Wine evaluation situations abound for wine-makers, wine judges, wine retailers, and for every consumer of wine. Apart from a few studies, there has been little new world research in wine evaluation that has ventured sensory-chemical related studies. In order to resume the information given by a panel of judges on sensory characteristics of wines and study complex and/or noisy relationships between sensory and chemical-physical variables, we advance a new strategy based on cluster analysis of the information given by the judges on sensory variables (which include visual characteristics, olfactory characteristics and taste characteristics), and on a non-linear generalization of partial least squares which permits to state what are the chemical-physical variables which more affect these sensorial ones.
Sensory evaluation of wine via multivariate additive partial least squares
LOMBARDO, Rosaria
2010
Abstract
Wine evaluation situations abound for wine-makers, wine judges, wine retailers, and for every consumer of wine. Apart from a few studies, there has been little new world research in wine evaluation that has ventured sensory-chemical related studies. In order to resume the information given by a panel of judges on sensory characteristics of wines and study complex and/or noisy relationships between sensory and chemical-physical variables, we advance a new strategy based on cluster analysis of the information given by the judges on sensory variables (which include visual characteristics, olfactory characteristics and taste characteristics), and on a non-linear generalization of partial least squares which permits to state what are the chemical-physical variables which more affect these sensorial ones.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.