Educational data mining is the method for extracting and discovering new knowledge from education data. As education data is often complex and imbalanced, it requires a data preprocessing step or learning algorithms in order to obtain accurate analysis and interpretation. Many studies emphasize on classification and clustering methods in order to get insight and comprehensive knowledge from education data. However, a small number of previous works exclusively focused on the preprocessing of education data, particularly on the topic of the imbalanced dataset. Therefore, this research objective is to enhance the accuracy of data classification in educational web usage data. Our study involves the application of synthetic minority over-sampling techniques (SMOTE) to preprocess the raw dataset from web usage data. The minority class is a group of the students who failed the examination and the majority class is the students who passed the examination. In our experiments, four synthetic minority over-sampling methods are applied, SMOTE, and its variants: Borderline-SMOTE1, Borderline-SMOTE2, and SVM-SMOTE, in order to balance the number of samples in the minority class. The experiments are evaluated by comparing the results from well-known classification methods that are Naive Bayesian, decision tree, and k-nearest neighbors. The study experiments with real-world datasets from education data. The results present that synthetic minority over-sampling methods are capable of improving the detection of the minority class and achieve improving classification performance on precision, recall, and F1-value. Ed

Mechanical damage is a major cause of postharvest quality deterioration in guava, and early discrimination of bruises caused by impact and vibration remains challenging due to visually indistinguishable peel bruising. This study investigated the feasibility of deep learning-based RGB imaging for early classification of mechanical bruise types in ‘Glom Sali’ guava. A total of 623 and 520 fruits were subjected to simulated vibration and impact conditions, respectively. RGB images were acquired from four orientations covering the entire fruit surface on Days 1–4 following the simulated tests. After image preprocessing and data augmentation, two convolutional neural network architectures, MobileNetV3 and EfficientNetV2-B0, were trained and evaluated using accuracy, precision, recall, F1-score, sensitivity, and specificity. Both models successfully distinguished impact- and vibration-induced bruises, confirming that RGB images contain sufficient discriminative information for bruise classification. MobileNetV3 consistently outperformed EfficientNetV2-B0, achieving testing accuracies above 98% across all evaluation periods. The performance advantage was particularly pronounced on Day 1, when bruises were visually inconspicuous, with precision, recall, and F1-score of 98–100% and sensitivity and specificity exceeding 97%. Model performance improved as bruise symptoms became more evident, while data augmentation enhanced classification robustness and generalization. These findings demonstrate that MobileNetV3 combined with RGB imaging provides a rapid, non-destructive, and computationally efficient approach for early classification of mechanical bruise types in guava, offering strong potential for deployment in automated postharvest inspection systems to improve fruit sorting, transportation quality assessment, and postharvest loss reduction.