Optimization of optical spectroscopy classification algorithms for limited data scenarios in the food industry: tomato sauce samples case

Simple item page
dc.contributor.authorGracia Moisés, Ander
dc.contributor.authorVitoria Pascual, Ignacio
dc.contributor.authorAvedillo de la Casa, Amaia
dc.contributor.authorMoreno Pérez, María
dc.contributor.authorImas González, José Javier
dc.contributor.authorRuiz Zamarreño, Carlos
dc.contributor.departmentIngeniería Eléctrica, Electrónica y de Comunicaciónes_ES
dc.contributor.departmentIngeniaritza Elektrikoa, Elektronikoa eta Telekomunikazio Ingeniaritzaeu
dc.contributor.departmentInstitute of Smart Cities - ISCen
dc.contributor.funderGobierno de Navarra / Nafarroako Gobernua
dc.contributor.funderUniversidad Pública de Navarra / Nafarroako Unibertistate Publikoa
dc.date.accessioned2024-11-20T11:32:29Z
dc.date.issued2025-01-01
dc.date.updated2024-11-20T11:06:29Z
dc.description.abstractThis study addresses the problem of training deep learning models with limited datasets, a significant challenge in sectors like medical imaging and food quality analysis. To tackle this issue, generative adversarial networks (GANs) will be employed to augment the available data and improve model performance. An innovative approach is introduced here, integrating semi-supervised learning and generative modeling to maximize the use of small datasets in developing robust models. The method involves reversing the conventional distribution of training and testing data to focus on model evaluation and generalization from limited samples. Wasserstein GANs (WGANs) and Semi-Supervised GANs (SGANs), are utilized to supplement datasets with synthetic but realistic examples, enhancing the training process in scenarios of data scarcity. These techniques are applied in the context of visible reflectance spectroscopy to analyze tomato sauces, demonstrating the method's effectiveness in non-invasively assessing key quality parameters such as oil content, °Brix, and pH. The results show significant improvements in model performance metrics: for %Oil content, overall accuracy increased from 0.47 to 0.66; for °Bx, it rose from 0.65 to 0.71; and for pH measurement, accuracy improved from 0.43 to 0.62. These outcomes highlight the model's improved capability to generalize and maintain accuracy with limited data.en
dc.description.sponsorshipThis work was founded in part by the Industrial Doctorate grants 2021 and AGROFLUID 0011-1365-2022-000048 research grant from the Government of Navarra.
dc.embargo.lift2026-01-01
dc.embargo.terms2026-01-01
dc.format.mimetypeapplication/pdfen
dc.identifier.citationGracia Moisés, A., Vitoria-Pascual, I., Avedillo de la Casa, A., Moreno-Pérez, M., Imas González, J. J., Ruiz-Zamarreño, C. (2025). Optimization of optical spectroscopy classification algorithms for limited data scenarios in the food industry: Tomato sauce samples case. Food Control, 167, 1-9. https://doi.org/10.1016/j.foodcont.2024.110819.
dc.identifier.doi10.1016/j.foodcont.2024.110819
dc.identifier.issn0956-7135
dc.identifier.urihttps://academica-e.unavarra.es/handle/2454/52546
dc.language.isoeng
dc.publisherElsevier
dc.relation.ispartofFood Control (2025), vol. 167, 110819
dc.relation.projectIDinfo:eu-repo/grantAgreement/Gobierno de Navarra//0011-1365-2022-000048/
dc.relation.publisherversionhttps://doi.org/10.1016/j.foodcont.2024.110819
dc.rights© 2024 Elsevier Ltd. This manuscript version is made available under the CC-BY-NC-ND 4.0.
dc.rights.accessRightsinfo:eu-repo/semantics/embargoedAccess
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectFood quality controlen
dc.subjectGenerative adversarial networksen
dc.subjectOil contenten
dc.subjectpHen
dc.subjectSemi-supervised learningen
dc.subjectVisible reflectance spectroscopyen
dc.subject°Brixen
dc.titleOptimization of optical spectroscopy classification algorithms for limited data scenarios in the food industry: tomato sauce samples caseen
dc.typeinfo:eu-repo/semantics/article
dc.type.versioninfo:eu-repo/semantics/acceptedVersion
dspace.entity.typePublication
relation.isAuthorOfPublication5131262a-e53d-4f80-83e3-f4f58d720031
relation.isAuthorOfPublication1d3ab98f-d163-4f9d-8baf-a6f5130c957c
relation.isAuthorOfPublication77495fb3-fd9a-4636-be2d-37165dd2e90d
relation.isAuthorOfPublicationf85c4fed-8804-4e02-b746-0855066291e3
relation.isAuthorOfPublication.latestForDiscovery5131262a-e53d-4f80-83e3-f4f58d720031

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Gracia_OptimizationOptical.pdf
Size:
1.54 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description:
Download

Collections

Artículos de revista DIEC - IEKS Aldizkari artikuluak
Artículos de revista - Aldizkari artikuluak
Artículos de revista ISC - ISC aldizkari artikuluak