Identification of production area of Ossolano Italian cheese with chemometric complex approach

̈sson, J.D. Coı; Arlorio, Marco; Rinaldi, Maurizio

doi:10.1016/j.foodcont.2004.10.016

Cited by 36 publications

(22 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The interest of evolutionary optimisation methods for the resolution of complex problems related to agri-food is demonstrated by various recent publications. For example, [4] used genetic algorithms to identify the smallest discriminant set of variables to be used in certification process for an Italian cheese (validation of origin labels). [21] used GP to select the most significant wavenumbers produced by a Fourier transform infrared spectroscopy measurement device, in order to build a rapid detector of bacterial spoilage of beef.…”

Section: Modeling Expertise On Cheese Ripeningmentioning

confidence: 99%

“…• The discrimination capability for each phase, computed on the 5% best individuals of each class as the minimum of: ∆ = max i∈ [1,2,3,4] …”

Section: Aggregation Of Partial Solutions and Global Fitnessmentioning

confidence: 99%

“…This modification of the fitness landscape allows avoiding plateaus which would prevent the genetic algorithm to travel all over the search space. Here is the adjusted local fitness 4 :…”

Section: Search Space and Local Fitnessmentioning

confidence: 99%

See 2 more Smart Citations

Cooperative Coevolution for Agrifood Process Modeling

Barrière

Lutton

Wuillemin

et al. 2013

EVOLVE- A Bridge Between Probability, Set Oriented Numerics and Evolutionary Computation

View full text Add to dashboard Cite

On the contrary to classical schemes of evolutionary optimisations algorithms, single population Cooperative Co-evolution techniques (CCEAs, also called "Parisian" approaches) make it possible to represent the evolved solution as an aggregation of several individuals (or even as a whole population). In other words, each individual represents only a part of the solution. This scheme allows simulating the principles of Darwinian evolution in a more economic way, which results in gain in robustness and efficiency. The counterpart however is a more complex design phase. In this chapter, we detail the design of efficient CCEAs schemes on two applications related to the modeling of an industrial agri-food process. The experiments correspond to complex optimisations encountered in the modeling of a Camembert-cheese ripening process. Two problems are considered:• A deterministic modeling problem, phase prediction, for which a search for a closed form tree expression is performed using genetic programming (GP).• A Bayesian network structure estimation problem. The novelty of the proposed approach is based on the use of a two step process based on an intermediate representation called independence model. The search for an independence model is formulated as a complex optimisation problem, for which the CCEA scheme is particularly well suited. A Bayesian network is finally deduced using a deterministic algorithm, as a representative of the equivalence class figured by the independence model.

show abstract

Section: Modeling Expertise On Cheese Ripeningmentioning

confidence: 99%

“…• The discrimination capability for each phase, computed on the 5% best individuals of each class as the minimum of: ∆ = max i∈ [1,2,3,4] …”

Section: Aggregation Of Partial Solutions and Global Fitnessmentioning

confidence: 99%

See 1 more Smart Citation

Cooperative Coevolution for Agrifood Process Modeling

Barrière

Lutton

Wuillemin

et al. 2013

EVOLVE- A Bridge Between Probability, Set Oriented Numerics and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…The multilayer perceptron ANN (Multilayer Perceptron -MLP), also known as progressive multilayer network (feedforward), is one of the most widely used because of its versatility and significant results in solving complex problems (Barile et al, 2006;Vafaei et al, 2009;Eyng and Fileti, 2010). A multilayer neural network is typically formed of layers of aligned neurons, with the variables being presented in the first layer, usually referred to as the input layer.…”

