Analysis of total phenolic, flavonoids, anthocyanins and tannins content in Romanian red wines: Prediction of antioxidant activities and classification of wines using artificial neural networks

Wine is one of the most consumed beverages over the world containing large quantities of polyphenolic compounds. These compounds are responsible for quality of red wines, influencing the antioxidant activity, astringency, bitterness and colour, their composition in wine being influenced by the varieties, the vintage and the wineries. The aim of the present work is to build software instruments intended to work as data-mining tools for predicting valuable properties of wine and for revealing different wine classes. The developed ANNs are able to reveal the relationships between the concentration of total phenolic, flavonoids, anthocyanins, and tannins content, associated to the antioxidant activity, and the wine distinctive classes determined by the wine variety, harvesting year or winery. The presented ANNs proved to be reliable software tools for assessment or validation of the wine essential characteristics and authenticity and may be further used to establish a database of analytical characteristics of wines.