Güçlendirme (Gradient Boosting) [26] ve Karar Ağaçları Regresyon (Decision Tree Regression) [27]. Seçilen makine öğrenmesi algoritmalarının temel parametreleri Tablo 1'de gösterilmiştir.…”