SABER-ULA, Universidad de Los Andes - Mérida - Venezuela >
Facultades >
Facultad de Ciencias >
Unidades de Investigación de la Facultad de Ciencias >
Laboratorios de Investigación >
Laboratorio de Espectroscopía Molecular >
Articulos, Pre-prints (Laboratorio de Espectroscopía Molecular) >


Título: Classification of Venezuelan spirituous beverages by means of discriminant analysis and artificial neural networks based on their Zn, Cu and Fe concentrations
Autores: Hernández C., Edwin A.
Ávila G., Rita M.
Capote, Tarcisio
Rivas E., Francklin I.
Pérez M., Anna G.
Correo Electrónico: ehernandez@ucla.edu.ve
ritaavila@ucla.edu.ve
rivas@ula.ve
gabipm@ula.ve
Editor: SABER ULA
Resumen: Classification of Venezuelan spirituous beverages by means of discriminant analysis and artificial neural networks based on their Zn, Cu and Fe concentrations (Hernández C., Edwin A.; Ávila G., Rita M.; Capote, Tarcisio; Rivas E., Francklin I.; Pérez M., Anna G.) Abstract Copper, zinc and iron concentrations were determined in ''aguardiente de Cocuy de Penca'' (Cocuy de Penca firewater), a spirituous beverage very popular in the North-Western region of Venezuela, by flame atomic absorption spectrometry (FAAS). These elements were selected for their presence can be traced to the (illegal) manufacturing process of the aforementioned beverages. Linear and quadratic discriminant analysis (QDA), and artificial neural networks (ANNs) trained with the backpropagation algorithm were employed for estimating if such beverages can be distinguished based on the concentrations of these elements in the final product, and whether it is possible to assess the geographic location of the manufacturers (Lara or Falco´n states) and the presence or absence of sugar in the end product. A linear discriminant analysis (LDA) performed poorly, overall estimation and prediction rates being 51.7% and 50.0%, respectively. A QDA showed a slightly better overall performance, yet unsatisfactory (estimation: 79.2%, prediction: 72.5%). Various ANNs, comprising a linear function (L) in the input layer, a sigmoid function (S) in the hidden layer(s) and a hyperbolic tangent function (T) in the output layer, were evaluated. Of the networks studied, the (3L:5S:7S:4T) gave the highest estimation (overall: 96.5%) and prediction rates (overall: 97.0%), demonstrating the superb performance of ANNs for classification purposes. Artículo publicado en: Talanta 60 (2003) 1259-1267
Fecha: 26-Jan-2006
Palabras Clave: Iron
Copper
Zinc
Classification
Cocuy
Spirituous beverages
Linear discriminant analysis (LDA)
Quadratic discriminant analysis (QDA)
Artificial neural networks (ANNs)
Backpropagation algorithm
URI: http://www.saber.ula.ve/handle/123456789/16367
Aparece en colecciones:Articulos, Pre-prints (Laboratorio de Espectroscopía Molecular)
Articulos, Pre-prints (Facultad de Ciencias Económicas y Sociales)
Artículos, Pre-prints (Facultad de Ingeniería)
Articulos, Pre-prints (Facultad de Ciencias)
Articulos, Pre-prints (Instituto de Estadística Aplicada y Computación (IEAC))

Archivos en estos artículos:

Archivo Descripción TamañoFormato
classification-venezuelan.pdf247.39 kBAdobe PDFVer/Abrir
resumen.htm2 kBHTMLVer/Abrir

Todos los artículos en Dspace están protegidos con Derecho de Autor, todos los derechos reservados, a menos que se indique lo contrario.

 

Licencia Creative Commons
Todos los documentos publicados en este repositorio se distribuyen bajo una
Licencia Creative Commons Atribución-NoComercial-CompartirIgual 3.0 Venezuela.

Repositorio Institucional de la Universidad de Los Andes, Mérida, Venezuela - Comentarios
Software DSpace Copyright © 2002-2007 MIT and Hewlett-Packard -
DSpace Add-on Statistics of RepositóriUM © University of Minho.