The early detection abnormal fermentations (sluggish and stuck) is one of the main problems that appear in wine production, due to the significant impacts in wine quality and utility. This situation is specially important in Chile, which is one of the top ten worldwide wine production countries. In last years, two different methods coming from Computational Intelligence have been applied to solve this problem: Artificial Neural Networks and Support Vector Machines. In this work we present the main results that have been obtained to detect abnormal wine fermentations applying these approaches. The Support Vector Machine method with radial basis kernel present the best results for the time cutoffs considered (72 [hr] and 96 [hr]) over all the techniques studied with respect to prediction rates and number of the training sets.
© 2001-2024 Fundación Dialnet · Todos los derechos reservados