Data Science in the evaluation of extreme quality coffee samples
DOI:
https://doi.org/10.35699/2447-6218.2020.15863Keywords:
Sensory attribute, Multivariate analysis, Regression tree, Peeled cherry coffeeAbstract
Demand for the quality of specialty coffees has driven the market and influenced the increased commercial value of coffee bags. In the Brazilian market, the state of Minas Gerais contributes a significant percentage of productivity, a fact that has been accompanied by quality coffee contests. This paper analyzed the first twenty samples of peeled cherry coffee ranked in the Concurso Mineiro de Qualidade do Café in 2013. Under the quantitative approach, an exploratory analysis was performed from the construction of the principal components with the 15 attributes. Subsequently, the prediction capacity of final grades was evaluated through a regression tree model. As a result, Linoleic and Palmitic acids were the attributes that most contributed to the construction of the first principal components. In addition, Linoleic acid was attributed as the root of the regression tree, which is a important attribute for the prediction of final scores.
Downloads
References
Alvarenga, S. T. 2017. Caracterização química e sensorial de cafés especiais do sul de Minas Gerais. 120 f. Tese (Doutorado em Ciência dos Alimentos) - Universidade Federal de Lavras, Lavras.
Barbosa, J.; Borém, F.; Alves, H.; Volpato, M.; Souza, V.; Santos, W. ; Andrade, L. 2009. Distribuição espacial de cafés do Estado de Minas Gerais e sua relação com a qualidade. In: Simpósio de Pesquisa dos Cafés do Brasil, 6, 2009, Vitória. Anais. Vitória. p. 1-7.
Baqueta, M; Coqueiro, A; Valderrama, P. 2019. Brazilian coffee blends: a simple and fast method by near-infrared spectroscopy for the determination of the sensory attributes elicited in professional coffee cupping. Journal of food science, 84:1247-1255. Doi: http://dx.doi.org/10.1111/1750-3841.14617.
Boaventura, P; Abdalla, C; Araújo, C; Arakelian, J. 2018. Cocriação de valor na cadeia do café especial: o movimento da terceira onda do café. Revista de Administração de Empresas, São Paulo, 58: 254-266. Doi: http://dx.doi.org/10.1590/s0034-759020180306.
Borém, F; Cirillo, M; Alves, A; Santos, C; Liska, G; Ramos, M; Lima, R. 2019. Coffee sensory quality study based on spatial distribution in the Mantiqueira mountain region of Brazil. Journal of Sensory Studies, e12552. Doi: https://doi.org/10.1111/joss.12552.
Borém, F; Figueiredo, L; Ribeiro, F; Taveira, J; Giomo, G; Salva, T. 2016. The relationship between organic acids, sucrose and the quality of specialty coffees. African Journal of Agricultural Research, 709-717. Doi: http://dx.doi.org/10.5897/AJAR2015.10569
Chalfoun, S.; Pereira, M.; Carvalho, G.; Pereira, A.; Savian, T.; Botelho, D. 2013. Sensorial characteristics of coffee (coffea arabica l.) varieties in the alto paranaíba region. Coffe Science, 8: 43-52. Doi: http://dx.doi.org/10.25186/cs.v8i1.330.
Dutcosky, S. D. 2013. Análise sensorial de alimentos. 4. ed. Curitiba: Editora Universitária Champagnat, 2013.
EMATER, 2019. Vencedores do 10º Concurso de Qualidade dos Cafés de Minas são premiados na UFLA. Portal do Agronegócio, 17 dez. 2013. Disponível em: https://www.portaldoagronegocio.com.br/noticia/vencedores-do-10-concurso-de-qualidade-dos-cafes-de-minas-saopremiados-na-ufla-102238.
EMATER, 2013. XVI Concurso de Qualidade dos Cafés de Minas Gerais–2019. Disponível em: http://www.emater.mg.gov.br/doc/intranet/upload/cafe2018/regulamento_2019.pdf.
Figueiredo, L; Borém, F; Ribeiro, F; Giomo, G; Taveira, J; Malta, M. 2015. Fatty acid profiles and parameters of quality of specialty coffees produced in different Brazilian regions. African Journal of Agricultural Research, 10: 3484-3493. Doi: 10.5897/AJAR2015.9697.
Goyal, S; Goyal, G. 2013. Machine learning ann models for predicting sensory quality of roasted coffee flavoured sterilized drink. 2013. Advances in Distributed Computing and Artificial Intelligence Journal, 2: 9-13. Doi: http://dx.doi.org/10.14201/ADCAIJ201426913.
Izbicki, R; Santos, T. 2018. Machine learning sob a ótica estatística: uma abordagem preditivista para estatística com exemplos em R. Disponível em: http://www.rizbicki.ufscar.br/sml.pdf.
