Análise de correspondência canônica não linear com ênfase na descrição da redundância da variabilidade de dados sensoriais de blends de cafés com diferentes variedades

• Ano de defesa: 2022
• Autor(a) principal: Santos, Herbert Stein Pereira Torres
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Lavras; Programa de Pós-graduação em Estatística e Experimentação Agropecuária; UFLA; brasil; Departamento de Estatística
• Palavras-chave em Português: Cafés especiais; Café comercial; Regressão polinomial multivariada; Blendas; Redução de dimensionalidade; Avaliadores sensoriais; Specialty coffees; Commercial coffee; Multivariate polynomial regression; Blends; Dimensionality reduction; Sensory assessors; Análise Multivariada
• Link de acesso: http://repositorio.ufla.br/jspui/handle/1/55798

The formulation of coffee blends is of paramount importance for the coffee industry, as it provides the final product with an expressive ability to compete in the market and adds sensory attributes that complement the consumption experience. Through redundancy analysis and canonical correspondence analysis, it is possible to study the relationships between a set of sensory notes and a set of blends with different proportions of coffee variety through multivariate linear regression models. However, it is unrealistic to assume that such sensory responses are given in a linear fashion in relation to the formulation of blends, since some types of coffee have greater weight in the sensory evaluation (quadratic terms) and the effect of blends must be considered (term of interaction). With this motivation, this work aims to propose the use of redundancy analysis and nonlinear correspondence analysis through multivariate polynomial regression to evaluate the acceptance of different varieties of coffee blends. The blends were formulated from proportions of specialty coffee varieties such as Arabica, Yellow Bourbon and Acaiá, Conilon coffee and a commercial brand of roasted coffee. The blends were evaluated receiving scores that ranged from 0 to 10 for the qualitative characteristics of the drink: flavor, bitterness, acidity, body and final note. The results showed significant gains in the percentage of total explained variance in the nonlinear models in relation to the linear ones.