Employment of Ensemble Machine Learning Methods for Human Activity Recognition

Table 5

Performance metrics of trained ensemble ML models (with tuning).

Algorithm	Accuracy	Precision (micro)	Precision (macro)	Precision (weighted)	Recall (micro)	Recall (macro)	Recall (weighted)	F1-score (micro)	F1-score (macro)	F1-score (weighted)	Cross-validation score
Stacking	0.9936	0.9936	0.9936	0.9936	0.9936	0.9936	0.9936	0.9936	0.9936	0.9936	0.9793
Voting	0.9936	0.9936	0.9936	0.9936	0.9936	0.9936	0.9936	0.9936	0.9936	0.9936	0.9765
Blending	0.991	0.991	0.9910	0.9910	0.9910	0.9910	0.9910	0.9910	0.991	0.9910	-
Averaging	0.9927	0.9927	0.9927	0.9927	0.9927	0.9927	0.9927	0.9927	0.9927	0.9927	-