Prediction of Rockburst Intensity Grade in Deep Underground Excavation Using Adaptive Boosting Classifier

Table 3

Hyperparameter optimization results.

Algorithm	Hyperparameter	Explanation	Optimal value/function
AdaBoost	Number of estimators	Number of trees	0.5
	Learning rate	It determines to what extent the newly acquired information will override the old information	0.75
	Boosting algorithm	Updates base estimator’s weight with probability estimates or classification results	SAMME.R
	Regression loss function	Linear/square/exponential	Exponential