Using machine learning for image-based analysis of sweetpotato root sensory attributes
The sweetpotato breeding process involves assessing different phenotypic traits, such as the sensory attributes, to decide which varieties to progress to the next stage during the breeding cycle. Sensory attributes like appearance, taste, colour and mealiness are important for consumer acceptability...
| Autores principales: | , , , , , , , , , , , , , |
|---|---|
| Formato: | Journal Article |
| Lenguaje: | Inglés |
| Publicado: |
Elsevier
2023
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/131399 |
| _version_ | 1855538124696846336 |
|---|---|
| author | Nakatumba-Nabende, J. Babirye, C. Tusubira, J. Mutegeki, H. Nabiryo, A. Murindanyi, S. Katumba, A. Nantongo, J.S. Sserunkuma, E. Nakitto, M. Ssali, R.T. Makunde, G.S. Moyo, M. Campos, Hugo |
| author_browse | Babirye, C. Campos, Hugo Katumba, A. Makunde, G.S. Moyo, M. Murindanyi, S. Mutegeki, H. Nabiryo, A. Nakatumba-Nabende, J. Nakitto, M. Nantongo, J.S. Ssali, R.T. Sserunkuma, E. Tusubira, J. |
| author_facet | Nakatumba-Nabende, J. Babirye, C. Tusubira, J. Mutegeki, H. Nabiryo, A. Murindanyi, S. Katumba, A. Nantongo, J.S. Sserunkuma, E. Nakitto, M. Ssali, R.T. Makunde, G.S. Moyo, M. Campos, Hugo |
| author_sort | Nakatumba-Nabende, J. |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | The sweetpotato breeding process involves assessing different phenotypic traits, such as the sensory attributes, to decide which varieties to progress to the next stage during the breeding cycle. Sensory attributes like appearance, taste, colour and mealiness are important for consumer acceptability and adoption of new varieties. Therefore, measuring these sensory attributes is critical to inform the selection of varieties during breeding. Current methods using a trained human panel enable screening of different sweetpotato sensory attributes. Despite this, such methods are costly and time-consuming, leading to low throughput, which remains the biggest challenge for breeders. In this paper, we describe an approach to apply machine learning techniques with image-based analysis to
predict flesh-colour and mealiness sweetpotato sensory attributes. The developed models can be used as highthroughput methods to augment existing approaches for the evaluation of flesh-colour and mealiness for different sweetpotato varieties. The work involved capturing images of boiled sweetpotato cross-sections using the DigiEye imaging system, data pre-processing for background elimination and feature extraction to develop machine learning models to predict the flesh-colour and mealiness sensory attributes of different sweetpotato varieties. For flesh-colour the trained Linear Regression and Random Forest Regression models attained 𝑅2 values of 0.92 and 0.87, respectively, against the ground truth values given by a human sensory panel. In contrast, the Random Forest Regressor and Gradient Boosting model attained 𝑅2 values of 0.85 and 0.80, respectively, for the prediction of mealiness. The performance of the models matched the desirable 𝑅2 threshold of 0.80 for acceptable comparability to the human sensory panel showing that this approach can be used for the prediction of these attributes with high accuracy. The machine learning models were deployed and tested by the sweetpotato breeding team at the International Potato Center in Uganda. This solution can automate and increase throughput for analysing flesh-colour and mealiness sweetpotato sensory attributes. Using machine learning tools for analysis can inform and quicken the selection of promising varieties that can be progressed for participatory evaluation
during breeding cycles and potentially lead to increased chances of adoption of the varieties by consumers. |
| format | Journal Article |
| id | CGSpace131399 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| publisher | Elsevier |
| publisherStr | Elsevier |
| record_format | dspace |
