TABLE 4.

Test results for the remaining participant after training using data for the other seven participants.

	DT	RF	ADB	LR	MLP	SVM	KNN	LDA	LR-CNN	CNN	LSTM
Participant 1	0.759	0.825	0.828	0.793	0.856	0.829	0.806	0.841	0.923	0.898	0.886
Participant 2	0.737	0.836	0.828	0.813	0.863	0.837	0.819	0.824	0.932	0.883	0.877
Participant 3	0.742	0.831	0.829	0.798	0.856	0.835	0.816	0.823	0.919	0.869	0.855
Participant 4	0.716	0.822	0.826	0.816	0.853	0.840	0.814	0.854	0.932	0.889	0.883
Participant 5	0.732	0.836	0.833	0.822	0.833	0.833	0.811	0.821	0.917	0.796	0.811
Participant 6	0.721	0.820	0.827	0.821	0.843	0.836	0.810	0.826	0.926	0.913	0.878
Participant 7	0.727	0.843	0.826	0.816	0.852	0.842	0.812	0.822	0.862	0.877	0.858
Participant 8	0.712	0.832	0.829	0.794	0.829	0.828	0.821	0.829	0.921	0.881	0.862

DT, decision tree; RF, random forest; ADB, adboost; LR, logistic regression; MLP, multilayer perceptron; SVM, support vector machine; KNN, k-nearest neighbor; LDA, linear discriminant analysis; LR-CNN, logistic regression and convolutional neural network; CNN, convolutional neural network; LSTM, long short-term memory.