Using machine learning for image-based analysis of sweetpotato root sensory attributes

Simple item page
cg.authorship.typesCGIAR and developing country instituteen
cg.authorship.typesCGIAR and advanced research instituteen
cg.contributor.affiliationMakerere Universityen
cg.contributor.affiliationInternational Potato Centeren
cg.contributor.donorBill & Melinda Gates Foundationen
cg.creator.identifierJoyce Nakatumba-Nabende: 0000-0002-0108-3798en
cg.creator.identifierJudith Nantongo: 0000-0001-7914-9139en
cg.creator.identifierMariam Nakitto: 0000-0002-4140-7216en
cg.creator.identifierReuben SSALI Tendo: 0000-0002-8143-6564en
cg.creator.identifierGodwill Makunde: 0000-0002-9003-7266en
cg.creator.identifierMukani Moyo: 0000-0001-5658-2669en
cg.creator.identifierHugo Campos: 0000-0003-0070-1336en
cg.howPublishedFormally Publisheden
cg.identifier.doihttps://doi.org/10.1016/j.atech.2023.100291en
cg.isijournalISI Journalen
cg.issn2772-3755en
cg.journalSmart Agricultural Technologyen
cg.reviewStatusPeer Reviewen
cg.subject.cipANDEAN ROOTS AND TUBERSen
cg.subject.cipSWEETPOTATOESen
cg.subject.cipSWEETPOTATO AGRI-FOOD SYSTEMSen
cg.volume5en
dc.contributor.authorNakatumba-Nabende, J.en
dc.contributor.authorBabirye, C.en
dc.contributor.authorTusubira, J.en
dc.contributor.authorMutegeki, H.en
dc.contributor.authorNabiryo, A.en
dc.contributor.authorMurindanyi, S.en
dc.contributor.authorKatumba, A.en
dc.contributor.authorNantongo, J.S.en
dc.contributor.authorSserunkuma, E.en
dc.contributor.authorNakitto, M.en
dc.contributor.authorSsali, R.T.en
dc.contributor.authorMakunde, G.S.en
dc.contributor.authorMoyo, M.en
dc.contributor.authorCampos, Hugoen
dc.date.accessioned2023-08-04T17:48:06Zen
dc.date.available2023-08-04T17:48:06Zen
dc.identifier.urihttps://hdl.handle.net/10568/131399
dc.titleUsing machine learning for image-based analysis of sweetpotato root sensory attributesen
dcterms.abstractThe 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.en
dcterms.accessRightsOpen Access
dcterms.audienceAcademicsen
dcterms.audienceCGIARen
dcterms.audienceDevelopment Practitionersen
dcterms.audienceDonorsen
dcterms.audienceExtensionen
dcterms.audienceFarmersen
dcterms.audienceGeneral Publicen
dcterms.audienceNGOsen
dcterms.audiencePolicy Makersen
dcterms.audienceScientistsen
dcterms.available2023-07-25en
dcterms.bibliographicCitationNakatumba-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.2023.100291en
dcterms.extent14 p.en
dcterms.issued2023-10en
dcterms.languageen
dcterms.licenseCC-BY-4.0
dcterms.publisherElsevieren
dcterms.subjectsweet potatoesen
dcterms.subjectrootsen
dcterms.typeJournal Article

Files

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.75 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

CIP Journal Articles
CIP Science Goal: Crop Improvement
SweetGAINS: Genetics Advances and Innovative Seed Systems for Sweet Potato