| spelling | CGSpace1313992025-10-26T12:56:17Z Using machine learning for image-based analysis of sweetpotato root sensory attributes Nakatumba-Nabende, J. Babirye, C. Tusubira, J. Mutegeki, H. Nabiryo, A. Murindanyi, S. Katumba, A. Nantongo, J.S. Sserunkuma, E. Nakitto, M. Ssali, R.T. Makunde, G.S. Moyo, M. Campos, Hugo sweet potatoes roots The sweetpotato breeding process involves assessing different phenotypic traits, such as the sensory attributes, to decide which varieties to progress to the next stage during the breeding cycle. Sensory attributes like appearance, taste, colour and mealiness are important for consumer acceptability and adoption of new varieties. Therefore, measuring these sensory attributes is critical to inform the selection of varieties during breeding. Current methods using a trained human panel enable screening of different sweetpotato sensory attributes. Despite this, such methods are costly and time-consuming, leading to low throughput, which remains the biggest challenge for breeders. In this paper, we describe an approach to apply machine learning techniques with image-based analysis to predict flesh-colour and mealiness sweetpotato sensory attributes. The developed models can be used as highthroughput methods to augment existing approaches for the evaluation of flesh-colour and mealiness for different sweetpotato varieties. The work involved capturing images of boiled sweetpotato cross-sections using the DigiEye imaging system, data pre-processing for background elimination and feature extraction to develop machine learning models to predict the flesh-colour and mealiness sensory attributes of different sweetpotato varieties. For flesh-colour the trained Linear Regression and Random Forest Regression models attained 𝑅2 values of 0.92 and 0.87, respectively, against the ground truth values given by a human sensory panel. In contrast, the Random Forest Regressor and Gradient Boosting model attained 𝑅2 values of 0.85 and 0.80, respectively, for the prediction of mealiness. The performance of the models matched the desirable 𝑅2 threshold of 0.80 for acceptable comparability to the human sensory panel showing that this approach can be used for the prediction of these attributes with high accuracy. The machine learning models were deployed and tested by the sweetpotato breeding team at the International Potato Center in Uganda. This solution can automate and increase throughput for analysing flesh-colour and mealiness sweetpotato sensory attributes. Using machine learning tools for analysis can inform and quicken the selection of promising varieties that can be progressed for participatory evaluation during breeding cycles and potentially lead to increased chances of adoption of the varieties by consumers. 2023-10 2023-08-04T17:48:06Z 2023-08-04T17:48:06Z Journal Article https://hdl.handle.net/10568/131399 en Open Access Elsevier Nakatumba-Nabende, J.; Babirye, C.; Tusubira, J.; Mutegeki, H.; Nabiryo, A.; Murindanyi, S.; Katumba, A.; Nantongo, J.; Sserunkuma, E.; Nakitto, M.; Ssali, R.T.; Makunde, G.S.; Moyo, M.; Campos, H. 2023. Using machine learning for image-based analysis of sweetpotato root sensory attributes. Smart Agricultural Technology. ISSN 2772-3755. 5. DOI: https://doi.org/10.1016/j.atech.2023.100291 |
| spellingShingle | sweet potatoes roots Nakatumba-Nabende, J. Babirye, C. Tusubira, J. Mutegeki, H. Nabiryo, A. Murindanyi, S. Katumba, A. Nantongo, J.S. Sserunkuma, E. Nakitto, M. Ssali, R.T. Makunde, G.S. Moyo, M. Campos, Hugo Using machine learning for image-based analysis of sweetpotato root sensory attributes |
| title | Using machine learning for image-based analysis of sweetpotato root sensory attributes |
| title_full | Using machine learning for image-based analysis of sweetpotato root sensory attributes |
| title_fullStr | Using machine learning for image-based analysis of sweetpotato root sensory attributes |
| title_full_unstemmed | Using machine learning for image-based analysis of sweetpotato root sensory attributes |
| title_short | Using machine learning for image-based analysis of sweetpotato root sensory attributes |
| title_sort | using machine learning for image based analysis of sweetpotato root sensory attributes |
| topic | sweet potatoes roots |
| url | https://hdl.handle.net/10568/131399 |
| work_keys_str_mv | AT nakatumbanabendej usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT babiryec usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT tusubiraj usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT mutegekih usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT nabiryoa usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT murindanyis usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT katumbaa usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT nantongojs usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT sserunkumae usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT nakittom usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT ssalirt usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT makundegs usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT moyom usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes AT camposhugo usingmachinelearningforimagebasedanalysisofsweetpotatorootsensoryattributes |