<![CDATA[This study explores the application of Machine Learning (ML) for the evaluation of banana quality through Exploratory Data Analysis (EDA) and classification techniques. The research emphasizes the importance of objective, accurate, and consistent assessment methods to replace traditional manual evaluation, which is often subjective and inefficient. A dataset comprising multiple banana attributes, including sweetness, firmness, acidity, size, and ripeness, was analyzed to identify key patterns and relationships. Several ML algorithms, such as Random Forest (RF), were implemented and evaluated using metrics such as accuracy, precision, recall, and F1-score. Results demonstrated that the Random Forest algorithm achieved the highest performance with an overall accuracy of 90%, effectively distinguishing bananas in the “Good” and “Poor” categories, though limitations remained for the “Average” class due to class imbalance. These findings highlight the potential of ML-based approaches to enhance smart agriculture practices, providing a reliable and scalable solution for automated banana quality evaluation. Future research should focus on addressing class imbalance and integrating additional features, such as image-based or biochemical data, to further improve classification performance.]]>
Copyrights © 2025
