TABLE 3. Comparison of Classification Accuracy Obtained by Our Proposed Approach (Method 3: VGG16) Compared to the Classification Accuracy Obtained by the Different Existing Studies.

Cases	Authors	Year	Method	Results
				Accuracy (%)	Sensitivity (%)	Specificity (%)
A_E	[10]	2011	Extreme learning machine (ELM)	96.50	92.50	96.00
A_E	[2]	2016	SVM	97.25	94.50	100.00
A_E	[37]	2017	ANN and LNDP	99.82	99.90	99.75
A_E	[7]	2018	Deep Pyramidal 1D-CNN	100.00	–	–
A_E	[8]	2019	ESD-LSTM	100.00	100.00	100.00
A_E	[38]	2019	CNN and CWT	99.50	99.00	100.00
A_E	[6]	2020	1D-CNN	99.52	–	–
A_E	–	–	Proposed FT-VGG16 and CWT	99.38	100.00	98.75
B_E	[37]	2017	ANN and LNDP	99.25	99.10	99.40
B_E	[7]	2018	Deep Pyramidal 1D-CNN	99.80	–	–
B_E	[38]	2019	CNN and CWT	99.50	100.00	100.00
B_E	[6]	2020	1D-CNN	99.11	–	–
B_E	–	–	Proposed FT-VGG16 and CWT	100.00	100.00	100.00
C_E	[2]	2016	SVM	96.00	95.83	96.15
C_E	[37]	2017	ANN and 1D-LGP	99.10	98.75	99.45
C_E	[7]	2018	Deep Pyramidal 1D-CNN	99.10	–	–
C_E	[38]	2019	CNN and CWT	98.50	98.01	98.98
C_E	[6]	2020	1D-CNN	98.02	–	–
C_E	–	–	Proposed FT-VGG16 and CWT	99.69	99.38	100.00
D_E	[37]	2017	ANN and 1D-LGP	99.07	98.82	99.32
D_E	[7]	2018	Deep Pyramidal 1D-CNN	99.40	–	–
D_E	[38]	2019	CNN and CWT	98.50	98.01	98.98
D_E	[6]	2020	1D-CNN	97.63	–	–
D_E	–	–	Proposed FT-VGG16 and CWT	98.44	97.50	99.38
AB_E	[7]	2018	Deep Pyramidal 1D-CNN	99.80	–	–
AB_E	[6]	2020	1D-CNN	99.38	–	–
AB_E	–	–	Proposed FT-VGG16 and CWT	100.00	100.00	100.00
AC_E	[6]	2020	1D-CNN	99.03	–	–
AC_E	–	–	Proposed FT-VGG16 and CWT	99.38	98.75	100.00
AD_E	[6]	2020	1D-CNN	98.50	–	–
AD_E	–	–	Proposed FT-VGG16 and CWT	98.13	97.50	98.75
BC_E	[7]	2018	Deep Pyramidal 1D-CNN	99.50	–	–
BC_E	[6]	2020	1D-CNN	98.68	–	–
BC_E	–	–	Proposed FT-VGG16 and CWT	100.00	100.00	100.00
BD_E	[6]	2020	1D-CNN	97.83	–	–
BD_E	–	–	Proposed FT-VGG16 and CWT	98.44	98.75	98.13
CD_E	[11]	2017	Random forest and correletion based feature selection	98.67	98.70	98.70
CD_E	[37]	2017	ANN and LNDP	98.88	97.05	99.80
CD_E	[6]	2020	1D-CNN	98.03	–	–
CD_E	–	–	Proposed FT-VGG16 and CWT	99.38	98.75	100.00
ABC_E	[7]	2018	Deep Pyramidal 1D-CNN	99.97	–	–
ABC_E	[6]	2020	1D-CNN	98.89	–	–
ABC_E	–	–	Proposed FT-VGG16 and CWT	100.00	100.00	100.00
ABD_E	[6]	2020	1D-CNN	98.52	–	–
ABD_E	–	–	Proposed FT-VGG16 and CWT	98.46	98.75	98.18
ACD_E	[11]	2017	Random forest and correletion based feature selection	98.50	98.50	98.50
ACD_E	[7]	2018	Deep Pyramidal 1D-CNN	99.80	–	–
ACD_E	–	–	Proposed FT-VGG16 and CWT	98.46	97.50	99.39
BCD_E	[11]	2017	Random forest and correletion based feature selection	97.50	97.50	97.50
BCD_E	[6]	2020	1D-CNN	98.36	–	–
BCD_E	–	–	Proposed FT-VGG16 and CWT	98.46	98.75	98.18
ABCD_E	[11]	2017	Random forest and correletion based feature selection	97.40	97.40	97.50
ABCD_E	[37]	2017	ANN and LNDP	98.72	98.30	98.82
ABCD_E	[7]	2018	Deep Pyramidal 1D-CNN	99.70	–	–
ABCD_E	[8]	2019	ESD-LSTM	100.00	100.00	100.00
ABCD_E	[6]	2020	1D-CNN	98.76	–	–
ABCD_E	–	–	Proposed FT-VGG16 and CWT	100.00	100.00	100.00