Table 4 Hyperparameters of ML models.
Models | Hyperparameter | Value |
|---|---|---|
ANN | The ith element represents the number of neurons in the ith hidden layer | (1000, 500) |
Activation function for the hidden layer | relu | |
The solver for weight optimization | adam | |
Strength of the L2 regularization term | 0.01 | |
Maximum number of iterations | 500,000 | |
SVM | Specifies the kernel type to be used in the algorithm | rbf |
Degree of the polynomial kernel function | 3 | |
Kernel coefficient for ‘rbf’, ‘poly’ and ‘sigmoid’ | scale | |
Regularization parameter | 50.0 | |
Epsilon in the epsilon-SVR model | 0.1 | |
RF | The number of trees in the forest | 140 |
The function to measure the quality of a split | SE | |
The number of features to consider when looking for best split | 1.0 | |
The minimum number of samples required to be at a leaf node | 2 |
