Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Detection of subsurface bruises in plums using spectral imaging and deep learning with wavelength selection

  • Castillo-Gironés, S.
  • Van Belleghem, R.
  • Wouters, N.
  • Blasco, J.
  • Saeys, W.
  • Munera, S|||0000-0003-3064-1186
[EN] Plums are widely consumed, both fresh and processed. During harvest, handling, or transportation, they are exposed to static and dynamic compression forces exceeding the critical stress for tissue damage. Compressionrelated damage typically develops further as the fruit ripens and softens, facilitating the occurrence of rot, which might cause significant losses in the supply chain. Early detection of these damages is crucial to sorting the damaged fruit out and deviating it to processing, thus preventing food waste. However, early-stage bruises or damages on plums are not visible, especially not in dark-skin cultivars. Therefore, this study aimed to explore the potential of hyperspectral imaging in the 430 to 1 000 nm range and deep learning algorithms to detect these invisible bruises at an early stage. To this end, 'Presenta' plums were impacted at three different levels to simulate varying degrees of damage. Images of both bruised and non-bruised plums were taken immediately after bruising and 24 and 48 h after bruise induction. Three distinct CNNs were trained to analyze the images. Two of these networks were implemented using transfer learning (ResNet and HSCNN), while the third was customdesigned for this specific purpose. The most informative wavelengths were identified as inputs for the CNNs employing PCA. F1 scores over 81% were obtained in all cases, and almost 100% accuracy was obtained in classifying the bruised plums with the highest impact energy of 0.50 J. Thus, detecting and classifying bruised plums using only three wavelengths is possible, paving the way for in-line sorting with multispectral cameras in packing houses., This work was partially funded by projects GVA-PROMETEO CIPROM/2021/014. Salvador Castillo Girones thanks INIA for the FPI-INIA grant number. PRE2020-094491, partially supported by European Union FSE funds and the COST action CA19145 for granting the research stay at KU Leuven. Remi Van Belleghem thanks the Research Foundation -Flanders (FWO, Brussels, Belgium) for his Ph.D. Fellowship strategic basic research (1S28522N) . Sandra Munera thanks the post-doctoral contract Juan de la Cierva-Formacion (FJC2021 -047786-I) co-funded by MCIN/AEI/10.13039/501100011033 and European Union NextGenerationEU/PRTR. The authors thank Mieke Thoelen from Belorta for providing the packing sheets and Wim Wouters from Fruithandel Romain Wouters & Co. nv for his flexibility in providing the plums.
IRTA Pubpro. Open Digital Archive
Publication Artículo científico (JournalArticle)

Exploring the use of FTIR Amide I band deconvolution to investigate protein secondary structure and texturisation during high moisture extrusion

  • Barnés Calle, Clara
  • Gou, Pere
  • Fulladosa, Elena
  • van den Berg, Frans W.J.
Fourier transform infrared spectroscopy (FTIR) combined with Amide I band deconvolution has been used to investigate protein structural changes occurring during high moisture extrusion processing (HMEP). However, it is a sensitive, user-dependent technique that has sparked debate over its appropriate analytical approach. This paper aims to assess the suitability of FTIR Amide I band deconvolution to investigate protein structural changes in fava bean protein concentrate (FBPC) caused by temperature treatment and/or HMEP at different temperatures (110 ◦C, 135 ◦C and 165 ◦C), and to explore its relationship with the texturisation level of the obtained products. Influence of sample preparation and parameter selection during FTIR deconvolution procedure was also explored. To do so, FBPC was heated in a convection oven or subjected to HMEP at different temperatures (110, 135 or 165 ◦C), and Fourier self-deconvolution (FSD) and second derivative (SD) were explored as bandnarrowing methods to analyse protein conformation from FTIR spectra. FTIR Amide I band deconvolution showed high sensitivity to sample preparation and parameter selection during FSD and SD analytical procedure. Results suggested that HMEP caused the denaturation of β-sheet forms present initially in FBPC, and an increase of other structures including intermolecular β-sheet and/or aggregates—probably due to the formation of new intermolecular bonds. Moreover, although higher temperature during HMEP enhanced fibre-like structure formation, texturisation level could not be directly related to the protein conformation of the final high moisture, This work was supported by the SENSANALOG project funded by MICIU/AEI/10.13039/501100011033 and ERDF/EU [PID2021- 122285OR-I00], and by the CROPDIVA project funded by the European Union's Horizon 2020 research and innovation programme [Grant Agreement 101000847]. C. Barnés-Calle gratefully acknowledges receiving a predoctoral fellowship [FPU20/04009] from the Spanish MCIN/AEI/10.13039/501100011033 and “ESF Investing in your Future”, and a mobility grant from the Institute of Agrifood Research and Technology (IRTA) within the Incentives for Research Program 2023. Acknowledgements are extended to the SensorFINT COST action (CA19145) funded by the European Union for supporting C. Barnés-Calle and E. Fulladosa with mobility grants for Short Term Scientific Missions, to the Consolidated Research Group (TECQUAL 2021 SGR 00461), to the Agència de Gestió d'Ajuts Universitaris i de Recerca (AGAUR), to the CERCA Program of the Generalitat de Catalunya, and to the University of Copenhagen., info:eu-repo/semantics/publishedVersion
Helvia. Repositorio Institucional de la Universidad de Córdoba
Publication Artículo científico (JournalArticle)

