THESIS

Determination Of Ripeness Stages and Shelf-Life Estimation of Avocados using YOLOv8, Hybrid Machine Learning, and Additional Local Avocado Datasets

ABSTRACT

Post-harvest management of ‘Hass’ avocados faces significant challenges due to unpredictable ripening, leading to substantial losses. While recent studies have utilized deep learning for ripening assessment, gaps persist in accuracy, efficiency for resource-constrained devices, and optimal exploitation of internal model features. This research aims to develop and evaluate a system for detecting avocado ripening stages and estimating shelf life using YOLOv8 and hybrid machine learning approaches. The system was adapted to a local avocado dataset, and a mobile application prototype was developed. The dataset comprises avocado images across five ripening stages (unripe, breaking, ripe1, ripe2, and overripe), including additional data from local Central Aceh avocado varieties. The YOLOv8 model was initially trained using the dataset by Xavier and subsequently fine-tuned with local data. Evaluation results indicate that the standalone model accurately classifies ripening stages with a mean Average Precision (mAP) of 0.93 and a classification accuracy of 0.88. The hybrid approach involved extracting features from optimal YOLOv8 layers, followed by Random Forest feature selection, class balancing with SMOTE, and classification using Logistic Regression, SVM, and XGBoost algorithms. Among these, Logistic Regression achieved the highest accuracy at 0.99 Shelf-life estimation demonstrated an overall Mean Absolute Error (MAE) of 0.43 days for the hybrid approach and 0.44 days for Y OLOv8, significantly outperforming previous research (0.96 days). Thus, this study successfully developed an effective and more accurate system for avocado detection and estimation of shelf-life Implementing the model within a mobile application offers a practical solution that contributes to post-harvest efficiency by helping to reduce losses and improve avocado management.

PUBLICATION

• Utilizing Edge Device and Streamlit for Comparative Evaluation of CLAHE-Based Underwater Image Enhancement Techniques (link)
• Ripeness Detection and Shelf-Life Prediction of Avocados using YOLOv8 and Hybrid Machine Learning (link)
• Optimizing Pomegranate Growth Stage Detection Using YOLOv8 and Hybrid Machine Learning Approaches (link)