Premium
SENSORY ANALYSIS OF RED WINES: DISCRIMINATION BY ADAPTIVE FUZZY PARTITION
Author(s) -
PICLIN NADÈGE,
PINTORE MARCO,
LANZA CARMELA MARIA,
SCACCO ANTONIO,
GUCCIONE SALVATORE,
GIURATO LAURA,
CHRÉTIEN JACQUES R.
Publication year - 2008
Publication title -
journal of sensory studies
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.61
H-Index - 53
eISSN - 1745-459X
pISSN - 0887-8250
DOI - 10.1111/j.1745-459x.2008.00172.x
Subject(s) - wine , fuzzy logic , sensory system , sensory analysis , partition (number theory) , artificial intelligence , computer science , pattern recognition (psychology) , set (abstract data type) , fuzzy set , data mining , machine learning , mathematics , statistics , food science , psychology , chemistry , combinatorics , cognitive psychology , programming language
Classification models were established on a set of sensory profiles associated with red wine samples bottled from three vintages. These profiles were defined by eight assessors charged, for all wine samples, to assign to each of 17 sensory descriptors a note ranged from 1.0 to 9.0, with two assessments for each judge. A new and innovative method called adaptive fuzzy partition (AFP), derived from fuzzy logic (FL) concepts, was tested on the same data set. FL is particularly suitable to classify sensory analysis data sets, as it can represent the “fuzziness” linked to an expert's subjectivity in the characterization of wine sensory profiles. More precisely, after subdividing the 48 sensory profiles into training and test sets, the AFP method predicted correctly 75% of the test assessments. These very encouraging preliminary results show the proposed methods are worth investigating more thoroughly, testing large and diverse wine data sets.PRACTICAL APPLICATIONS A new and innovative method called adaptive fuzzy partition, derived from fuzzy logic (FL) concepts, is presented. FL is particularly suitable to classify sensory analysis data sets, as it can represent the “fuzziness” linked to an expert's subjectivity in the characterization of wine sensory profiles.