Our novel method is a trial of realizing an engineering model of the sensing and recognizing systems of humans that combines all features of artificial olfactory and artificial taste, i.e. 'electronic nose' and 'electronic tongue' for the classification of wine.
NMR-based metabolomics has been extensively used for the classification of wine samples according to their geographical origin, and several studies have shown a clear differentiation among wine samples produced by grapes belonging to the same cultivar but harvested in different regions of the same country.
This motivation spawned a new classification of wine in Italy.
But Best Cellars's innovative classification of wines by style and taste features will apply to the upscale merchandise.
Figure 7 presents PCA (A) and OPLS-DA (B) score plots of healthy and botrytized base wines indicating the correct classification of healthy wines and wines infected by Botrytis cinerea (20 and 40% of infection).
1H NMR spectroscopy combined with multivariate statistical analysis has been applied successfully for the classification of different wine cultivars, usually involving the study of wines produced from the same geographical region, in order to exclude site-specific effects capable of affecting the wine metabolome.
(Extra bonus points here for anyone who wants to compare the mid-nineteenth-century classification of French wine, which only happened in 1855, with the companion classification of dogs around the same time.
The organic compounds that were responsible for the classification of the wine samples according to vintage were mainly amino acids, sugars, and aromatic compounds [11].
The data obtained were treated using advanced chemometric tools like Principal Component Analysis (PCA) and Soft Independent Modeling Class Analogy (SIMCA) for the classification of the wine mixtures and Partial Least Squares (PLS) regression for the quantification of the grape variety composition.
PLS-DA models of the obtained metabolomic data showed good differentiation of the wine samples according to their geographical origin, with total acidity, citric acid, malic acid, succinic acid, lactic acid, total polyphenol index, glucose, and proline/arginine ratio being the main contributors to the classification of the wine samples [62].
The application of wine quality classification is implemented in Zhang [141] using a multi-task transfer learning approach.
