Application of a GA–PLS strategy for variable reduction of electronic tongue signals

Abstract A genetic algorithm (GA) combined with partial least squares (PLS) regression was applied in order to reduce the considerable number of variables of electrochemical signals recorded by a voltammetric electronic tongue. The algorithm was specifically designed for improving the analysis of data matrices with high collinearity, providing good solutions in terms of both predictive ability and interpretability and, at the same time, minimising the risk of overfitting. The variable reduction was carried out within a wine characterisation performed with an electronic tongue based on voltammetric sensors. In more detail, the aim was the evaluation of differences among wines aged by means of two different processes: the traditional ageing process in oak wood barrels and an alternative method based on the use of stainless steel tanks and oak wood chips or staves. The results show that the variables selected are at least as good as the full signals to separate the two different classes, even though the number of parameters has been reduced from 1980 to 280 variables; furthermore, the models obtained are simpler and more easily interpretable. In fact, it is important to point out that the variables selected by the genetic algorithm are related to the electrochemical activity of the polyphenolic fraction of wine.

[1]  M. L. Rodriguez-Mendez,et al.  Electronic tongue based on voltammetric electrodes modified with materials showing complementary electroactive properties. Applications , 2008 .

[2]  R. Boggia,et al.  Genetic algorithms as a strategy for feature selection , 1992 .

[3]  M. Valle.  Electronic Tongues Employing Electrochemical Sensors , 2010 .

[4]  Constantin Apetrei,et al.  Using an e-tongue based on voltammetric electrodes to discriminate among red wines aged in oak barrels or aged using alternative methods: Correlation between electrochemical signals and analytical parameters , 2007 .

[5]  P. Kilmartin,et al.  Extraction of phenolic compounds during vinification of Pinot Noir wine examined by HPLC and cyclic voltammetry , 2002 .

[6]  R. Bellman.  Dynamic programming. , 1957, Science.

[7]  Fredrik Winquist,et al.  Investigation of Electrode Materials as Sensors in a Voltammetric Electronic Tongue , 2002 .

[8]  John H. Kalivas,et al.  Comparison of Forward Selection, Backward Elimination, and Generalized Simulated Annealing for Variable Selection , 1993 .

[9]  Paolo Oliveri,et al.  Development of a voltammetric electronic tongue for discrimination of edible oils , 2009, Analytical and bioanalytical chemistry.

[10]  J. Saja,et al.  E-tongue based on a hybrid array of voltammetric sensors based on phthalocyanines, perylene derivatives and conducting polymers : Discrimination capability towards red wines elaborated with different varieties of grapes , 2006 .

[11]  Patrycja Ciosek,et al.  The analysis of sensor array data with various pattern recognition techniques , 2006 .

[12]  Fredrik Winquist,et al.  Voltammetric electronic tongues – basic principles and applications , 2008 .

[13]  Antonio Riul,et al.  Recent advances in electronic tongues. , 2010, The Analyst.

[14]  R. Leardi,et al.  Genetic algorithms applied to feature selection in PLS regression: how and when to use them , 1998 .

[15]  Paolo Oliveri,et al.  Chemometric brains for artificial tongues. , 2010, Advances in food and nutrition research.

[16]  Maria Luz Rodriguez-Mendez,et al.  Electrochemical sensor array made from bisphthalocyanine modified carbon paste electrodes for discrimination of red wines , 2004 .

[17]  M. Peris,et al.  Review: highlights in recent applications of electronic tongues in food analysis. , 2010, Analytica chimica acta.

[18]  R. Leardi,et al.  Variable selection for multivariate calibration using a genetic algorithm: prediction of additive concentrations in polymer films from Fourier transform-infrared spectral data , 2002 .

[19]  Riccardo Leardi,et al.  Genetic-algorithm-based wavelength selection in multicomponent spectrophotometric determination by PLS: application on copper and zinc mixture. , 2003, Talanta.

[20]  J. Saja,et al.  Electronic tongue based on chemically modified electrodes and voltammetry for the detection of adulterations in wines , 2006 .

[21]  J. Saja,et al.  Application of an electronic tongue to study the effect of the use of pieces of wood and micro-oxygenation in the aging of red wine , 2010 .