Fig. 8

Receiver Operating Characteristic Curve for every class. a Using training set, b validation set, and c test set Dataset. The dotted line (data1) shows a worthless test that has a 50/50 chance of correctly detecting it
Receiver Operating Characteristic Curve for every class. a Using training set, b validation set, and c test set Dataset. The dotted line (data1) shows a worthless test that has a 50/50 chance of correctly detecting it