Diagnosis of COVID-19 Disease in Chest CT-Scan Images Based on Combination of Low-Level Texture Analysis and MobileNetV2 Features

Table 1

Performance evaluation results of the proposed approach in terms of accuracy (%) and precision (%).

Distance measure	Classifier
	Measure	3-NN	5-NN	7-NN	Random forest (trees = 100)	Random forest (trees = 150)	Naïve Bayes
Euclidean	Accuracy	87.02	90.02	89.49	86.88	84.93	80.17
	Precison	88.27	90.54	89.92	86.77	85.64	80.67
Cosine	Accuracy	88.23	91.61	91.27	86.38	85.26	81.29
	Precison	88.65	91.79	91.18	86.89	85.17	82.04
Log-likelihood	Accuracy	88.68	91.09	90.56	87.01	85.87	82.37
	Precison	89.04	91.82	90.77	87.33	85.94	82.65