Skip to main content

Table 3 The model parameters

From: Representation learning in intraoperative vital signs for heart failure risk prediction

Model

The parameter settings

Adaboost

n_estimators = 100 # The maximum number of estimators at which boosting is

# terminated.

Decision Tree (DT)

criterion = “gini” # The function to measure the quality of a split, supported criteria

# are “gini” for the Gini impurity

min_samples_split = 2 # The minimum number of samples required to split an

# internal node.

min_samples_leaf = 1 # The minimum number of samples required to be at a leaf

# node.

min_weight_fraction_leaf = 0.0 # The minimum weighted fraction of the sum total

# of weights required to be at a leaf node.

support vector machine (SVM)

kernel = “rbf” # Specifies the kernel type to be used in the algorithm.

# “rbf” is Gaussian kernel function.

logistic regression (LR)

penalty = “l2” # Specifies the norm used in the penalization, the ‘l2’ penalty is the

# standard used in SVC.

Random forest (RF)

n_estimators = 100 # The number of trees in the forest.

Multiple perception machine (MLP)

alpha = 1e-5 # It is regularized parameters.

hidden_layer_sizes = (5, 2) # The i-th element represents the number of neurons

# in the i-th hidden layer.

Gradient Boosting Decison Tree (GBDT)

n_estimators = 200 # The number of boosting stages to perform.