A novel method for classification of wine based on organic acids

Warning

This publication doesn't include Institute of Computer Science. It includes Faculty of Science. Official publication website can be found on muni.cz.
Authors

MILOVANOVIĆ Miodrag ŽERAVÍK Jiří OBOŘIL Michal PELCOVÁ Marta LACINA Karel CAKAR Uros PETROVIC Aleksandar GLATZ Zdeněk SKLÁDAL Petr

Year of publication 2019
Type Article in Periodical
Magazine / Source Food Chemistry
MU Faculty or unit

Faculty of Science

Citation
Web web časopisu
Doi http://dx.doi.org/10.1016/j.foodchem.2019.01.113
Keywords Carboxylic acids; Capillary electrophoresis; Biosensor; Principal component analysis; Self-organizing map
Description Bio-electronic tongue was linked to artificial intelligence processing unit and used for classification of wines based on carboxylic acids levels, which were indirectly related to malolactic fermentation. The system employed amperometric biosensors with lactate oxidase, sarcosine oxidase, and fumarase/sarcosine oxidase in the three sensing channels. The results were processed using two statistical methods – principal component analysis (PCA) and self-organized maps (SOM) in order to classify 31 wine samples from the South Moravia region in the Czech Republic. Reference assays were carried out using the capillary electrophoresis (CE). The PCA patterns for both CE and biosensor data provided good correspondence in the clusters of samples. The SOM treatment provided a better resolution of the generated patterns of samples compared to PCA, the SOM derived clusters corresponded with the PCA classification only partially. The biosensor/SOM combination offers a novel procedure of wine classification.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info