Table 3 Optimum hyperparameters used in the studied models.

SVM

Penalty parameter of the error term (C)

10

Kernel coefficient for Gaussian function (γ)

1

Tolerance for stopping criterion (ϵ)

Default (~ 0.001)

RF

The minimum number of samples required to split an internal node (min_samples_split)

2

Minimum number of samples at leaf node (min_samples_leaf)

1

Number of trees in the forest

20

Maximum number of features to consider for best split

6

ANN

Number of hidden layers

2

Number of nodes in the first hidden layer

100

Number of nodes in the second hidden layer

50

Activation function

Default (‘relu’)

LR

Maximum Number of Iterations (max_iter)

1000

Regularization type

Default (‘12’)

KNN

Number of nearest neighbors (ηneighbors)

5

Algorithms to compute nearest neighbors

Default (‘auto’)

DT

Maximum depth of tree (Max_ Depth)

12

Minimum number of samples at a leaf node (min_samples_leaf)

1

Minimum samples required to split an internal node (min_samples_split)

2