Prediction of the type of milk and degree of ripening in cheeses by means of artificial neural networks with data concerning fatty acids and near infrared spectroscopy

Soto-Barajas, Milton C.; González-Martín, M.I.; Salvador-Esteban, Javier; Hernández-Hierro, José Miguel; Moreno, Vidal; Quintana, Ana María Vivar; Revilla, I.; Ortega, Iris Lobos; Morón-Sancho, Raúl; Curto, Belén

doi:10.1016/j.talanta.2013.04.043

Cited by 28 publications

(19 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial neural networks have been used successfully in the dairy industry to predict shelf life (as reviewed by Goyal and Goyal, 2012), physicochemical composition (Etzion et al, 2004;Khanmohammadi et al, 2009), and sensory characteristics (Singh et al, 2009;; to discriminate varieties, geographical origin, or seasonal variations (He et al, 2005;Cruz et al, 2009Cruz et al, , 2013Gori et al, 2012); to control milk quality (Hettinga et al, 2008;Souza et al, 2011); and to model operational parameters during product manufacture (Funahashi and Horiuchi, 2008). As far as cheese manufacture is concerned, ANN have been applied mainly for authentication, classification, or traceability purposes (Pillonel et al, 2005;Zeppa et al, 2005;Barile et al, 2006;Verdini et al, 2007;Cevoli et al, 2011Cevoli et al, , 2013 but also for predicting ripening (Soto-Barajas et al, 2013) or moisture (Jimenez-Marquez et al, 2003 or the optimization of the cheese-making process (Paquet et al, 2000;Horiuchi et al, 2004).…”

Section: Introductionmentioning

confidence: 99%

Estimation of somatic cell count levels of hard cheeses using physicochemical composition and artificial neural networks

Hernández-Ramos

Quintana

Revilla

2019

Journal of Dairy Science

View full text Add to dashboard Cite

This study addresses the prediction of the somatic cell counts of the milk used in the production of sheep cheese using artificial neural networks. To achieve this objective, the neural network was designed using 33 parameters of the physicochemical composition of the cheeses obtained after they have been matured for 12 mo as input data. The physicochemical analysis of the cheeses revealed that the somatic cell count level of the cheese has a significant influence on the amount of protein, fat, dry extract, and fatty acids. When properly set up, the neural network allows the correct classification of the cheeses (100% of correct results in both training and test phases) and therefore their samples in each of the 3 nominal output variables (low, average, and high somatic cell counts). The fatty composition of the cheeses, individual fatty acids, and fat acidity are the variables that most affect the correct operation of the neural network.

show abstract

Section: Introductionmentioning

confidence: 99%

Estimation of somatic cell count levels of hard cheeses using physicochemical composition and artificial neural networks

Hernández-Ramos

Quintana

Revilla

2019

Journal of Dairy Science

View full text Add to dashboard Cite

show abstract

“…The RNA model was found to require a storage temperature below -25 °C and microwave heating below -15 °C to maintain the acceptability of the samples for more than 40 days. On the other hand, Soto-Barajas [17] used RNA for the prediction of maturation time and the variation of milk mixtures (cow, sheep and goat) for cheese making, using the content of 19 fatty acids as input values. and near infrared spectral values (NIR).…”

Section: Determination Of Shelf Life and Maturity Stagesmentioning

confidence: 99%

Neural networks in food industry

Correa¹,

Castillo²,

Martelo³

2018

ces

View full text Add to dashboard Cite

In the present review we study the application of artificial neural networks in food industry, classifying the information obtained in different categories and the most used programs for its development. The prediction of parameter on operation such as drying, heat treatment, food classification and quality analysis are the main objective for RNA application. Multilayer with feedback propagation is the model most used being Matlab, the software par excellence for its development. Application of artificial neural network in food industry proved to be a useful tool to determine their quality through non-invasive, low-cost and real time processes.

show abstract

“…Optical spectroscopy techniques have been widely used to study dairy products due to their advantages of being rapid, having high sensitivity, and being non-invasive. Near-infrared spectroscopy (NIR) technique allows rapid and accurate determination of typical chemical structures presenting in nutrients, such as C-H, N-H, and O-H, due to their characteristic absorption spectrum in the near-infrared range (750-2500 nm) caused by the molecular transition [6][7][8][9][10]. Based on visible/NIR spectroscopy, principal component analysis (PCA) and artificial neural network (ANN) has been used for the discrimination of five kinds of yogurt, as well as for the determination of the sugar content and acidity of yogurt [11,12].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Yogurt Quality during Storage by Fluorescence Spectroscopy

et al. 2019

View full text Add to dashboard Cite

The physico-chemical parameters including pH and viscosity, and the fluorescence signal induced by fluorescent compounds presenting in yogurts such as riboflavin and porphyrin were measured during one week’s storage at room temperature when five brands of yogurt samples were exposed to ambient air. The fluorescence spectra of yogurt showed four evident emission peaks, 525 nm, 633 nm, 661 nm, and 672 nm. To quantitatively investigate the quality of yogurt during deteriorating, a calculating method of the average rate of change (ARC) was proposed to study the relative change of fluorescence intensity in the spectral range of 600 to 750 nm associated with porphyrin and chlorin compounds. During the storage, the time evolution of two ARC, pH value, and viscosity were regular. Moreover, the ARC showed a good linear relationship with pH value and viscosity of yogurt. Further, multiple linear regression (MLR) models using two ARC as independent variables were developed to verify the dependence of fluorescence signal with pH value and viscosity, which showed a good linear relationship with an R-square of more than 85% for each class of yogurt. The results demonstrate that fluorescence spectra have a great potential to predict the quality of yogurt.

show abstract

Prediction of the type of milk and degree of ripening in cheeses by means of artificial neural networks with data concerning fatty acids and near infrared spectroscopy

Cited by 28 publications

References 41 publications

Estimation of somatic cell count levels of hard cheeses using physicochemical composition and artificial neural networks

Estimation of somatic cell count levels of hard cheeses using physicochemical composition and artificial neural networks

Neural networks in food industry

Evaluation of Yogurt Quality during Storage by Fluorescence Spectroscopy

Contact Info

Product

Resources

About