Table 1.
Notation guide.
Fig 1.
Exploring education through artificial intelligence proposed methodology.
Fig 2.
Visualizations comparing gender and Internet types.
Fig 3.
Correlation matrix.
Fig 4.
Architecture of the proposed stacked ensemble learning model, illustrating the use of three base learners (decision tree, random forest, and XGBoost) to generate predictions (Prediction 1, Prediction 2, and Prediction 3), which are then combined by a gradient boosting meta-learner to produce the final prediction.
This approach leverages the strengths of individual models to enhance overall predictive accuracy.
Fig 5.
CNN model evaluation.
Fig 6.
RCNN model evaluation.
Fig 7.
Decision tree evaluation.
Fig 8.
Stacking approach evaluation.
Fig 9.
XG boosting evaluation.
Fig 10.
Random forest evaluation.
Table 2.
Accuracy of ML classifiers.
Fig 11.
Confusion matrix evaluation of CNN.
Fig 12.
Confusion matrix evaluation of RCNN.
Fig 13.
Confusion matrix evaluation of XGB.
Fig 14.
Confusion matrix evaluation of decision trees.
Fig 15.
Confusion matrix evaluation of stacking approach.
Fig 16.
ROC curve CNN.
Fig 17.
ROC curve RCNN.
Fig 18.
ROC curve stacking meta model gradient boosting.
Fig 19.
ROC curve XG boosting.
Fig 20.
ROC curve decision trees.
Fig 21.
ROC curve random forest.
Fig 22.
Accuracy chart of ML and DL classifiers.