Table 2.

Performance of tree-based models

Method	Classification			Regression
	AUC	MCC	BA	MAE	MSE	R2
RF	0.996 (0.006)	0.949 (0.048)	0.961 (0.004)	0.577 (0.077)	0.587 (0.142)	0.787 (0.073)
ExtraTrees	0.996 (0.006)	0.957 (0.041)	0.967 (0.030)	0.560 (0.073)	0.566 (0.138)	0.792 (0.072)

Reported is the mean performance (standard deviation) over 10 activity classes for decision tree-based classification and regression models using different metrics. For classification models, area under the ROC curve (AUC), balanced accuracy (BA), and Matthew’s correlation coefficient (MCC) values are given. For regression models, the mean absolute error (MAE), mean squared error (MSE), and coefficient of determination (R²) are reported