Fig. 8

Model testing performance metrics: testing accuracy and area under receiver operating characteristic curve. Testing accuracy (above) and ROC AUC (below) for the 44 tests. The four different symbol shapes/colors correspond to the four networks. Solid and hollow symbols represent non-augmented and augmented test sets, respectively. Error bars are binomial exact 95% confidence intervals. Horizontal axes labels stand for different ways of applying augmentation: A = Make three sets, then augment validation; B = Make three sets; C = Make three sets, then augment training; D = Make three sets, then augment both training and validation; E = Separate test set, augment the rest, then make two other sets; F = Augment all before making three sets. CI = confidence interval; ROC AUC = area under the receiver operating characteristic curve