Table 7.

Performance comparison with different percentage Split for dataset #2

Technology	Accuracy (in %)	Sensitivity (in %)	Specificity (in %)	MCC	Precision	F1 Score	Gmean
90% training set − 10% testing set
MLP-NN	79.16	84.61	72.73	0.5795	0.7857	0.8148	0.7844
RBF-NN	80.56	77.78	83.33	0.612	0.8223	0.7999	0.8050
RNN	79.17	72.72	84.62	0.5795	0.8	0.7619	0.7844
LSTM	79.17	81.82	76.92	0.5853	0.75	0.7826	0.7933
SEFRON [Dataset#2]	85.41	82.61	88	0.7079	0.8636	0.8445	0.8526
85% training set − 15% testing set
MLP-NN	77.78	73.68	82.35	0.5604	0.8235	0.7778	0.7789
RBF-NN	83.33	92.30	72.72	0.6693	0.8	0.8571	0.7844
RNN	72.22	66.67	77.78	0.4472	0.75	0.7059	0.72
LSTM	80.56	77.78	83.33	0.612	0.823	0.799	0.805
SEFRON [Dataset#2]	86.61	84.21	88.23	0.7233	0.1389	0.8649	0.8619
80% training set − 20% testing set
MLP-NN	81.25	78.26	84	0.6242	0.8181	0.8	0.8108
RBF-NN	87.5	82.61	92	0.7513	0.9048	0.8260	0.8636
RNN	81.25	83.33	79.17	0.6255	0.8	0.8163	0.8122
LSTM	81.25	87.5	75	0.6299	0.7778	0.8235	0.81
SEFRON [Dataset#2]	89.58	91.3	88	0.7923	0.875	0.8936	0.8963
70% training set − 30% testing set
MLP-NN	83.33	77.78	88.89	0.6708	0.875	0.823	0.8314
RBF-NN	84.72	77.78	91.68	0.7012	0.9032	0.8358	0.8443
RNN	87.5	89.19	85.71	0.7499	0.8684	0.88	0.8743
LSTM	83.33	89.19	77.14	0.6696	0.8049	0.8461	0.8295
SEFRON [Dataset#2]	88.89	89.47	88.23	0.7771	0.8947	0.8947	0.8885