Assessment of E-Senses Performance through Machine Learning Models for Colombian Herbal Teas Classification

This paper describes different E-Senses systems, such as Electronic Nose, Tongue, and Eyes, which were used to build several machine learning models assess their performance in classifying a variety of Colombian herbal tea brands Albahaca, Frutos Verdes, Jaibel, Toronjil, Toute. To do this, set samples previously acquired from the instruments processed through multivariate data analysis techniques (principal component linear discriminant analysis) feed support vector machine, K-nearest neighbors, decision trees, naive Bayes, random forests algorithms. The results validated using HS-SPME-GC-MS analysis. best classification methods reached 100% success rate samples. proposal this study was enhance teas three sensory perception systems. achieved by consolidating obtained collected