Skip to main content

Table 1 Classification model parameters

From: Comparative assessment of synthetic time series generation approaches in healthcare: leveraging patient metadata for accurate data synthesis

Model

Configuration

RF

Number of trees: 100, split criteria: Gini index

KNN

Number of neighbors: 10

DT

Split criteria: Gini index

SVM

Regularization parameter: 100, maximum epochs: 300, kernel type: linear

MLP

Maximum epochs: 100, hidden layers: (a) 64 neurons and (b) 32 neurons, activation: relu, solver: adam, batch size: 200, learning rate: 0.001