Table 1 Hyperparameter optimization
From: Development of PDAC diagnosis and prognosis evaluation models based on machine learning
Models | Parameters | Value Range | Optimal Parameters |
|---|---|---|---|
RF | mtry | mtry = c(1:15) | 6 |
NNET | size | size = seq(1, 10, 1) | 10 |
decay | decay = seq(0.1, 0.5, 0.1) | 0.5 | |
SVM Radial | sigma | sigma =[0.1,0.5,1,2,5] | 0.5 |
C | C=[ 1, 10, 100, 1000] | 10 | |
GBM | n.trees | n.trees = (1:30)*50 | 400 |
interaction.depth | interaction.depth = c(1, 5, 9) | 9 | |
shrinkage | shrinkage = 0.1 | 0.1 | |
n.minobsinnode | n.minobsinnode = 20 | 20 |