Multiobjective Genetic Algorithm and Convolutional Neural Network Based COVID-19 Identification in Chest X-Ray Images

Table 1

Training analysis of the COVID-19 identification models by utilizing confusion matrix-based performance metrics when training to testing ratio is 60 : 40.

Model	Accuracy	F-measure	Specificity	Sensitivity	AUC
SVM	0.872881	0.871186	0.871404	0.872666	0.872034
ANFIS	0.884746	0.883051	0.883249	0.868455	0.883898
CNN	0.894661	0.894915	0.895093	0.896435	0.895763
AlexNet	0.908475	0.906678	0.906937	0.908319	0.907627
ResNet-34	0.920339	0.918644	0.918782	0.920204	0.919492
GoogLeNet	0.932203	0.930508	0.930626	0.932088	0.931356
VGG-16	0.944068	0.942373	0.942747	0.943973	0.947322
ResNet-50	0.955932	0.954237	0.954315	0.955857	0.955085
Xception	0.967797	0.966102	0.966159	0.967742	0.966949
DenseNet201	0.979661	0.977966	0.978003	0.979626	0.978814
Proposed model	0.991525	0.989831	0.989848	0.991511	0.990678