Table 3.

Cross-validated average performance metrics of classic ML models on each 20 top-ranked features dataset.

Feature Extractor	Best model	Accuracy	Precision	Recall	F1-score
MobileNetV3-Small	Linear SVM	0.968	0.970	0.962	0.965
MobileNetV1	RBF SVM	0.958	0.955	0.936	0.944
MobileNetV3-Large	RFC	0.935	0.934	0.923	0.925
MobileNetV2	Linear SVM	0.898	0.905	0.859	0.874

Four models acting as feature extractors were tested together with five different classical machine learning algorithms acting as classifiers. The accuracy, precision, recall, and f1-score for all hybrid models, on the 20 top-ranked features dataset, are reported below.