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

Table 10

Confusion matrix and Classification report for the proposed work, AlexNet 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
AlexNet+SVM	COVID-19	107	4	0	111	COVID-19	0.96	0.96	0.96	0.98
	CAP	1	108	2	111	CAP	0.95	0.97	0.96	0.97
	Normal	1	3	107	111	Normal	0.98	0.96	0.97	0.98
	Total	109	113	109	333	Average	0.96	0.96	0.96	0.98
AlexNet+Random Forest	COVID-19	102	5	4	111	COVID-19	0.92	0.92	0.91	0.96
	CAP	4	102	5	111	CAP	0.91	0.91	0.91	0.98
	Normal	5	4	102	111	Normal	0.91	0.91	0.91	0.98
	Total	111	111	110	333	Average	0.91	0.91	0.91	0.98
AlexNet+Decision Tree	COVID-19	104	4	3	111	COVID-19	0.94	0.94	0.94	0.97
	CAP	3	103	4	111	CAP	0.93	0.93	0.93	0.97
	Normal	4	3	104	111	Normal	0.93	0.93	0.93	0.96
	Total	111	111	111	333	Average	0.94	0.94	0.94	0.97
AlexNet+Naive Bayes	COVID-19	93	8	10	111	COVID-19	0.84	0.82	0.83	0.91
	CAP	10	93	8	111	CAP	0.84	0.83	0.83	0.90
	Normal	10	11	90	111	Normal	0.81	0.83	0.82	0.91
	Total	113	112	108	333	Average	0.83	0.83	0.83	0.91
AlexNet + KNN	COVID-19	104	3	4	111	COVID-19	0.94	0.94	0.94	0.94
	CAP	4	103	40	111	CAP	0.93	0.94	0.93	0.93
	Normal	3	4	104	111	Normal	0.94	0.93	0.93	0.94
	Total	111	110	112	333	Average	0.94	0.94	0.94	0.94