Employment of Ensemble Machine Learning Methods for Human Activity Recognition

Table 4

Performance metrics of trained 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
SVC	0.9931	0.9931	0.9931	0.9932	0.9931	0.9931	0.9931	0.9931	0.9931	0.9931	0.9775
LSVC	0.9854	0.9854	0.9854	0.9854	0.9854	0.9854	0.9854	0.9854	0.9854	0.9854	0.972
NuSVC	0.9923	0.9923	0.9923	0.9923	0.9923	0.9923	0.9923	0.9923	0.9923	0.9923	0.9793
AdB	0.8195	0.8195	0.8226	0.8227	0.8195	0.8194	0.8196	0.8195	0.8199	0.8200	0.7469
XGB	0.9786	0.9786	0.9785	0.9785	0.9786	0.9786	0.9786	0.9786	0.9785	0.9785	0.9517
LGBM	0.9859	0.9859	0.9858	0.9858	0.9859	0.9859	0.9859	0.9859	0.9858	0.9858	0.9606
GB	0.9689	0.9689	0.9702	0.9691	0.9689	0.9699	0.9689	0.9689	0.9699	0.9689	0.9187
ETC	0.9709	0.9709	0.9709	0.9709	0.9717	0.9717	0.9717	0.9709	0.9707	0.9708	0.9411