Fig. 15

Comparing the performance of the proposed hybrid stacking and voting models with the top performers from phase I experiment: (a) accuracy, (b) precision, (c) recall, (d) F1-score, (e) MCC, (f) kappa, and (g) AUC.

Comparing the performance of the proposed hybrid stacking and voting models with the top performers from phase I experiment: (a) accuracy, (b) precision, (c) recall, (d) F1-score, (e) MCC, (f) kappa, and (g) AUC.