Ensemble Deep Learning for Biomedical Time Series Classification

Table 5

Performance comparison of different classification models.

Dataset	Model	Sp (%)	Se (%)	GMean (%)	Acc (%)	AUC	NPV = 95%
							TPR (%)	FPR (%)
DS1	Explicit [6]	88.84	76.95	82.68	85.41	0.9034	63.322	8.217
	Explicit	89.85	76.81	83.07	86.09	0.9123	71.111	9.227
	Implicit	92.58	73.52	82.50	87.08	0.9149	71.202	9.239
	Fusion	91.81	74.96	82.96	86.95	0.9172	74.063	9.611
DS2	Explicit [6]	88.63	79.55	83.97	85.99	0.9174	74.389	9.558
	Explicit	89.92	80.05	84.84	87.05	0.9272	78.879	10.135
	Implicit	92.45	76.40	84.04	87.78	0.9318	80.983	10.405
	Fusion	91.47	78.27	84.61	87.64	0.9324	81.468	10.468
DS3	Explicit [6]	86.58	77.69	82.01	84.03	0.8972	65.597	8.599
	Explicit	87.81	78.03	82.77	85.01	0.9074	72.506	9.505
	Implicit	90.23	74.88	82.20	85.84	0.9112	74.256	9.735
	Fusion	89.57	76.29	82.66	85.76	0.9122	74.819	9.809
DS4	Explicit [6]	82.75	84.81	83.77	83.91	0.9096	0.091	0.011
	Explicit	83.67	85.09	84.38	84.47	0.9153	0.051	0.004
	Implicit	88.15	82.30	85.18	84.85	0.9192	0	0
	Fusion	86.64	84.18	85.40	85.25	0.9215	0.020	0.005
DS5	Explicit [6]	79.52	86.20	82.79	83.23	0.9084	0	0
	Explicit	80.70	86.64	83.62	84.00	0.9144	0	0
	Implicit	86.78	82.34	84.53	84.31	0.9135	0	0
	Fusion	84.69	84.82	84.76	84.76	0.9187	0	0
DS6	Explicit [6]	81.98	84.90	83.43	83.57	0.9101	0.025	0.003
	Explicit	82.80	85.49	84.13	84.26	0.9169	0	0
	Implicit	88.21	81.60	84.84	84.62	0.9168	0	0
	Fusion	86.31	83.81	85.05	84.96	0.9213	19.835	0.882
DS7	Explicit [6]	77.81	84.71	81.19	81.28	0.8905	0.010	0.001
	Explicit	78.60	85.17	81.82	81.90	0.8964	0	0
	Implicit	84.19	80.46	82.30	82.31	0.8943	0	0
	Fusion	82.08	83.02	82.55	82.55	0.9000	10.769	0.561
DS8	Explicit [6]	78.31	84.74	81.47	81.71	0.8913	0	0
	Explicit	79.46	85.23	82.30	82.51	0.8976	0.020	0.003
	Implicit	84.79	80.97	82.86	82.77	0.8962	0.032	0.004
	Fusion	82.69	83.32	83.00	83.02	0.9011	10.889	0.514
DS9	Explicit [6]	83.97	75.40	79.57	81.48	0.8661	1.196	0.159
	Explicit	84.62	76.04	80.22	82.13	0.8778	52.160	6.722
	Implicit	87.24	70.91	78.65	82.51	0.8733	0	0
	Fusion	86.46	73.37	79.64	82.66	0.8806	53.151	6.850

The classification models are obtained by “explicit training” and “implicit training,” respectively, and the results are based on subview prediction.