Premium
Sensory Evaluation of Virgin Olive Oils by Artificial Neural Network Processing of Dynamic Head‐Space Gas Chromatographic Data
Author(s) -
Angerosa Franca,
Giacinto Luciana Di,
Vito Raffaella,
Cumitini Sergio
Publication year - 1996
Publication title -
journal of the science of food and agriculture
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.782
H-Index - 142
eISSN - 1097-0010
pISSN - 0022-5142
DOI - 10.1002/(sici)1097-0010(199611)72:3<323::aid-jsfa662>3.0.co;2-a
Subject(s) - ripeness , artificial neural network , olive oil , sensory system , head (geology) , artificial intelligence , sensory analysis , pattern recognition (psychology) , mathematics , computer science , statistics , food science , chemistry , biology , ripening , paleontology , neuroscience
A different approach to the traditional sensory method was used for the sensory quality evaluation of virgin olive oils. Two hundred and four oil samples differing in their quality, and extracted from olives of various varieties, ripeness, sanitary state and geographical origin, were submitted to sensory evaluation by a panel test and dynamic head‐space analysis for the quantification of volatile fractions. An artificial neural network (ANN), using the back‐propagation algorithm, was applied to the head‐space results (input) with the aim of predicting panel test scores (output). It was found that the ANN was able to generalise well and to assign the sensory evaluations with a good degree of accuracy. The high proportion of correct answers (96%) suggested that sensory evaluation from the panel test could be successfully replaced by the dynamic head‐space analysis–ANN coupled approach.