Table 1.
Classification of Mainstream Methods.
Fig 1.
The dataset visualization.
Fig 2.
Combined dataset distribution.
Fig 3.
Details of these features.
Fig 4.
Setting an upper limit.
Fig 5.
The proposed methodology framework.
Fig 6.
The process of the stack model.
Table 2.
The confusion matrix.
Fig 7.
Accuracy comparison with base classifiers and the proposed stacking model.
Table 3.
Performance of the proposed stacking model.
Fig 8.
Overall performance of base classifiers and the proposed stacking model.
Fig 9.
Comparison of performance evaluation metrics between baseline and adjusted models.
Table 4.
Performance comparison before and after tuning.
Fig 10.
The 5-fold cross-validation for the determination of best hyperparameter values for XGBoost.
Table 5.
Comparison of the most successful accuracy rates on the same and different data sets.
Fig 11.
Comparison of results.