Electronic tongue for wine discrimination, using PCA and ANN

摘要

This article explains the discrimination of wines through an electronic tongue, using machine learning algorithms and signal processing techniques: Principal Component Analysis (PCA) and Artificial Neural Networks (ANN), where the model of the multilayer perceptron was implemented. A database for wine quality was used and a study was conducted with a green wine of northeastern Portugal. The analysis of data and subsequent processing was performed for two different types of wine; White and Red. The proposed method was able to classify and identify each of the categories of wine, giving a success rate of 98% with ANN and a variance of 98%.