Table 4.

Hyperparameters in proposed machine learning models.

Model	Hyperparameters
RF	n_estimators = 100, *, criterion = 'entropy'
SVM	kernel = 'liniar', degree = 2, gamma = 'scale', cache_size = 100, decision_function_shape = 'ovo'
AD	n_estimators = 100 algorithm = 'SAMME', random_state = 40
KNN	n_neighbors = 1, *, weights = 'uniform', algorithm = ‘kd_tree’, leaf_size = 20, p = 2, metric = 'euclidean'
DT	criterion = 'entropy', splitter = 'best', max_depth = 100, ccp_alpha = 0.0
GNB	priors = None, var_smoothing = 1e-09

Where the hyperparameters are not explicitly defined, they are considerate as default.