Enhancing virgin olive oil authentication with Bayesian probabilistic models and near infrared spectroscopy

  • Garrido-Cuevas, María del Mar
  • Garrido-Varo, Ana
  • Marini, Federico
  • Sánchez, María-Teresa
  • Pérez-Marín, D.C.
Ensuring the authenticity of Extra Virgin olive oils is crucial due to the high risk of fraudulent practices associated with this valuable product. Traditional methods rely on physicochemical and organoleptic analyses, which are costly, time-consuming, and require specialized personnel. This study introduces probabilistic classification models utilizing Bayesian methods to enhance the reliability of Near Infrared Spectroscopy (NIRS) for olive oil (OO) quality control. Unlike traditional models, these methos allow the quantification of uncertainty, thereby improving decision-making precision in industrial applications. A total of 259 olive oils (104 extra virgin (EV), 71 virgin (V) and 84 lampante (L)) were analysed by two instruments with different optical configurations and sample presentation methods. Partial Least Square-Discriminant Analysis (PLS-DA) was applied to develop a two-step classification strategy: first, to discriminate non-LOO versus LOO categories, and then to predict the category of non-LOO samples (discriminating EVOO versus VOO). The models achieved a correct classification rate (CCR) of up to 86.36% for discriminating EVOO vs. VOO with the bench-top instrument, with more than half of the samples classified into their respective categories with a probability exceeding 75%, which highlights their effectiveness in ensuring the quality and authenticity of VOOs while optimizing resources in the olive oil industry. Similar results (81.82 %) were obtained for the portable device, despite differences in operational range, optical quality and price. The results demonstrate that probabilistic classification models can significantly improve the classification process by quantifying uncertainty, thereby complementing traditional methods and providing a robust framework for classifying olive oils categories.
Helvia. Repositorio Institucional de la Universidad de Córdoba
Publication Artículo científico (JournalArticle)

Evaluation of NIRS portable sensors for the determination of the physicochemical quality and maturity of intact mangoes

  • Téllez-García, Javier
  • Sánchez, María-Teresa
  • Gónzalez-Fernández, José-Jorge
  • Pérez-Marín, D.C.
Determining the on-tree maturity stage of mango fruits is essential for optimising harvest timing and maximising postharvest quality. This study investigates the feasibility of Near Infrared Spectroscopy (NIRS) as a reliable technology for establishing the optimal harvest time of mangoes. To achieve this, two portable near infrared (NIR) spectrophotometers —the MicroNIR™ Pro 1700 and the pre-calibrated F-751 Mango Quality Meter— with distinct technical specifications were systematically compared for in situ, on-tree analysis, a novel approach under Spanish production conditions. A total of 210 mangoes from the ‘Osteen’ and ‘Keitt’ cultivars were analysed. Predictive NIRS models were developed using the MicroNIR™ Pro 1700 to estimate skin colour, flesh colour, pulp firmness, dry matter (DM), and soluble solids content (SSC), employing modified partial least squares (MPLS) regression and various spectral pre-treatments. The F-751, with commercial calibrations based on other mango cultivars, was used solely to predict DM and SSC. The residual predictive deviation for cross-validation (RPDcv) values for the combined ‘Osteen’ and ‘Keitt’ sample set confirmed the efficacy of the MicroNIR™ in assessing flesh colour (L*) (1.83), pulp firmness (1.80), DM (1.55), and SSC (3.42). These findings confirm the viability of using NIRS technology as a reliable decision-support tool for monitoring the on-tree evolution of mango internal quality and determining the optimal harvest time. However, the routine implementation of the F-751 pre-calibrated models proved unsuitable for accurate predictions when applied to Spanish-grown mangoes. Therefore, this work addresses the limitations of generic, pre-calibrated models and provides practical recommendations for enhancing the reliability of commercial devices
Helvia. Repositorio Institucional de la Universidad de Córdoba
Publication Artículo científico (JournalArticle)

