Look-up in Google Scholar
Title: Hyperspectral imaging for food quality control: cocoa beans hybrids and chia seeds shelf-life
Other Titles: Imagens hiperespectrais para o controle da qualidade de alimentos: híbridos de graos de cacau e vida de prateleira de sementes de chia
Advisor(s): Fernandes Barbin, Douglas
OCDE field: https://purl.org/pe-repo/ocde/ford#2.11.01
Issue Date: 2020
Institution: Universidade Estadual de Campinas
Abstract: Utiliza el HSI para el control de calidad de productos agrícolas, que incluye la autenticación de híbridos de cacao en grano y la estimación de la vida útil de las semillas de chía. Para las semillas de chía, las muestras se almacenaron a 25, 35 y 45 °C durante 180 días. El objetivo fue utilizar imágenes hiperespectrales y análisis multivariado para desarrollar una metodología para estimar la vida útil de las semillas de chía, llamada Multivariate Accelerated Shelf Life Testing (MASLT). Los espectros de las semillas de chía donde la acidez aumentó en un 75 % desde el valor inicial se utilizaron para calcular el valor de corte (-0,9853). Las estimaciones de vida útil fueron 1300, 798 y 90 días para las semillas de chía almacenadas a 25, 35 y 45 °C, respectivamente. Por otro lado, los granos de cacao se transportaron al Centro de Investigación de Wallonie (Bélgica), donde se adquirieron imágenes hiperespectrales de 1100 a 2500 nm. PLS-DA y SVM se implementaron para clasificar los híbridos de cacao en grano. Los resultados mostraron que PLS-DA y SVM muestran resultados comparables para modelos de dos clases (híbridos), pero SVM (3,8–23,1 % de error de predicción) fue superior a PLS-DA (4,4–34,4 % de error de predicción) cuando las cinco clases (híbridos) se incluyeron en un modelo.

Hyperspectral imaging (HSI) enables simultaneous acquisition of spectral and spatial information. In this work, HSI was used for quality control of agricultural products, which includes the authentication of cocoa bean hybrids and the estimation of shelf-life of chia seeds. Regarding the chia seeds study, samples were stored at 25, 35 and 45 ° C for 180 days, for accelerated shelf life analyzes. From time to time, chia samples were removed from storage to acquire hyperspectral images (900 - 2500 nm), acidity analysis, and fatty acid profile. The objective was to use hyperspectral images and multivariate analysis to develop a methodology for estimating the shelf-life of chia seeds, called Multivariate Accelerated Shelf Life Testing (MASLT). Principal Component Analysis (PCA) was used to study the variability during storage, and then, the PC scores were used to model the kinetics and estimate the parameters of the Arrhenius Equation, and finally to estimate the shelf life. Furthermore, for the first time a new strategy was proposed to validate this methodology, which we called "Resampling", where the samples from the validation set were projected onto the calibration set with a reasonable number of iterations. PC1 scores and kinetic charts were built fitting the time-related PC1 scores versus time by a fused kinetic model (R² > 0.85). The spectra of chia seeds where acidity increased at 75% from initial value were used to calculate the cut-off value (-0.9853). The shelf life estimations were 1300, 798 and 90 days for chia seeds stored at 25, 35 and 45 °C, respectively. For the first time, a reliable methodology is proposed to validate that all samples were correctly predicted using PC1 scores. In the second study, cocoa beans hybrids (five) were grown and processed under the same conditions in CEPLAC (Medicilândia, Para, Brazil). The cocoa beans were then transported to the Wallonie Research Center (Belgium), where hyperspectral images in the 1100 - 2500 nm range were acquired. Partial least square discriminant analysis (PLS-DA) and Support vector machine (SVM) was implemented to classify cocoa bean hybrids, (1) two classes of hybrids and (2) five classes of hybrids. Additionally, a new set of images was used for external pixel-to-pixel validation. The results showed that PLS-DA and SVM demonstrate comparable results for two-class (hybrids) models, but SVM (3.8–23.1% prediction error) was superior to PLS-DA (4.4– 34.4% prediction error) when all five classes (hybrids) were included in a model. Pixelto- pixel prediction results on a set of external images showed a correct classification rate of 50 - 100%. The results for both the two-class models and the five-class model were comparable with polymerase chain reaction techniques. The results show the potential of HSI for quality control of agricultural products, both for authentication and estimation of shelf life.
Note: Descargue el texto completo en el repositorio institucional de la Universidade Estadual de Campinas: https://hdl.handle.net/20.500.12733/1641036
Discipline: Ingeniería de Alimentos
Grade or title grantor: Universidade Estadual de Campinas. Faculdade de Engenharia de Alimentos
Grade or title: Maestro en Ingeniería de Alimentos
Juror: Fernandes Barbin, Douglas; Blasco Ivars, José; Aleixos Borras, Nuria
Register date: 6-Oct-2022

Files in This Item:
File Description SizeFormat 
CruzTiradoLJP.pdf
  Restricted Access
Disertación (abierta en repositorio de origen)3.21 MBAdobe PDFView/Open Request a copy
Autorizacion.pdf
  Restricted Access
Autorización del registro509.05 kBAdobe PDFView/Open Request a copy


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.