James, G; Witten, D; Hastie, T; Tibshirani, R. 2013. An Introduction to Statistical Learning. Reino Unido: Springer.
Johnson, R; Wichern, D. 2015. Applied Multivariate Statistical Analysis. 6. ed. Pearson.
Jolliffe, I; Cadima, J. 2016. Principal component analysis: a review and recent developments. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 374 (2065). Doi: http://dx.doi.org/10.1098/rsta.2015.0202.
Kassambara, A. 2017. Principal Component Methods. In: R: practical guide. Disponível em: https://www.datanovia.com/en/wp-content/uploads/dn-tutorials/book-preview/principal-component-methodsin-r-preview.pdf.
Kim, H; Hong, D; Yu, J; Lee, S; Lee; Y. 2019. Identification of Headspace Volatile Compounds of Blended Coffee and Application to Principal Component Analysis. Preventive Nutrition and Food Science, 24, 217-223. Doi: 10.3746/pnf.2019.24.2.217.
Kreuml, M.; Majchrzak, D.; Ploederl, B.; Koenig, J. 2013. Changes in sensory quality characteristics of coffee during storage. Food Science & Nutrition, 4:267–272. Doi: 10.1002/fsn3.35. Lantz, B. 2015 Machine Learning with R. 2. ed. Reino Unido: Packt Publishing.
Loh, W. 2014. Classification and regression tree methods. Wiley StatsRef: Statistics Reference Online.
Mingoti, S. 2005. Análise de dados através de métodos de estatística multivariada. Belo Horizonte: Editora UFMG.
Minim, V. Análise sensorial: estudo com consumidores. 2. ed. Viçosa: Editora da Universidade Federal de Viçosa, 2010.
Mori, A; Garcia, A; Ferrão, M; Fonseca, A; Ferrão, R; Benassi, M. 2018. Sensory profile of conilon coffee brews from the state of Espírito Santo, Brazil. Pesquisa Agropecuária Brasileira, 53: 1061-1069. Doi: http://dx.doi.org/10.1590/s0100-204x2018000900010.
Oliveira, J; Elias, T; Lessa, M. 2012. Café Especial: Agregação de Valor ao Tradicional Café. Revista Eletrônica de Comunicação, 3: 1-8. Disponível em: http://periodicos.unifacef.com.br/index.php/rec/article/view/445.
Oliveira, L; Menezes, F; Cirillo, M; Saúde, A; Borém, F; Liska, G. 2019. Machine Learning techniques in muliclass problems with application in sensorial analysis. Concurrency and Computation: Practice and Experience. Doi: 10.1002/cpe.5579.
Ormond, J; Paula, S; Farevet Filho, P. 1999. Café: (re)conquista dos mercados. Disponível em: https://www.bndes.gov.br/SiteBNDES/export/sites/default/bndes_pt/Galerias/Arquivos/conhecimento/bnset/set1001.pdf.
R CORE TEAM. 2019. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. Sanchez, K.; Chambers, E. 2015. How Does Product Preparation Affect Sensory Properties? An Example with Coffee. Journal of Sensory Studies, 30. Doi: 10.1111/joss.12184.
Saraiva, S; Araújo, M; Lucia, S, Silva, L; Zeferino, L. 2010. Comparação dos tipos de processamento pós-colheita de café. In: Simpósio de Pesquisa dos Cafés Do Brasil. Vitória. Anais. Brasília, DF: Embrapa.
Silva, S; Queiroz, D; Ferreira, W; Corrêa, P; Rufino, J. 2015. Mapping the potential beverage quality of coffee produced in the Zona da Mata, Minas Gerais, Brazil. Journal of the science of food and agriculture, 96:3098-30108. Doi: 10.1002/jsfa.7485.
Souza, M. 2006. Cafés sustentáveis e denominação de origem: a certificação de qualidade na diferenciação de cafés orgânicos, sombreados e solidários. Tese (Doutorado em Ciência Ambiental) - Ciência Ambiental, Universidade de São Paulo, São Paulo.
Published
How to Cite
Issue
Section
License
Copyright (c) 2020 Agrarian Sciences Journal
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in this journal agree to the following terms:
The Copyright for articles published in this journal follow authorship. The articles are open access, with their own attributions, in educational and non-commercial applications.
The journal reserves the right to make regulatory, orthographic and grammatical changes in the originals, with the aim of maintaining the standard language and the credibility of the vehicle. It will respect, however, the writing style of the authors.
Changes, corrections or suggestions of conceptual order will be forwarded to the authors, when necessary. In such cases, the articles, once appropriate, should be submitted for further consideration.
The opinions issued by the authors of the articles are their sole responsibility.
Agrarian Science Journal is licensed under a 