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

被引:64
作者
Kruzlicova, Dasa [1 ]
Mocak, Jan [1 ,2 ]
Balla, Branko [1 ]
Petka, Jan [3 ]
Farkova, Marta [4 ]
Havel, Josef [4 ]
机构
[1] Slovak Tech Univ Bratislava, Fac Chem & Food Technol, Inst Analyt Chem, SK-81237 Bratislava, Slovakia
[2] Univ Ss Cyril & Methodius, Fac Nat Sci, Dept Chem, SK-91701 Trnava, Slovakia
[3] Food Res Inst, SK-82475 Bratislava, Slovakia
[4] Masaryk Univ, Fac Sci, Dept Analyt Chem, CZ-61137 Brno, Czech Republic
关键词
Wine classification; Wine authentication; Artificial neural networks; Feature selection; ANOVA; CAPILLARY-ZONE-ELECTROPHORESIS; PRINCIPAL COMPONENT ANALYSIS; FRENCH RED WINES; EXPERIMENTAL-DESIGN; GEOGRAPHIC CLASSIFICATION; ELECTRONIC NOSE; VARIETIES; OPTIMIZATION; GRAPE; TERMS;
D O I
10.1016/j.foodchem.2008.06.047
中图分类号
O69 [应用化学];
学科分类号
081704 ;
摘要
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. (C) 2008 Elsevier Ltd. All rights reserved.
引用
收藏
页码:1046 / 1052
页数:7
相关论文
共 49 条
[1]  
Almela L, 1996, J SCI FOOD AGR, V70, P173, DOI 10.1002/(SICI)1097-0010(199602)70:2<173::AID-JSFA479>3.3.CO
[2]  
2-A
[3]   An integrated approach utilizing artificial neural networks and SELDI mass spectrometry for the classification of human tumours and rapid identification of potential biomarkers [J].
Ball, G ;
Mian, S ;
Holding, F ;
Allibone, RO ;
Lowe, J ;
Ali, S ;
Li, G ;
McCardle, S ;
Ellis, IO ;
Creaser, C ;
Rees, RC .
BIOINFORMATICS, 2002, 18 (03) :395-404
[4]   Geographical classification of wine and olive oil by means of classification and influence matrix analysis (CAIMAN) [J].
Ballabio, D ;
Mauri, A ;
Todeschini, R ;
Buratti, S .
ANALYTICA CHIMICA ACTA, 2006, 570 (02) :249-258
[5]  
Bishop Christopher M, 1995, Neural networks for pattern recognition
[6]   Artificial neural networks for quantification in unresolved capillary electrophoresis peaks [J].
Bocaz-Beneventi, G ;
Latorre, R ;
Farková, M ;
Havel, J .
ANALYTICA CHIMICA ACTA, 2002, 452 (01) :47-63
[7]  
Capron X., 2006, FOOD CHEM, V225, P559
[8]   Sensory and compositional profiles of British Columbia Chardonnay and Pinot noir wines [J].
Cliff, MA ;
Dever, MC .
FOOD RESEARCH INTERNATIONAL, 1996, 29 (3-4) :317-323
[9]  
DELACALLEGARCIA D, 1998, VITIS, V37, P181
[10]  
DELAPRESAOWENS C, 1995, AM J ENOL VITICULT, V46, P5