SMOTE-ENN resampling technique with Bayesian optimization for multi-class classification of dry bean varieties

The imbalanced classification problem poses a significant challenge in machine learning, often resulting in biased models and poor performance for minority classes. This study introduces an innovative hybrid resampling technique combining Synthetic Minority Oversampling Technique and Edited Nearest Neighbours (SMOTE-ENN), optimized using Bayesian Optimization, to address these limitations. The proposed framework integrates advanced feature pre-processing, hybrid resampling, and machine learning models to enhance classification performance. Using the publicly available dry bean dataset containing 16 geometric features of seven seed varieties, the methodology demonstrates remarkable improvements in predictive accuracy and class balance. Employing cutting-edge classifiers, the improved Light Gradient Boosting Machine (LBM) with Bayesian optimization achieved an unprecedented accuracy of 99.59%, outperforming traditional approaches. Results reveal the potential of hybrid resampling techniques and Bayesian optimization in effectively capturing feature patterns, enhancing model diversity, and ensuring robust classification of imbalanced datasets. This research underscores the application of soft computing methods to real-world multi-class classification challenges, offering practical insights for similar domains. ∙ An efficient machine learning framework is designed to meet the demands of producers and customers for food security. ∙ Feature selection strategy is used to reduce the risk of overfitting by removing redundant features and strengthen the model predictive power. ∙ Hybrid resembling technique improves the model’s ability to generalize to new seed or unknown seed, reducing classification bias towards the majority classes. ∙ Confusion matrix is followed to represents how the classification model is confused when it makes predictions. That is, it provides insight not only the errors which are made by the classifier but also types of errors that are being made. ∙ Feature importance is analyzed to illustrate, which types of geometric features influence the model’s predictions significantly.