Near Infrared Spectroscopy in mango sorting lines for quality assessment and cultivar discrimination

  • Téllez-García, Javier
  • Sánchez, María-Teresa
  • Gónzalez-Fernández, José-Jorge
  • Pérez-Marín, D.C.
The mango industry is subject to increasingly stringent standards concerning fruit ripeness and quality, prompting the adoption of real-time sorting technologies. This study examined the feasibility of using near infrared spectroscopy (NIRS) under laboratory conditions to assess mango quality and classify fruit by cultivar on sorting lines. A total of 227 fruit samples from Spain’s main cultivars, ‘Osteen’ and ‘Keitt’, were analysed on a conveyor belt operating at two speeds (2.3 and 7 cm s−1) using a diode-array spectrophotometer (spectral range: 950–1650 nm). Modified partial least squares regression models, combined with various spectral pretreatments, were developed to predict skin and pulp colour, pulp firmness, dry matter content, and soluble solids content (SSC). In addition, partial least squares–discriminant analysis was applied for cultivar classification. The results demonstrated that NIRS technology enabled accurate prediction of SSC (Ratio of Prediction to Deviation for prediction, RPDp = 2.6) and pulp firmness (RPDp = 1.7) in less than one second for fruit moving at 7 cm s−1. At the lower belt speed (2.3 cm s−1), which allowed a longer scan duration (3 s), predictive performance improved for SSC (RPDp = 3.2) and firmness (RPDp = 2.1). Under both operational conditions, more than 98% of the fruit in the validation set were correctly classified by cultivar. These findings confirm the suitability of NIRS as a decision-support technology, enabling efficient, real-time classification by cultivar, ripeness, and quality.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Exploring the use of FTIR Amide I band deconvolution to investigate protein secondary structure and texturisation during high moisture extrusion

  • Barnés Calle, Clara
  • Gou, Pere
  • Fulladosa, Elena
  • van den Berg, Frans W.J.
Fourier transform infrared spectroscopy (FTIR) combined with Amide I band deconvolution has been used to investigate protein structural changes occurring during high moisture extrusion processing (HMEP). However, it is a sensitive, user-dependent technique that has sparked debate over its appropriate analytical approach. This paper aims to assess the suitability of FTIR Amide I band deconvolution to investigate protein structural changes in fava bean protein concentrate (FBPC) caused by temperature treatment and/or HMEP at different temperatures (110 ◦C, 135 ◦C and 165 ◦C), and to explore its relationship with the texturisation level of the obtained products. Influence of sample preparation and parameter selection during FTIR deconvolution procedure was also explored. To do so, FBPC was heated in a convection oven or subjected to HMEP at different temperatures (110, 135 or 165 ◦C), and Fourier self-deconvolution (FSD) and second derivative (SD) were explored as bandnarrowing methods to analyse protein conformation from FTIR spectra. FTIR Amide I band deconvolution showed high sensitivity to sample preparation and parameter selection during FSD and SD analytical procedure. Results suggested that HMEP caused the denaturation of β-sheet forms present initially in FBPC, and an increase of other structures including intermolecular β-sheet and/or aggregates—probably due to the formation of new intermolecular bonds. Moreover, although higher temperature during HMEP enhanced fibre-like structure formation, texturisation level could not be directly related to the protein conformation of the final high moisture, This work was supported by the SENSANALOG project funded by MICIU/AEI/10.13039/501100011033 and ERDF/EU [PID2021- 122285OR-I00], and by the CROPDIVA project funded by the European Union's Horizon 2020 research and innovation programme [Grant Agreement 101000847]. C. Barnés-Calle gratefully acknowledges receiving a predoctoral fellowship [FPU20/04009] from the Spanish MCIN/AEI/10.13039/501100011033 and “ESF Investing in your Future”, and a mobility grant from the Institute of Agrifood Research and Technology (IRTA) within the Incentives for Research Program 2023. Acknowledgements are extended to the SensorFINT COST action (CA19145) funded by the European Union for supporting C. Barnés-Calle and E. Fulladosa with mobility grants for Short Term Scientific Missions, to the Consolidated Research Group (TECQUAL 2021 SGR 00461), to the Agència de Gestió d'Ajuts Universitaris i de Recerca (AGAUR), to the CERCA Program of the Generalitat de Catalunya, and to the University of Copenhagen., info:eu-repo/semantics/publishedVersion