Table 2 Hyperparameters in machine learning algorithms
From: Anesthesia depth prediction from drug infusion history using hybrid AI
Model | Hyperparameters |
|---|---|
Random Forest (RF) | Number of estimators: [100, 200, 300] Max features: [1, 10, ‘log2’, ‘sqrt’] Criterion: squared error |
Logistic Regression (LR) | Regularization: [L1, L2] C: [0.01, 0.1, 1, 10] |
Naive Bayes (NB) | Model: [Gaussian, Multinomial] Laplace smoothing: [True, False] |
AdaBoost (ADB) | Number of estimators: [100, 200, 300] |
Gradient Boosting (GB) | Number of estimators: [100, 200, 300] Learning rate: [0.01, 0.1, 0.2] Max depth: [3, 5, 7] |
XGBoost (XGB) | Number of estimators: [100, 200, 300] Learning rate: [0.01, 0.1, 0.2] Max depth: [3, 5, 7] |