Optimized ensemble learning for non-destructive avocado ripeness classification
Classifying avocado ripeness accurately is crucial for enhancing post-harvest management and minimizing waste in agricultural supply chains. This study focuses on creating a strong ensemble classification model using spectral data from 120 kilogrammes of Buccaneer avocados obtained from the Royal Pr...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525003478 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849419443465093120 |
|---|---|
| author | Panudech Tipauksorn Prasert Luekhong Minoru Okada Jutturit Thongpron Chokemongkol Nadee Krisda Yingkayun |
| author_facet | Panudech Tipauksorn Prasert Luekhong Minoru Okada Jutturit Thongpron Chokemongkol Nadee Krisda Yingkayun |
| author_sort | Panudech Tipauksorn |
| collection | DOAJ |
| description | Classifying avocado ripeness accurately is crucial for enhancing post-harvest management and minimizing waste in agricultural supply chains. This study focuses on creating a strong ensemble classification model using spectral data from 120 kilogrammes of Buccaneer avocados obtained from the Royal Project in Chiang Mai, Thailand. We analyzed the avocados with near-infrared (NIR) spectroscopy at 18 wavelengths. Five machine learning models Random Forest, Decision Tree, XGBoost, Gradient Boosting, and Gaussian Mixture Model were trained separately and then merged into an ensemble. Four algorithms were used to optimize the model weight distribution: Bayesian Optimisation, Differential Evolution, Particle Swarm Optimisation, and Grid Search. We assessed performance through accuracy, precision, recall, F1-score, confusion matrices, and ROC curves. Grid Search achieved the best classification performance, reaching an accuracy of 82.5% and an F1-score of 85.3%, highlighting the benefits of weight-optimized ensemble learning compared to single classifiers. This study offers a scalable and clear method for non-destructive ripeness detection. The findings, despite some limitations like overfitting and reliance on spectral data quality, support future real-time deployment in agriculture. |
| format | Article |
| id | doaj-art-e42be9cd83654f57bb23e6799e281e67 |
| institution | Kabale University |
| issn | 2772-3755 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-e42be9cd83654f57bb23e6799e281e672025-08-20T03:32:04ZengElsevierSmart Agricultural Technology2772-37552025-12-011210111410.1016/j.atech.2025.101114Optimized ensemble learning for non-destructive avocado ripeness classificationPanudech Tipauksorn0Prasert Luekhong1Minoru Okada2Jutturit Thongpron3Chokemongkol Nadee4Krisda Yingkayun5Department of Electrical Engineering, Faculty of Engineering, Rajamangala University of Technology Lanna, 128 Huay Kaew Road, Muang, 50300, Chiangmai, ThailandDepartment of Electrical Engineering, Faculty of Engineering, Rajamangala University of Technology Lanna, 128 Huay Kaew Road, Muang, 50300, Chiangmai, ThailandDivision of Information Science, Nara Institute of Science and Technology, 8916-5 Takayama-cho, Ikoma, 630-0192, Nara, JapanDepartment of Electrical Engineering, Faculty of Engineering, Rajamangala University of Technology Lanna, 128 Huay Kaew Road, Muang, 50300, Chiangmai, ThailandDepartment of Electrical Engineering, Faculty of Engineering, Rajamangala University of Technology Lanna, 128 Huay Kaew Road, Muang, 50300, Chiangmai, ThailandDepartment of Electrical Engineering, Faculty of Engineering, Rajamangala University of Technology Lanna, 128 Huay Kaew Road, Muang, 50300, Chiangmai, Thailand; Corresponding author.Classifying avocado ripeness accurately is crucial for enhancing post-harvest management and minimizing waste in agricultural supply chains. This study focuses on creating a strong ensemble classification model using spectral data from 120 kilogrammes of Buccaneer avocados obtained from the Royal Project in Chiang Mai, Thailand. We analyzed the avocados with near-infrared (NIR) spectroscopy at 18 wavelengths. Five machine learning models Random Forest, Decision Tree, XGBoost, Gradient Boosting, and Gaussian Mixture Model were trained separately and then merged into an ensemble. Four algorithms were used to optimize the model weight distribution: Bayesian Optimisation, Differential Evolution, Particle Swarm Optimisation, and Grid Search. We assessed performance through accuracy, precision, recall, F1-score, confusion matrices, and ROC curves. Grid Search achieved the best classification performance, reaching an accuracy of 82.5% and an F1-score of 85.3%, highlighting the benefits of weight-optimized ensemble learning compared to single classifiers. This study offers a scalable and clear method for non-destructive ripeness detection. The findings, despite some limitations like overfitting and reliance on spectral data quality, support future real-time deployment in agriculture.http://www.sciencedirect.com/science/article/pii/S2772375525003478Avocado ripeness classificationEnsemble learningOptimization algorithmsNIR spectroscopyPrecision agricultureMachine learning in agriculture |
| spellingShingle | Panudech Tipauksorn Prasert Luekhong Minoru Okada Jutturit Thongpron Chokemongkol Nadee Krisda Yingkayun Optimized ensemble learning for non-destructive avocado ripeness classification Smart Agricultural Technology Avocado ripeness classification Ensemble learning Optimization algorithms NIR spectroscopy Precision agriculture Machine learning in agriculture |
| title | Optimized ensemble learning for non-destructive avocado ripeness classification |
| title_full | Optimized ensemble learning for non-destructive avocado ripeness classification |
| title_fullStr | Optimized ensemble learning for non-destructive avocado ripeness classification |
| title_full_unstemmed | Optimized ensemble learning for non-destructive avocado ripeness classification |
| title_short | Optimized ensemble learning for non-destructive avocado ripeness classification |
| title_sort | optimized ensemble learning for non destructive avocado ripeness classification |
| topic | Avocado ripeness classification Ensemble learning Optimization algorithms NIR spectroscopy Precision agriculture Machine learning in agriculture |
| url | http://www.sciencedirect.com/science/article/pii/S2772375525003478 |
| work_keys_str_mv | AT panudechtipauksorn optimizedensemblelearningfornondestructiveavocadoripenessclassification AT prasertluekhong optimizedensemblelearningfornondestructiveavocadoripenessclassification AT minoruokada optimizedensemblelearningfornondestructiveavocadoripenessclassification AT jutturitthongpron optimizedensemblelearningfornondestructiveavocadoripenessclassification AT chokemongkolnadee optimizedensemblelearningfornondestructiveavocadoripenessclassification AT krisdayingkayun optimizedensemblelearningfornondestructiveavocadoripenessclassification |