Prediction of COVID-19 with Computed Tomography Images using Hybrid Learning Techniques

Table 13

Confusion matrix and classification report for proposed work, Inception V3 for feature extraction, and various machine learning models for classification.

Confusion matrix						Classification report
Models	Category	COVID-19	CAP	Normal	Total	Category	Precision	Recall	F1Score	Specificity
IncpetionV3+SVM	COVID-19	103	4	4	111	COVID-19	0.93	0.93	0.93	0.95
	CAP	4	102	5	111	CAP	0.92	0.93	0.92	0.96
	Normal	4	4	103	111	Normal	0.93	0.92	0.94	0.96
	Total	111	110	11	333	Average	0.93	0.93	0.93	0.96
Inception V3 + Random Forest	COVID-19	102	5	4	111	COVID-19	0.92	0.92	0.92	0.96
	CAP	4	103	4	111	CAP	0.91	0.91	0.91	0.96
	Normal	5	5	101	111	Normal	0.91	0.92	0.91	0.95
	Total	111	113	109	333	Average	0.91	0.92	0.92	0.96
InceptionV3+Decision Tree	COVID-19	101	5	5	111	COVID-19	0.91	0.91	0.91	0.95
	CAP	5	101	5	111	CAP	0.91	0.90	0.91	0.95
	Normal	5	6	100	111	Normal	0.90	0.90	0.90	0.95
	Total	111	112	110	333	Average	0.91	0.90	0.91	0.95
InceptionV3+Naive Bayes	COVID-19	96	9	6	111	COVID-19	0.86	0.86	0.86	0.93
	CAP	6	96	9	111	CAP	0.86	0.85	0.86	0.93
	Normal	7	9	95	111	Normal	0.89	0.88	0.88	0.93
	Total	108	112	107	333	Average	0.87	0.87	0.87	0.93
InceptionV3+KNN	COVID-19	101	5	5	111	COVID-19	0.91	0.92	0.91	0.95
	CAP	4	102	5	111	CAP	0.92	0.91	0.92	0.95
	Normal	5	5	101	111	Normal	0.96	0.91	0.91	0.95
	Total	110	112	111	333	Average	0.91	0.92	0.92	0.95