Transfer of multivariate classification models applied to digital images and fluorescence spectroscopy data

Abstract This work evaluates the use of transfer of classification models for identifying adulteration of extra virgin olive oil (EVOO) samples involving, separately, two analytical techniques: fluorescence spectroscopy and digital imaging. The chemometric procedures, including development of classification models and application of classification transfer methods, were performed individually for each analytical technique. Methods of direct standardization (DS) and piecewise direct standardization (PDS) were applied to transfer samples sets in order to estimate an adjustment function and apply it to a samples set measured by the secondary instrument. For purposes of comparison, classification models were built based on linear discriminant analysis (LDA) with previous selection of variables by the successive projections algorithm (SPA), and partial least squares discriminant analysis (PLS-DA). The performance of the classification models was evaluated according to the number of errors and correct classification rate (CCR) for the prediction set measured by the secondary instrument. Before standardization, SPA-LDA and PLS-DA models achieved the same CCR using two analytical techniques: 54% for fluorescence emission spectra and 47% for histograms of digital images. After the standardization, a substantial increase of the CCR was observed. For the SPA-LDA models, a CCR of 88% was obtained for the fluorescence emission spectra and 82% for the histograms of the digital images. The PLS-DA classification models reached 85% and 76% of CCR for the fluorescence and imaging data, respectively, after standardization. These results demonstrate the efficiency of standardization procedures applied to multivariate classification models developed from fluorescence spectroscopy and digital images.

[1]  A. Ferrer,et al.  Pixel classification methods for identifying and quantifying leaf surface injury from digital images , 2014 .

[2]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[3]  Vincent Baeten,et al.  Evaluation of the overall quality of olive oil using fluorescence spectroscopy. , 2015, Food chemistry.

[4]  Márcio José Coelho Pontes,et al.  Classification of extra virgin olive oil and verification of adulteration using digital images and discriminant analysis , 2015 .

[5]  D. Massart,et al.  Standardisation of near-infrared spectrometric instruments: A review , 1996 .

[6]  Welma T. S. Vilar,et al.  A novel strategy for the classification of naturally colored cotton fibers based on digital imaging and pattern recognition techniques , 2015 .

[7]  Svante Wold,et al.  Pattern recognition by means of disjoint principal components models , 1976, Pattern Recognit..

[8]  L. A. Stone,et al.  Computer Aided Design of Experiments , 1969 .

[9]  Jez Willian Batista Braga,et al.  Non-destructive identification of different types and brands of blue pen inks in cursive handwriting by visible spectroscopy and PLS-DA for forensic analysis , 2014 .

[10]  Paulo Henrique Gonçalves Dias Diniz,et al.  Identification of adulteration in ground roasted coffees using UV–Vis spectroscopy and SPA-LDA , 2015 .

[11]  Maria Fernanda Pimentel,et al.  Calibration transfer employing univariate correction and robust regression. , 2015, Analytica chimica acta.

[12]  Maria Fernanda Pimentel,et al.  Robust modeling for multivariate calibration transfer by the successive projections algorithm , 2005 .

[13]  Ronei J. Poppi,et al.  Discrimination between authentic and counterfeit banknotes using Raman spectroscopy and PLS-DA with uncertainty estimation , 2013 .

[14]  Maria Fernanda Pimentel,et al.  TRANSFERÊNCIA DE CALIBRAÇÃO EM MÉTODOS MULTIVARIADOS , 2007 .

[15]  Carolina V. Di Anibal,et al.  Standardization of UV-visible data in a food adulteration classification problem. , 2012, Food chemistry.

[16]  Andrew J Racher,et al.  Rapid high-throughput characterisation, classification and selection of recombinant mammalian cell line phenotypes using intact cell MALDI-ToF mass spectrometry fingerprinting and PLS-DA modelling. , 2014, Journal of biotechnology.

[17]  M. J. C. Pontes,et al.  Standardization of NIR data to identify adulteration in ethanol fuel , 2016 .

[18]  Steven D. Brown,et al.  Transfer of Multivariate Classification Models between Laboratory and Process Near-Infrared Spectrometers for the Discrimination of Green Arabica and Robusta Coffee Beans , 2006, Applied spectroscopy.

[19]  A. González,et al.  Use and misuse of supervised pattern recognition methods for interpreting compositional data. , 2007, Journal of chromatography. A.

[20]  Roberto Kawakami Harrop Galvão,et al.  A new validation criterion for guiding the selection of variables by the successive projections algorithm in classification problems , 2013 .

[21]  R. Poppi,et al.  Classification of Amazonian rosewood essential oil by Raman spectroscopy and PLS-DA with reliability estimation. , 2013, Talanta.

[22]  Maria Fernanda Pimentel,et al.  Classification of Brazilian and foreign gasolines adulterated with alcohol using infrared spectroscopy. , 2015, Forensic science international.

[23]  S. Peng,et al.  Calibration transfer based on maximum margin criterion for qualitative analysis using Fourier transform infrared spectroscopy. , 2012, The Analyst.

[24]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[25]  Richard G. Brereton,et al.  Chemometrics for Pattern Recognition , 2009 .

[26]  Anna Luiza Bizerra Brito,et al.  Near infrared reflectance spectrometry classification of lettuce using linear discriminant analysis , 2015 .

[27]  Steven D. Brown,et al.  Transfer of multivariate calibration models: a review , 2002 .