S2 Fig -
(a) Evaluating the optimum number of clusters: The plot displays the Calinski-Harabasz evaluation method . The optimum number of clusters is the number of cluster values that correspond to the highest Calinski-Harabasz value. In this case, the optimum number of clusters is two. (b) Range of values assessed by the Bayesian optimisation objective function to select the optimal machine learning hyperparameters for the Kernel naïve Bayes supervised learning model [77,78].