Research Article
COVID-19 Propagation Prediction Model Using Improved Grey Wolf Optimization Algorithms in Combination with XGBoost and Bagging-Integrated Learning
Table 5
Algorithm-related parameters.
| Model | Parameter setting |
| Bagging-COLGWO-XGBoost | n_estimators = 21 | Bagging-COLGWO-GBDT | n_estimators = 21 | COLGWO-XGBoost | n_estimators = 18; learning_rate = 0.8561; max_depth = 7 | COLGWO- GBDT | n_estimators = 22; learning_rate = 0.3208; max_depth = 4 | GWO-XGBoost | n_estimators = 46; learning_rate = 0.8563; max_depth = 6 | GWO-GBDT | n_estimators = 38; learning_rate = 0.5996; max_depth = 4 | XGBoost | Default parameter | GBDT | Default parameter | LSTM | Optimizer = Adam; loss = mse; epochs = 100 | RNN | Optimizer = Adam; loss = mse; epochs = 100 | CNN | Optimizer = Adam; loss = mse; epochs = 100 | SVR | Default parameter | MLP | Default parameter | LR | Default parameter | COLGWO | Iteration number: 100; Population size: 30 | GWO | Iteration number: 100; Population size: 30 |
|
|