Chilean Wines Classification based only on Aroma Information

Results of Chilean wine classification based on the information provided by an electronic nose are reported in this paper. The classification scheme consists of two parts; in the first stage, Principal Component Analysis is used as feature extraction method to reduce the dimensionality of the original information. Then, Radial Basis Functions Neural Networks is used as pattern recognition technique to perform the classification. The objective of this study is to classify different Cabernet Sauvignon, Merlot and Carménère wine samples from different years, valleys and vineyards of Chile.

Authors:

• Nicolás H. Beltrán
• Manuel A. Duarte-Mermoud
• Víctor A. Soto
• Sebastián A. Salah
• and Matías A. Bustos

Keywords:

• Feature extraction techniques
• Pattern recognitiontechniques
• Principal component analysis
• Radial basis functionsneural networks
• Wine classification.

References:

[1] A.Yamazaki and T. B. Ludermir, "Classification of Vintages of Wine by
an Artificial Nose with Neural Networks", Proceedings of Tercer
Encuentro Nacional de Inteligencia Artificial, Fortaleza, Brasil, 2001.
[2] M.S. Santos, "Construction of an Artificial Nose using Neural
Networks". Ph.D. Thesis, Centre of Informatics, Federal University of
Pernambuco, Brazil, 2000.
[3] S. Haykin, Neural Networks: A Comprehensive Foundation. Macmillan
College Publihing Company, 1994.
[4] J.P. Santos, J. Lozano, H. Vásquez, J.A. Agapito, M.A. Martín, J.
González. "Clasificación e Identificación de Vinos Mediante un Sistema
de Estado Sólido", Proceedings of the XXI Jornadas de Automática,
Sevilla, 2000.
[5] M. Garc├¡a, M. Aleixandre, J. Gutiérrez and M.C. Horrillo, "Electronic
nose for wine discrimination", Sensors and Actuators B: Chemical, vol.
113, pp. 911-916, Feb. 2006.
[6] C. Bishop, Neural Networks for Pattern Recognition. Oxford University
Press, News York, 2002.
[7] J. Ghosh, A. Nag, An Overview of Radial Basis Functions Networks.
Physica-Verlag, 2000.
[8] B. D. Ripley, Pattern Recognition and Neural Networks. Cambridge
University Press, Cambridge, 1996.
[9] H. Mhaskar, M. Michelli, "Approximation by Superposition of
Sigmoidal and Radial Basis Functions", Advances in Applied
Mathematics, vol 13, pp. 350-373, 1992
[10] J. Schurmann, Pattern Classification: A Unified View of Statistical and
Neural Approaches, J. Wiley & Sons, 1996.
[11] K. Fukunaga and R. Hayes, "Estimation of Classifier Performance".
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.
11, pp. 1087-1101, Oct. 1989.
[12] F. J. Cortijo Bon (2001). Selección y Extracción de Características.
Available: http://www-etsi2.ugr.es/depar/ccia/rf/www/tema5_00-
01_www/tema5_00-01_www.html.
[13] Electronic Sensor Technology, 7100 Fast GC Analyzer: Operation
Manual, Electronic Sensor Technology, Bussines Center Circle, 1999.
[14] N.H. Beltrán, M.A. Duarte-Mermoud, S.A. Salah, M.A. Bustos, A.I.
Pe├▒a-Neira, E.A. Loyola and J.W. Jalocha. "Feature selection algorithms
using Chilean wine chromatograms as examples". Journal of Food
Engineering, vol. 67, No. 4, pp. 483-490, Apr. 2005.
[15] N.H. Beltrán, M.A. Duarte-Mermoud, M.A. Bustos, S.A. Salah, E.A.
Loyola, A.I. Pe├▒a-Neira and J.W. Jalocha, "Feature extraction and
classification of Chilean wines". Journal of Food Engineering, vol.75,
No. 1, pp. 1-10, Jul. 2006.
[16] M.A. Bustos, M.A. Duarte-Mermoud, N.H. Beltrán, S.A. Salah, E.A.
Loyola, A.I. Pe├▒a-Neira and J.W. Jalocha, "Classification of Chilean
wines using a Bayesian approach" (In Spanish). Viticultura / Enología
Profesional, No. 90, pp. 63-70, Jan.-Feb. 2004.