36303

USE OF KNN AND SIMCA CHEMOMETRIC METHODS FOR CLASSIFICATION OF COFFEE GLOBAL QUALITY

Favoritar este trabalho

Coffee is a very popular beverage, consumed worldwide. In Brazil, it is one of the traditional cultivation and the quality of its beverage has been the subject of several studies. The quality of the beverage depends on the previous operations for processing, such as type of cropping, grain maturation, preparation and drying of the coffee grain. In 2004, the Brazilian Association of Coffee Industry (ABIC) established criteria, from which it is possible to classify the coffee into four categories according to its quality level - Not recommended for delivery, Traditional, Superior and Gourmet. The aim of this study was to conduce sensory analysis on coffee samples from 2014 to 2015, through quantitative descriptive analysis (QDA) method, with a selected and trained team composed of at least five judges per session, using unstructured 0-10 cm scale for evaluation of powder fragrance, aroma, defects, acidity, bitterness, flavor, aftertaste, astringency and body of the coffee beverage with final evaluation of the overall quality, and then with the results they were built classification models using KNN (k-nearest neighbors) and SIMCA techniques. They were used 213 results from obtained from QDA, from which 18 results were used for external validation and 195 for constructing the classification model. On KNN technique, mean centered and with three nearest neighbors, it was obtained a model that could predict correctly, having classified all samples in their respective correspondent overall quality classes obtained in the sensory evaluation. On SIMCA technique, mean centered, the best results were obtained using two factors for "not recommended for delivery" and "gourmet" classes and one factor in the "traditional" and "superior" classes, but none of them was possible to classify correctly all samples.