Electronic nose based on independent component analysis combined with partial least squares and artificial neural networks for wine prediction

Teodoro Aguilera; Jesús Lozano; José A Paredes; Fernando J Alvarez; José I Suárez

doi:10.3390/s120608055

Electronic nose based on independent component analysis combined with partial least squares and artificial neural networks for wine prediction

Sensors (Basel). 2012;12(6):8055-72. doi: 10.3390/s120608055. Epub 2012 Jun 11.

Authors

Teodoro Aguilera¹, Jesús Lozano, José A Paredes, Fernando J Alvarez, José I Suárez

Affiliation

¹ Sensory Systems Research Group, University of Extremadura, 06006 Badajoz, Spain. teoaguibe@unex.es

Abstract

The aim of this work is to propose an alternative way for wine classification and prediction based on an electronic nose (e-nose) combined with Independent Component Analysis (ICA) as a dimensionality reduction technique, Partial Least Squares (PLS) to predict sensorial descriptors and Artificial Neural Networks (ANNs) for classification purpose. A total of 26 wines from different regions, varieties and elaboration processes have been analyzed with an e-nose and tasted by a sensory panel. Successful results have been obtained in most cases for prediction and classification.

Keywords: artificial neural networks; electronic nose; independent component analysis; partial least squares; wine classification.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Biosensing Techniques
Electronic Nose*
Least-Squares Analysis
Neural Networks, Computer*
Principal Component Analysis*
Signal Processing, Computer-Assisted
Time Factors
Wine / analysis*
Wine / classification