Section: Neural Network Structure and Learningmentioning

confidence: 99%

Neural networks to formulate special fats

et al. 2012

View full text Add to dashboard Cite

RESUMEN Utilización de redes neuronales para formular grasas técnicas.Las redes neuronales son una rama de la inteligencia artificial basadas en la estructura y funcionamiento de sistemas biológicos, teniendo como principal característica la capacidad de aprender y generalizar conocimiento. Estas son utilizadas en la resolución de problemas complejos, en los cuales los sistemas computacionales tradicionales presentan una eficiencia baja. Hasta la fecha, han sido propuestas aplicaciones para los más diversos sectores y actividades. En el área de grasas y aceites, la utilización de redes neuronales se ha concentrado principalmente en dos asuntos: la detección de adulteraciones y la formulación de productos grasos. La formulación de grasas para uso específico es el caso clásico de problema complejo donde un experto o grupo de expertos definen las proporciones de cada base, que al ser mezcladas proporcionaran características especificadas para el producto deseado. Algunos sistemas computacionales convencionales están disponibles actualmente para auxiliar a los expertos, sin embargo, estos sistemas presentan algunas deficiencias. En este artículo será descrito con detalles, un sistema para la formulación de productos grasos por redes neuronales (MIX) a partir de 3 o más componentes. Todas las etapas del desarrollo, incluyendo el diseño, construcción, entrenamiento, evaluación y operación de la red serán mostradas. PALABRAS CLAVE: Blending -Formulación -Grasas hidrogenadas -Grasas interesterificadas -Grasas técnicas -Redes neuronales. SUMMARY Neural networks to formulate special fats.Neural networks are a branch of artificial intelligence based on the structure and development of biological systems, having as its main characteristic the ability to learn and generalize knowledge. They are used for solving complex problems for which traditional computing systems have a low efficiency. To date, applications have been proposed for different sectors and activities. In the area of fats and oils, the use of neural networks has focused mainly on two issues: the detection of adulteration and the development of fatty products. The formulation of fats for specific uses is the classic case of a complex problem where an expert or group of experts defines the proportions of each base, which, when mixed, provide the specifications for the desired product. Some conventional computer systems are currently available to assist the experts; however, these systems have some shortcomings. This article describes in detail a system for formulating fatty products, shortenings or special fats, from three or more components by using neural networks (MIX). All stages of development, including design, construction, training, evaluation, and operation of the network will be outlined.

show abstract

“…The determination of food authenticity and geographic origin becomes now a crucial issue in food quality control and safety (Barile, 2005;Karoui, 2007). Development of new sophisticated techniques for the authentication of food products grows rapidly due to increased consumer awareness of food safety and quality issues (Reid et al 2006; Koca et al 2010).…”

Section: Introductionmentioning

confidence: 99%

Preliminary Discrimination of Cheese Adulteration by FT-IR Spectroscopy

et al. 2014

View full text Add to dashboard Cite

The present work describes a preliminary study to compare some traditional Romanian cheeses and adulterated cheeses using Attenuated Total Reflectance-Fourier transform infrared spectroscopy (ATR-FTIR). For PLS model calibration (6 concentration levels) and validation (5 concentration levels) sets were prepared from commercial Dalia Cheese from different manufacturers by spiking it with palm oil at concentrations ranging 2-50 % and 5-40 %, respectively. Fifteen Dalia Cheese were evaluated as external set. The spectra of each sample, after homogenization, were acquired in triplicate using a FTIR Shimatsu Prestige 21 Spectrophotometer, with a horizontal diamond ATR accessory in the MIR region 4000-600 cm -1. Statistical methods as PLS were applied using MVC1 routines written for Matlab R2010a. As first step the optimal condition for PLS model were obtained using cross-validation on the Calibration set. Spectral region in 3873-652 cm -1 , and 3 PLS-factors were stated as the best conditions and showed an R 2 value of 0.9338 and a relative error in the calibration of 17.2%. Then validation set was evaluated, obtaining good recovery rates (108%) and acceptable dispersion of the data (20%). The curve of actual vs. predicted values shows slope near to 1 and origin close to 0, with an R 2 of 0.9695. When the external sample set was evaluated, samples F19, F21, F22 and F24, showed detectable levels of palm fats. The results proved that FTIR-PLS is a reliable non-destructive technique for a rapid quantification the level of adulteration in cheese. The spectroscopic methods could assist the quality control authority, traders and the producers to discriminate the adulterated cheeses with palm oil.

show abstract

Identification of production area of Ossolano Italian cheese with chemometric complex approach

Cited by 36 publications

References 27 publications

Cooperative Coevolution for Agrifood Process Modeling

Cooperative Coevolution for Agrifood Process Modeling

Neural networks to formulate special fats

Preliminary Discrimination of Cheese Adulteration by FT-IR Spectroscopy

Contact Info

Product

Resources

About