Classificação de café arábica por meio de redes neurais artificiais: softwares ClassCafe 1.0 e ClassTorr 1.0
Data
2019-02-22
Autores
Título da Revista
ISSN da Revista
Título de Volume
Editor
Universidade Federal de Lavras
Resumo
O café é um produto de grande importância para a economia do país, e o estado de Minas Gerais é responsável por mais de 50% da produção nacional. Porém, o método tradicional de avaliação da qualidade da bebida é realizado de forma subjetiva, na qual provadores treinados através de análise sensorial, utilizam de suas percepções de aroma e sabor para classificar a bebida em padrões conhecidos como estritamente mole, mole, apenas mole, dura, riada, rio e rio zona. Muitos estudos tentam relacionar a composição química dos grãos crus e torrados com a qualidade da bebida, a fim de desenvolver metodologias analíticas objetivas para complementar a avaliação feita por provadores. Diante do exposto, o objetivo deste trabalho foi avaliar amostras diferentes de café oriundas do estado de Minas Gerais. Essas amostras, foram previamente classificadas por provadores treinados e, posteriormente, com o auxílio dos softwares de classificação de grãos cru (ClassCafe 1.0) e de classificação de grãos torrado, (ClassTor 1.0), classificadas novamente de maneira objetiva. Os dados químicos inseridos na camada de entrada do software para o café cru foram: a lixiviação de potássio, condutividade elétrica, acidez, pH, sólidos solúveis, atividade enzimática da polifenoloxidase e açúcares totais. Já para o café torrado, avaliou-se o teor de açúcares totais, açúcares redutores e açúcares não redutores, pH, sólidos solúveis, acidez e extrato etéreo. Ao final, comparou-se a classificação dada pelas duas metodologias. O software para café cru (ClassCafe 1.0) apresentou melhor eficiência na classificação das amostras quando comparado com o software para café torrado (ClassTorr 1.0). Com isso, conclui-se que os softwares desenvolvidos apresentaram grande capacidade em auxiliar a classificação do café, sugere-se que os dados químicos encontrados nesta pesquisa sejam utilizados para ampliar a alimentação desses sistemas computadorizados, a fim de aumentar a sensibilidade na distinção dos diferentes padrões.
Coffee is a product of great importance for the economy of the country, and the state of Minas Gerais, is responsible for more than 50% of the national production. However, the traditional method of evaluating the quality of the beverage is performed subjectively, whit tasters trained through sensorial analysis, using their perceptions of aroma and flavor to classify a beverage in in patterns known as strictly soft, soft, barely soft, hard, rioysh, rio and rio zona. Many studies attempt to relate the chemical composition of raw and roasted grains to the quality of the beverage in order to develop objective analytical methodologies to complement the evaluation done by tasters. In view of the above, the objective of this work was to evaluate different samples of coffee from the state of Minas Gerais. These samples were previously classified by trained tasters and, later, with the aid of grading software (ClassCafe 1.0) and classification of roasted grains (ClassTor 1.0), again objectively classified. The chemical data inserted in the raw coffee software input layer were: potassium leaching, electrical conductivity, acidity, pH, soluble solids, enzymatic activity of polyphenoloxidase and total sugars. For the roasted coffee, the content of total sugars, reducing sugars and non-reducing sugars, pH, soluble solids, acidity and ethereal extract were evaluated. At the end, the classification given by the two methodologies was compared. The raw coffee software (ClassCafe 1.0) presented better efficiency in classifying the samples when compared to the software for roasted coffee (ClassTorr 1.0). Therefore, it is concluded that the softwares developed had a great capacity to help the classification of coffee, it is suggested that the chemical data found in this research be used to increase the power of these computerized systems, in order to increase the sensitivity in the distinction between different standards.
Coffee is a product of great importance for the economy of the country, and the state of Minas Gerais, is responsible for more than 50% of the national production. However, the traditional method of evaluating the quality of the beverage is performed subjectively, whit tasters trained through sensorial analysis, using their perceptions of aroma and flavor to classify a beverage in in patterns known as strictly soft, soft, barely soft, hard, rioysh, rio and rio zona. Many studies attempt to relate the chemical composition of raw and roasted grains to the quality of the beverage in order to develop objective analytical methodologies to complement the evaluation done by tasters. In view of the above, the objective of this work was to evaluate different samples of coffee from the state of Minas Gerais. These samples were previously classified by trained tasters and, later, with the aid of grading software (ClassCafe 1.0) and classification of roasted grains (ClassTor 1.0), again objectively classified. The chemical data inserted in the raw coffee software input layer were: potassium leaching, electrical conductivity, acidity, pH, soluble solids, enzymatic activity of polyphenoloxidase and total sugars. For the roasted coffee, the content of total sugars, reducing sugars and non-reducing sugars, pH, soluble solids, acidity and ethereal extract were evaluated. At the end, the classification given by the two methodologies was compared. The raw coffee software (ClassCafe 1.0) presented better efficiency in classifying the samples when compared to the software for roasted coffee (ClassTorr 1.0). Therefore, it is concluded that the softwares developed had a great capacity to help the classification of coffee, it is suggested that the chemical data found in this research be used to increase the power of these computerized systems, in order to increase the sensitivity in the distinction between different standards.
Descrição
Dissertação de Mestrado defendida na Universidade Federal de Lavras
Palavras-chave
Inteligência artificial, Qualidade do café, Classificação de bebida, Artificial intelligence, Quality of coffee, Classification of the beverage
Citação
OLIVEIRA, Graziela Silva. Classificação de café arábica por meio de redes neurais artificiais: softwares ClassCafe 1.0 e ClassTorr 1.0. 2019. 66 p. Dissertação (Mestrado em Ciência dos Alimentos) – Universidade Federal de Lavras, Lavras, 2019.