Gracia Moisés, Ander

Loading...
Profile Picture

Email Address

Birth Date

Job Title

Last Name

Gracia Moisés

First Name

Ander

person.page.departamento

Ingeniería Eléctrica, Electrónica y de Comunicación

person.page.instituteName

person.page.observainves

person.page.upna

Name

Search Results

Now showing 1 - 2 of 2
  • PublicationEmbargo
    Optimization of optical spectroscopy classification algorithms for limited data scenarios in the food industry: tomato sauce samples case
    (Elsevier, 2025-01-01) Gracia Moisés, Ander; Vitoria Pascual, Ignacio; Avedillo de la Casa, Amaia; Moreno Pérez, María; Imas González, José Javier; Ruiz Zamarreño, Carlos; Ingeniería Eléctrica, Electrónica y de Comunicación; Ingeniaritza Elektrikoa, Elektronikoa eta Telekomunikazio Ingeniaritza; Institute of Smart Cities - ISC; Gobierno de Navarra / Nafarroako Gobernua; Universidad Pública de Navarra / Nafarroako Unibertistate Publikoa
    This 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.
  • PublicationOpen Access
    Alfalfa quality detection by means of VIS-NIR optical fiber reflection spectroscopy
    (IEEE, 2022) Ruiz Zamarreño, Carlos; Gracia Moisés, Ander; Vitoria Pascual, Ignacio; Imas González, José Javier; Castaño de Egüés, Lorena Yveth; Avedillo de la Casa, Amaia; Matías Maestro, Ignacio; Ingeniería Eléctrica, Electrónica y de Comunicación; Institute of Smart Cities - ISC; Ingeniaritza Elektrikoa, Elektronikoaren eta Telekomunikazio Ingeniaritzaren; Universidad Pública de Navarra / Nafarroako Unibertsitate Publikoa
    A first approach study for the classification of alfalfa (medicago sativa) quality has been performed by means of VIS-NIR optical fiber reflection spectroscopy. Reflection spectral data has been obtained from alfalfa samples comprising six different qualities. Obtained data has been classified and organized to feed supervised self-learning algorithms. Neural networks have been used in order to differentiate the quality level of the samples. Obtained results permit to validate the proposed approach with 72% of the samples properly classified. In addition, proposed solution was implemented in a low cost automated detection prototype suitable to be used by non-qualified operators. Obtained equipment consist of a first step towards its utilization in quality monitoring and classification of many other products in the agri-food field.