Evaluation of Sensorial Qualities of Fruit Wines by Kohonen Neural Network

Abstract:

Sensorial qualities of fruit wines were compared by clustering due artificial neural networks. A Kohonen network has been used as a software tool in order to increase the human skills in this kind of application. Seven wine samples were used in this work, which the five samples were of Barbados cherry wine, one sample of peach wine and one sample of grape wine. 50 consumers chosen to perhaps had been used to obtain the sensorial data using a hedonic scale of 1-9 times. Sensorial values of flavor, aroma and appearance obtained of the hedonic dating were compared. Results showed that Kohonen network classified the Barbados cherry wines in distinct group, for frequency among yours sensorial responses. Kohonen network results were similar or better than statistical classification, this shows that the use of Kohonen algorithm in the sensorial analysis of wines is valid. Kohonen algorithm is very good in clustering of Barbados cherry wine samples and it uses in sensorial analyses of wines is promises.

• Periodical: Advanced Materials Research (Volume 601)
• Pages: 216-221
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.601.216
• Online since: December 2012
• Authors: José Carlos Curvelo Santana, Cleber Gustavo Dias, Renato José Sassi, Roberto Rodrigues de Souza, Elias Basile Tambourgi
• Keywords: Fruit Wines, Kohonen Neural Network, Quality Standard, Sensorial Analysis

References

[1] S. S. Almeida, R. R. Souza, J. C. C. Santana, E. B.; Tambourgi,. Sensorial analysis of wines from Malpigia glaba L. pulp,. Brazilian Journal of Operation and Production Management, v. 5, n. 1, pp.1-12, (2008).

[2] A. F. Evangelista, S. S. Almeida, J. C. C. Santana, R. R, Souza. RSM evaluation of factors that influencing to acerola wine production,. Brazilian Journal of. Food Technology, 5th SIPAL, march, 8-13, (2005).

[3] P. M. A. Gomes, R. M. F. Figueiredo. A. J. M. Queiroz. Caracterização e isotermas de adsorção de umidade de polpa de acerola em pó,. Brazilian Journal of Agroindustrial Product, v. 4, n. 2, pp.157-165, (2002).

DOI: 10.15871/1517-8595/rbpa.v4n2p157-165

[4] T. Kohonen. Self-Organization and Associative Memory,. Berlin: Springer-Verlag, (2009).

[5] C. G. Dias and V. Randonsky. The development of an auxiliar system to help in the pediatrics diagnosis using artificial neural,. Exacta, v. 1, 89-95., (2003).

[6] U. A. Lima, A. Borzani. E. Aqarone. W.; Schimidel. Biotecnologia Industrial: Processos Fermentativos,. Vol. 3, 1ª ed., São Paulo – SP: Ed. Blucher Ltda, 598 p., (2001).

[7] J. B. SEVERO JÚNIOR, S. S.; ALMEIDA. N. NARAIN. R. R. SOUZA, J. C. C. SANTANA, E. B. TAMBOURGI. Wine Clarification from Spondias mombin L. Pulp by Hollow Fiber Membrane System,. Process Biochemistry, v. 42, pp.1516-1520, (2007).

DOI: 10.1016/j.procbio.2007.08.003

[8] E. Teixeira, E. M. Meinert, P. A. Barbetta. Análise Sensorial de Alimentos,. Série Didática. Florianópolis – SC: EDUFSC, 1997, pp.18-102.