Comparison of Machine Learning Techniques for the Prediction of Compressive Strength of Concrete

Algorithm 1: Summary of DT model architecture for classification [39].

n = 33
node), split, n, deviance, yval
	∗ denotes terminal node
1)	root 33 925.23300 54.05455
2)	56 days compressive strength < 49.74 11 59.08462 47.84727 ∗
3)	56 days compressive strength >= 49.74 22 230.39950 57.15818∗
6)	28 days compressive strength < 48.895 11 13.79209 54.32091 ∗
7)	28 days compressive strength >= 48.895 11 39.50487 59.99545 ∗
Regression tree:
rpart(formula = 91 days compressive strength ∼ ., data = crs$dataset[crs$train, c(crs$input, crs$target)], method = “anova”, parms = list(split = “information”), control = rpart.control(usesurrogate = 0, maxsurrogate = 0))

Algorithm 1: Summary of DT model architecture for classification [39].