Table 5.

Comparison with state-of-the-art ensemble learning techniques applied to the WISDM and Hexoskin datasets.

Dataset	Methods	F1-Score	Precison	Recall
WISDM	The proposed method	0.77 ± 0.07	0.77 ± 0.07	0.77 ± 0.07
	Ensemble (DT-LR-MLP) [38]	0.73 ± 0.11	0.73 ± 0.11	0.73 ± 0.11
	Adaboost [61]	0.46 ± 0.13	0.46 ± 0.13	0.46 ± 0.13
	Random Forest [60]	0.72 ± 0.11	0.72 ± 0.11	0.72 ± 0.11
Hexoskin	The proposed method	0.85 ± 0.12	0.85 ± 0.12	0.85 ± 0.12
	Ensemble (DT-LR-MLP) [38]	0.79± 0.14	0.79± 0.14	0.79± 0.14
	Adaboost [61]	0.49 ± 0.11	0.49 ± 0.11	0.49 ± 0.11
	Random Forest [60]	0.81 ± 0.14	0.81 ± 0.14	0.81 ± 0.14