The UNEQ, PLS and MLF neural network methods in the modelling and prediction of the colour of young red wines from the Denomination of Origin ‘Rioja’

Abstract The modelling of the colour of young red wine of Denomination of Origin Rioja has become an issue of great practical importance. A UNEQ multivariate classification model for two categories (accepted wines and rejected wines), a partial least squares (PLS) model for the prediction of the value of the colour grading assigned by wine tasters and a multilayer feed forward (MLF) neural network capable of correctly classifying the wines in the two categories indicated were built based on oenologic parameters and psychophysical determination of colour.

[1]  D. Massart,et al.  UNEQ: a disjoint modelling technique for pattern recognition based on normal distribution , 1986 .

[2]  Johann Gasteiger,et al.  Neural Networks for Chemists: An Introduction , 1993 .

[3]  G. Dunteman.  Principal Components Analysis , 1989 .

[4]  Multivariate calibration : quantitative interpretation of non-selective chemical data , 1985 .

[5]  J. Friedman,et al.  A Statistical View of Some Chemometrics Regression Tools , 1993 .

[6]  S. Wold,et al.  A PLS kernel algorithm for data sets with many variables and fewer objects. Part 1: Theory and algorithm , 1994 .

[7]  S. Wold,et al.  The kernel algorithm for PLS , 1993 .

[8]  Silvia Lanteri,et al.  Chemometrics in Food Chemistry , 1987, Chemometrics and Species Identification.

[9]  J.R.M. Smits,et al.  Exploring the possibilities of applying artificial neural networks on problems in analytical chemistry , 1993 .

[10]  I. Wakeling,et al.  A test of significance for partial least squares regression , 1993 .

[11]  Silvia Lanteri,et al.  Full validation procedures for feature selection in classification and regression problems , 1992 .

[12]  M. S. Sánchez,et al.  Efficiency of multi-layered feed-forward neural networks on classification in relation to linear discriminant analysis, quadratic discriminant analysis and regularized discriminant analysis , 1995 .

[13]  Bruce R. Kowalski,et al.  Recent developments in multivariate calibration , 1991 .

[14]  M. C. Ortiz,et al.  Multiple standard addition with latent variables (MSALV): Application to the determination of copper in wine by using differential-pulse anodic stripping voltammetry , 1994 .

[15]  J. Zupan,et al.  Neural networks: A new method for solving chemical problems or just a passing phase? , 1991 .

[16]  J. Sáez,et al.  Typification of alcoholic distillates by multivariate techniques using data from chromatographic analyses , 1993 .

[17]  Riccardo Leardi,et al.  PARVUS: An Extendable Package of Programs for Data Exploration , 1988 .

[18]  Desire L. Massart,et al.  A non‐parametric class modelling technique , 1989 .

[19]  P. Sprent,et al.  Applied nonparametric statistical methods , 1988 .

[20]  S. D. Jong.  SIMPLS: an alternative approach to partial least squares regression , 1993 .

[21]  Roberto Todeschini,et al.  A fast method for the calculation of partial least squares coefficients , 1991 .

[22]  Philip Jonathan,et al.  Statistical thinking and technique for QSAR and related studies. Part II: Specific methods , 1994 .

[23]  Barry M. Wise,et al.  Identification of finite impulse response models with continuum regression , 1993 .

[24]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .