Coffee Science_v.15, 2020
URI permanente para esta coleçãohttps://thoth.dti.ufv.br/handle/123456789/12726
Navegar
2 resultados
Resultados da Pesquisa
Item Unsupervised classification of specialty coffees in homogeneous sensory attributes through machine learning(Editora UFLA, 2020) Ossani, Paulo César; Rossoni, Diogo Francisco; Cirillo, Marcelo Ângelo; Borém, Flávio MeiraBrazil is the largest exporter of coffee beans, 29% world exports, 15% this volume in specialty coffees. Thereby researches are done, so that identify different segments in the market, in order to direct the end consumer to a better quality product. New technologies are explored to meet an increasing demand for high quality coffees. Therefore, in this article has an objective to propose the use of machine learning techniques combined with projection pursuit in the construction of unsupervised classification models, in a sensory acceptance experiment, applied to four groups of trained and untrained consumers, in four classes of specialty coffees in which they were evaluated sensory characteristics: aroma, body coffee, sweetness and general note. For evaluating classifier performance, in the data with reduced dimension, all instances were used, and considering four groupings, the models were adjusted. The results obtained from the groupings formed were compared with pre-established classes to confirm the model. Success and error rates were obtained, considering the rate of false positives and false negatives, sensitivity and classification methods accuracy. It was concluded that, machine learning use in data with reduced dimensions is feasible, as it allows unsupervised classification of specialty coffees, produced at different altitudes and processes, considering the heterogeneity among consumers involved in sensory analysis, and the high homogeneity of sensory attributes among the analyzed classes, obtaining good hit rates in some classifiers.Item Mathematical modeling of dehydration resistance of pericarp tissues and endosperm in fruits of arabic coffee(Editora UFLA, 2020) Dias, Camila de Almeida; Andrade, Ednilton Tavares de; Lemos, Isabella Àvila; Borém, Flávio Meira; Westerich, Diogo Nogueira; Silva, Ana Claudia Almeida daCoffee represents an important source of income for producers and for the Brazilian economy, being the second product in the country’s agricultural exports. Unlike other agricultural products, freshly harvested coffee has a high fruit water content, approximately 60% (dry base). It is fundamental to optimize the drying process for cost reduction and quality maintenance, making it necessary to understand the interdependence relation of the tissues of the pericarp and the coffee endosperm during the dehydration of the fruit. The objective of this work was to elaborate a drying model for the constituent parts of coffee fruits evaluating the resistance of each of the pericarp tissues and endosperm. The experiment was set up in a 4x6 factorial scheme (4 relative humidity of the drying air and natural, pulped natural coffee, pericarp tissues and endosperm: 1 - natural coffee and 2 – pulped natural coffee, 3 - exocarp + a portion of mesocarp, 4 - mesocarp, 5 - endocarp, 6 - endosperm]) in a completely randomized design with four replicates. The results were analyzed through analysis of variance and regression, using the statistical software STATISTICA 5.0®. The resistance to water outflow, regardless of the processing or the fruit part of the coffee, is greater when the coffee is dried with the lowest relative humidity. The natural coffee was the treatment that presented greater resistance, while the lower resistance was presented by the exocarp + a portion of mesocarp.