Classification of Slovak white wines using artificial neural networks and discriminant techniques

Abstract This work demonstrates the possibility to use artificial neural networks (ANN) for the classification of white varietal wines. A multilayer perceptron technique using quick propagation and quasi-Newton propagation algorithms was the most successful. The developed methodology was applied to classify Slovak white wines of different variety, year of production and from different producers. The wine samples were analysed by the GC–MS technique taking into consideration mainly volatile species, which highly influence the wine aroma (terpenes, esters, alcohols). The analytical data were evaluated by means of the ANN and the classification results were compared with the analysis of variance (ANOVA). A good agreement amongst the applied computational methods has been observed and, in addition, further special information on the importance of the volatile compounds for the wine classification has been provided.

[1]  J. Havel,et al.  Capillary zone electrophoresis determination of galanthamine in biological fluids and pharmaceutical preparatives: Experimental design and artificial neural network optimization , 1999, Electrophoresis.

[2]  J. Fernández-López,et al.  Varietal classification of young red wines in terms of chemical and colour parameters , 1996 .

[3]  R J Poppi,et al.  Application of artificial neural networks to the classification of soils from São Paulo State using near-infrared spectroscopy. , 2001, The Analyst.

[4]  Use of artificial neural networks in capillary zone electrophoresis , 1999 .

[5]  V. Dohnal,et al.  Prediction of chiral separations using a combination of experimental design and artificial neural networks. , 1999, Chirality.

[6]  A. Rapp,et al.  Untersuchungen des Trauben- und Weinaromas , 1993 .

[7]  J. Havel,et al.  High-performance liquid chromatographic determination of deoxycytidine monophosphate and methyldeoxycytidine monophosphate for DNA demethylation monitoring: experimental design and artificial neural networks optimisation. , 2001, Journal of chromatography. B, Biomedical sciences and applications.

[8]  Josef Havel,et al.  Neural networks for optimization of high-performance capillary zone electrophoresis methods: A new method using a combination of experimental design and artificial neural networks , 1998 .

[9]  Johanna Smeyers-Verbeke,et al.  Multivariate determination of the geographical origin of wines from four different countries , 2007 .

[10]  A. Noble,et al.  Profiling Zinfandel Wines by Sensory and Chemical Analyses , 1987, American Journal of Enology and Viticulture.

[11]  Pascal Schlich,et al.  Varietal and geographic classification of French red wines in terms of major acids , 1989 .

[12]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[13]  J. Havel,et al.  Data evaluation for soft drink quality control using principal component analysis and back-propagation neural networks. , 2000, Journal of food protection.

[14]  Roberto Todeschini,et al.  Geographical classification of wine and olive oil by means of classification and influence matrix analysis (CAIMAN). , 2006, Analytica chimica acta.

[15]  P. Schlich,et al.  Varietal and Geographic Classification of French Red Wines in Terms of Elements, Amino Acids and Aromatic Alcohols , 1988 .

[16]  G. Li,et al.  An integrated approach utilizing artificial neural networks and SELDI mass spectrometry for the classification of human tumours and rapid identification of potential biomarkers , 2002, Bioinform..

[17]  D. Castner,et al.  Classification of adsorbed protein static ToF‐SIMS spectra by principal component analysis and neural networks , 2002 .

[18]  G. Capodaglio,et al.  Analytical Parameters in the Characterization of Three Venetian Wines. Application of the Statistical Linear Discriminant Analysis , 1980, American Journal of Enology and Viticulture.

[19]  V. Dohnal,et al.  Quantitative analysis of chiral compounds from unresolved peaks in capillary electrophoresis using multivariate calibration with experimental design and artificial neural networks. , 2002, Chirality.

[20]  Characterization of elementary wines of Vitis vinifera varieties by pattern recognition of free amino acid profiles , 1989 .

[21]  M. Dizy,et al.  Varietal Differentiation of Must and Wines by Means of Protein Fraction , 1993, American Journal of Enology and Viticulture.

[22]  V. Ferreira,et al.  A Study of Factors Affecting Wine Volatile Composition and its Application in Discriminant Analysis , 1996 .

[23]  Josef Havel,et al.  Evaluation of chemical equilibria with the use of artificial neural networks , 2002 .

[24]  J. Zupan,et al.  Neural Networks in Chemistry , 1993 .

[25]  James L. McClelland.  Explorations In Parallel Distributed Processing , 1988 .

[26]  Geoffrey E. Hinton,et al.  Proceedings of the 1988 Connectionist Models Summer School , 1989 .

[27]  M. C. Horrillo,et al.  Differentiation of red wines using an electronic nose based on surface acoustic wave devices. , 2006, Talanta.

[28]  Josef Havel,et al.  Artificial neural networks for quantification in unresolved capillary electrophoresis peaks , 2002 .

[29]  Paul R. Haddad,et al.  Prediction of retention times for anions in ion chromatography using Artificial Neural Networks , 1999 .

[30]  M. Cliff,et al.  Sensory and compositional profiles of British Columbia Chardonnay and Pinot noir wines , 1996 .

[31]  José Pedro Santos,et al.  Wine classification with a zinc oxide SAW sensor array , 2006 .

[32]  M. C. Horrillo,et al.  Classification of white wine aromas with an electronic nose. , 2005, Talanta.