THE UNEQ, PLS AND MLF NEURAL-NETWORK METHODS IN THE MODELING AND PREDICTION OF THE COLOR OF YOUNG RED WINES FROM THE DENOMINATION-OF-ORIGINRIOJA

The modelling of the colour of young red wine of Denomination of Origi n Rioja has become an issue of great practical importance. A UNEQ mult ivariate classification model for two categories (accepted wines and r ejected wines), a partial least squares (PLS) model for the prediction of the value of the colour grading assigned by wine tasters and a mul tilayer feed forward (MLF) neural network capable of correctly classif ying the wines in the two categories indicated were built based on oen ologic parameters and psychophysical determination of colour.