Characterization of the traditional Cypriot spirit Zivania by means of Counterpropagation Artificial Neural Networks

Multivariate chemometric techniques, such as Principal Component Analysis and Discriminant Analysis, were previously used to determine the authenticity of the Cypriot traditional spirit Zivania, but these techniques revealed difficulties in making this characterization. In the present paper, a non-linear classification model has been built by means of Counterpropagation Artificial Neural Networks. The aim of this model is the characterization of Zivania and the differentiation of this alcoholic beverage from other, similar, beverages from all over the world, especially Europe. This procedure may be an ideal tool for describing Zivania's uniqueness, since the mapping based on the Neural Networks has shown acceptable predictive capabilities. Moreover, the role of each variable in the classification model has been considered: Counterpropagation Artificial Neural Network results have been analysed by means of Principal Component Analysis, in order to study which variables have a real discriminant role in the classification model. This procedure appeared as a promising tool to study the relationship between variables and classes in a global way and not variable by variable, and to obtain a multivariate overview of variable behaviour in the classification model. © 2006 Elsevier B.V. All rights reserved.