Prediction Models to Control Aging Time in Red Wine
Gonzalo Astray,
Juan Carlos Mejuto,
Víctor Martínez-Martínez,
Ignacio Nevares,
Maria Alamo-Sanza,
Jesus Simal-Gandara
Affiliations
Gonzalo Astray
Department of Physical Chemistry, Faculty of Food Science and Technology, University of Vigo, Ourense Campus, 32004 Ourense, Spain
Juan Carlos Mejuto
Department of Physical Chemistry, Faculty of Food Science and Technology, University of Vigo, Ourense Campus, 32004 Ourense, Spain
Víctor Martínez-Martínez
Department of Agricultural and Forestry Engineering, UVaMOX-University of Valladolid, 47002 Valladolid, Spain
Ignacio Nevares
Department of Agricultural and Forestry Engineering, UVaMOX-University of Valladolid, 47002 Valladolid, Spain
Maria Alamo-Sanza
Department of Analytical Chemistry, UVaMOX-University of Valladolid, 47002 Valladolid, Spain
Jesus Simal-Gandara
Nutrition and Bromatology Group, Department of Analytical and Food Chemistry, Faculty of Food Science and Technology, University of Vigo, Ourense Campus, 32004 Ourense, Spain
A combination of physical-chemical analysis has been used to monitor the aging of red wines from D.O. Toro (Spain). The changes in the chemical composition of wines that occur over the aging time can be used to distinguish between wine samples collected after one, four, seven and ten months of aging. Different computational models were used to develop a good authenticity tool to certify wines. In this research, different models have been developed: Artificial Neural Network models (ANNs), Support Vector Machine (SVM) and Random Forest (RF) models. The results obtained for the ANN model developed with sigmoidal function in the output neuron and the RF model permit us to determine the aging time, with an average absolute percentage deviation below 1%, so it can be concluded that these two models have demonstrated their capacity to predict the age of wine.
