A4 Refereed article in a conference publication
Enhanced Grading of ‘Carabao’ Mango for Exportation Using Three-Way Rule-Based Ensemble Method
Authors: Banuag, Ladlennon C.; Malinao, Ritchie B.; Rosales, Jojimar S.; Sinogaya, Jonnifer R.; Patino, Chito L.; Juanico, Drandreb Earl
Editors: N/A
Conference name: IEEE International Conference on Agrosystem Engineering, Technology & Applications
Publisher: IEEE
Publication year: 2025
Book title : 2024 IEEE International Conference on Agrosystem Engineering, Technology & Applications (AGRETA)
Journal name in source: 2024 IEEE International Conference on Agrosystem Engineering, Technology and Applications: Integrating Smart Farming and Food Security for a Sustainable Future, AGRETA 2024
First page : 136
Last page: 142
ISBN: 979-8-3503-7367-7
eISBN: 979-8-3503-7366-0
DOI: https://doi.org/10.1109/AGRETA61912.2024.10948891
Web address : https://doi.org/10.1109/agreta61912.2024.10948891
The 'Carabao' mango, a significant agricultural export from the Philippines, requires accurate grading to ensure consistent quality and maximize market value. Traditional methods for mango grading, reliant on manual inspection, are prone to human error and inconsistency. While widely used for image classification, conventional Convolutional Neural Network (CNN) are limited to analyzing images of a single side of the mango, which restricts their ability to fully grade the fruit by not providing a comprehensive visual assessment of the entire mango. The research highlights a novel three-way rule-based ensemble approach of grading 'Carabao' mangoes using multi-architecture CNN. The proposed method leverages multiple-view analysis to improve the robustness of grading mango. By integrating ensemble method, the developed approach combines the outputs from various CNN s and utilizes different perspectives of the same mango to create a more reliable grading system and a more comprehensive analysis. The test accuracies of the three individual CNN models are 95.33 %, 89.33%, and 92.67% for side, top and bottom model respectively. The three-way rule-based ensemble method achieved an accuracy of 94.33%. Despite not having a higher accuracy, it excels with a higher true negative rate and lower average false positive rate, enhancing the robustness and consistency of the mango grading process.
Funding information in the publication:
The authors extend their sincere gratitude to the Department of Science and Technology Philippine Council for Agriculture, Aquatic and Natural Resources Research and Development for the research grant that enabled this study. We would also like to acknowledge the Department of Agriculture VII for their invaluable assistance in identifying mango sites, facilitating meetings with mango growers and sharing their expertise in the mango industry. Lastly, our sincerest gratitude to the University of the Philippines Cebu, the Center for Environmental Informatics and the College of Science for providing us with the necessary resources and workspace for the realization of this research.
