Table 3.

Performance Comparison with Supervised Learning Approaches in the Benchmark, Category 3.

		N vs. AF	N vs. I-AVB	N vs. LBBB	N vs. RBBB	N vs. PAC	N vs. PVC	N vs. STD	N vs. STE
GADF + MPCA + Adaboost	Accuracy	0.9955	0.9994	0.9582	0.9983	0.9973	0.9978	0.9966	0.9987
	AUROC	0.9971	0.9995	0.9851	0.9994	0.9966	0.9973	0.9966	0.9969
	F-score	0.9959	0.9993	0.8440	0.9987	0.9964	0.9973	0.9965	0.9953
GADF + MPCA + SVM	Accuracy	0.9406	0.9323	0.9867	0.9618	0.9599	0.9651	0.9799	0.9509
	AUROC	0.9928	0.9972	0.9976	0.9944	0.9970	0.9934	0.9992	0.9850
	F-score	0.9442	0.9272	0.9552	0.9716	0.9478	0.9572	0.9791	0.8451
GADF + MPCA + D-SVDD (proposed)	Accuracy	0.9752	0.9754	0.9733	0.9981	0.9666	0.9333	0.9570	0.9821
	AUROC	0.9849	0.9973	0.9598	0.9999	0.9860	0.9647	0.9804	0.9964
	F-score	0.9771	0.9712	0.9062	0.9986	0.9541	0.9231	0.9550	0.9394