Table 7 Comparative analysis with previous works.

Classification models	Accuracy	Precision	Sensitivity	Specificity	F1 Score	Error rate	Computational time (min)
PCA- GA-SVM—Zhang et al.¹⁷	0.670	0.669	0.769	0.555	0.715	0.329	2.01
Non-invasive approach—Zhang ⁴³	0.763	0.691	0.728	0.607	0.774	0.317	3.46
Greedy Snake Algorithm—Naveed and Geetha ⁴⁴	0.801	0.760	0.803	0.669	0.792	0.258	3.19
ResNet 34—Wang et al. [²⁷]	0.875	0.890	0.907	0.826	0.898	0.125	3.24
SqueezeNet—Wu et al.²⁹	0.856	0.865	0.899	0.793	0.882	0.143	3.31
AlexNet—Huo et al.¹⁸	0.863	0.870	0.905	0.801	0.887	0.137	3.27
Random forest algorithm—Xiang et al.⁴⁵	0.877	0.881	0.893	0.829	0.890	0.133	3.07
Stacking model—Li et al.⁴⁶	0.892	0.894	0.912	0.850	0. 917	0.119	3.61
GA_XGBT approach—Li et al.⁴⁷	0.906	0.911	0.899	0.872	0.934	0.103	3.57
SVM classifiers—Sagayaraj et al.⁴⁸	0.927	0.932	0.945	0.917	0.955	0.085	3.41
Proposed ResNet50-Deep RBFNN model	0.984	0.989	0.991	0.943	0.990	0.016	3.50

Quick links

Search