Table 2 Detailed description of partial parameter adjustment for the ensemble stacking model (n_evals = 20). For the evaluation of model performance, evaluation indicators such as accuracy, kappa, sensitivity, specificity and precision were utilized. The equations for each indicator are as follows
Models | Optimization range of partial hyperparameters | Tuned hyperparameters |
|---|---|---|
RF | ntree = [1:500]; mtry = [1:500]; depth = [1:10] | ntree = 459; mtry = 7; depth = 3 |
SVM | cost = [0:2]; gamma = [0:2]; kernel = [‘polynomial’, ‘radial’, ‘sigmoid’] | cost = 1.79; gamma = 0.34; kernel = ‘linear’ |
XGBoost | booster = [‘gbtree’, ‘gbliner’, ‘dart’]; η = [0:0.5]; nrounds = [1:20, tags = ‘budget’] | booster = ‘gblinear’; η = 0.41; nrounds = 15 |