Application of artificial neural network in food classification

Dębska, B.; Guzowska-Świder, B.

doi:10.1016/j.aca.2011.06.033

Cited by 103 publications

(59 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Among a large number of classification models, we select five representative methods for comparisons. They are Euclidean distance to centroids (EDC) [11], fuzzy ARTMAP network [12,13], multilayer perceptron neural network (MLP) [14][15][16], fisher linear discrimination analysis (FLDA) [17], and support vector machine (SVM) [18,19].…”

Section: Introductionmentioning

confidence: 99%

Classification of multiple indoor air contaminants by an electronic nose and a hybrid support vector machine

Zhang

Tian

Nie

et al. 2012

Sensors and Actuators B: Chemical

136

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Classification of multiple indoor air contaminants by an electronic nose and a hybrid support vector machine

Zhang

Tian

Nie

et al. 2012

Sensors and Actuators B: Chemical

136

View full text Add to dashboard Cite

“…La creciente necesidad de gestión de calidad en industrias de alimentos, ha permitido que se construyan sistemas con toma de decisiones automatizadas para la evaluación de productos. La gestión de calidad por su parte conlleva en la actualidad a la implementación de métodos que permitan clasificar grupos de alimentos con propiedades específicas similares teniendo en cuenta la marca, el origen geográfico, su autenticidad o adulteración [25].…”

Section: Introductionunclassified

Técnicas de análisis multivariado, modelamiento factorial múltiple y PLS-PATH para estudio y clasificación de tipos de mieles venezolanas de los estados de Lara y Yaracuy / Multivariate techniques, factorial multiple analysis and PLS-PATH modeling for study and classification of venezuelan honeys from states of Lara and Yaracuy

2017

View full text Add to dashboard Cite

La miel es un producto natural elaborado principalmente a partir del néctar de las flores, su calidad final final esta en función de su origen botánico y geográfico y su variabilidad es amplia inclusive para mieles de la misma región. En éste trabajo se han evaluado y clasificado tipos de venezolanas de los estados Lara y Yaracuy, tomando como referencia los parámetros fisicoquímicos de color, cromaticidad del sistema CIELab, pH, acidez libre (XAL), azucares totales (XS), humedad (XH), cenizas (XC), conductividad eléctrica (CE), densidad y actividad de agua (aw). Adicionalmente se han relacionado los atributos sensoriales y propiedades intrínsecas de las mieles para el proceso de clasificación de mieles homogéneas a partir del análisis multivariado, factorial múltiple y PLS-PATH. La relación entre las respuestas y la regresión, revela tipos de mieles con 50% dominantemente ámbar (A), 40% ámbar claro (LA) y 10 % ámbar obscura (DA) de naturaleza multifloral. Las propiedades fisicoquímicas y atributos sensoriales son conducentes a la diferenciación en virtud a su origen geográfico.

show abstract

“…Methods used for classification vary from Bayes classifiers and k-NN algorithms , Artificial Neural Networks (ANNs) (Debska and Guzowska-Swider, 2011;Gocławski et al, 2012) and Support Vector Machines (SVMs) (Hsu and Lin, 2002;Jeleń et al, 2008) to classifier ensembles (Woźniak and Krawczyk, 2012), The classification accuracy depends greatly on the method used, but also on the underlying problem, i.e., the characteristics of the data on which the classification method is applied.…”

Section: Classification and Feature Selectionmentioning

confidence: 99%

A differential evolution approach to dimensionality reduction for classification needs

Martinović

Bajer

Zorić

2014

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

The feature selection problem often occurs in pattern recognition and, more specifically, classification. Although these patterns could contain a large number of features, some of them could prove to be irrelevant, redundant or even detrimental to classification accuracy. Thus, it is important to remove these kinds of features, which in turn leads to problem dimensionality reduction and could eventually improve the classification accuracy. In this paper an approach to dimensionality reduction based on differential evolution which represents a wrapper and explores the solution space is presented. The solutions, subsets of the whole feature set, are evaluated using the k-nearest neighbour algorithm. High quality solutions found during execution of the differential evolution fill the archive. A final solution is obtained by conducting k-fold crossvalidation on the archive solutions and selecting the best one. Experimental analysis is conducted on several standard test sets. The classification accuracy of the k-nearest neighbour algorithm using the full feature set and the accuracy of the same algorithm using only the subset provided by the proposed approach and some other optimization algorithms which were used as wrappers are compared. The analysis shows that the proposed approach successfully determines good feature subsets which may increase the classification accuracy.

show abstract

Application of artificial neural network in food classification

Cited by 103 publications

References 50 publications

Classification of multiple indoor air contaminants by an electronic nose and a hybrid support vector machine

Classification of multiple indoor air contaminants by an electronic nose and a hybrid support vector machine

A differential evolution approach to dimensionality reduction for classification needs

Contact Info

Product

Resources

About