Independent components analysis to increase efficiency of discriminant analysis methods (FDA and LDA): Application to NMR fingerprinting of wine.

Discriminant analysis (DA) methods, such as linear discriminant analysis (LDA) or factorial discriminant analysis (FDA), are well-known chemometric approaches for solving classification problems in chemistry. In most applications, principle components analysis (PCA) is used as the first step to generate orthogonal eigenvectors and the corresponding sample scores are utilized to generate discriminant features for the discrimination. Independent components analysis (ICA) based on the minimization of mutual information can be used as an alternative to PCA as a preprocessing tool for LDA and FDA classification. To illustrate the performance of this ICA/DA methodology, four representative nuclear magnetic resonance (NMR) data sets of wine samples were used. The classification was performed regarding grape variety, year of vintage and geographical origin. The average increase for ICA/DA in comparison with PCA/DA in the percentage of correct classification varied between 6±1% and 8±2%. The maximum increase in classification efficiency of 11±2% was observed for discrimination of the year of vintage (ICA/FDA) and geographical origin (ICA/LDA). The procedure to determine the number of extracted features (PCs, ICs) for the optimum DA models was discussed. The use of independent components (ICs) instead of principle components (PCs) resulted in improved classification performance of DA methods. The ICA/LDA method is preferable to ICA/FDA for recognition tasks based on NMR spectroscopic measurements.

[1]  Y. Monakhova,et al.  Independent component analysis algorithms for spectral decomposition in UV/VIS analysis of metal-containing mixtures including multimineral food supplements and platinum concentrates , 2013 .

[2]  Delphine Jouan-Rimbaud Bouveresse,et al.  Independent component analysis as a pretreatment method for parallel factor analysis to eliminate artefacts from multiway data. , 2007, Analytica chimica acta.

[3]  Marco Arlorio,et al.  Application of ¹H NMR for the characterisation and authentication of ''Tonda Gentile Trilobata" hazelnuts from Piedmont (Italy). , 2014, Food chemistry.

[4]  Kwang-Sik Lee,et al.  An integrated analysis for determining the geographical origin of medicinal herbs using ICP-AES/ICP-MS and (1)H NMR analysis. , 2014, Food chemistry.

[5]  Tapani Ristaniemi,et al.  Answering six questions in extracting children’s mismatch negativity through combining wavelet decomposition and independent component analysis , 2011, Cognitive Neurodynamics.

[6]  Douglas N. Rutledge,et al.  Fruit juice authentication by 1H NMR spectroscopy in combination with different chemometrics tools , 2008, Analytical and bioanalytical chemistry.

[7]  Yulia B. Monakhova,et al.  Independent components in spectroscopic analysis of complex mixtures , 2010, 1009.0534.

[8]  Dirk W Lachenmeier,et al.  Determination of rice type by 1H NMR spectroscopy in combination with different chemometric tools , 2014 .

[9]  Johanna Smeyers-Verbeke,et al.  Handbook of Chemometrics and Qualimetrics: Part A , 1997 .

[10]  Yuan Ren,et al.  Classification for high-throughput data with an optimal subset of principal components , 2009, Comput. Biol. Chem..

[11]  L. Gribov,et al.  Methods of the decomposition of spectra of various origin in the analysis of complex mixtures , 2011 .

[12]  Andrzej Cichocki,et al.  Adaptive Blind Signal and Image Processing - Learning Algorithms and Applications , 2002 .

[13]  Theodoros N. Arvanitis,et al.  A hybrid method of application of independent component analysis to in vivo 1H MR spectra of childhood brain tumours , 2012, NMR in biomedicine.

[14]  Kwang-Sik Lee,et al.  Discrimination of the geographical origin of beef by (1)H NMR-based metabolomics. , 2010, Journal of agricultural and food chemistry.

[15]  M. Lees Food authenticity and traceability. , 2003 .

[16]  Dominique Bertrand,et al.  SAISIR: A new general chemometric toolbox , 2014 .

[17]  Giulio Cozzi,et al.  Application of near-infrared spectroscopy as an alternative to chemical and color analysis to discriminate the production chains of Asiago d'Allevo cheese. , 2009, Journal of agricultural and food chemistry.

[18]  D. Jouan-Rimbaud Bouveresse,et al.  Two novel methods for the determination of the number of components in independent components analysis models , 2012 .

[19]  Philippe Courcoux,et al.  Stepwise canonical discriminant analysis of continuous digitalized signals: Application to chromatograms of wheat proteins , 1990 .

[20]  D. Rutledge,et al.  Evolving window zone selection method followed by independent component analysis as useful chemometric tools to discriminate between grapefruit juice, orange juice and blends. , 2007, Analytica chimica acta.

[21]  J. Pulkkinen,et al.  Independent component analysis to proton spectroscopic imaging data of human brain tumours. , 2005, European journal of radiology.

[22]  E. K. Kemsley,et al.  THE USE AND MISUSE OF CHEMOMETRICS FOR TREATING CLASSIFICATION PROBLEMS , 1997 .

[23]  Fei Liu,et al.  Variable selection in visible/near infrared spectra for linear and nonlinear calibrations: a case study to determine soluble solids content of beer. , 2009, Analytica chimica acta.

[24]  W. Cai,et al.  Chemometric approach for fast analysis of prometryn in human hair by GC-MS. , 2013, Journal of separation science.

[25]  C. Fauhl-Hassek,et al.  Authentication of the botanical and geographical origin of distillers dried grains and solubles (DDGS) by FT-IR spectroscopy. , 2013, Journal of agricultural and food chemistry.

[26]  I. Schelkanova,et al.  Independent component analysis of broadband near-infrared spectroscopy data acquired on adult human head , 2011, Biomedical optics express.

[27]  Soo-Young Lee,et al.  Discriminant Independent Component Analysis , 2011, IEEE Trans. Neural Networks.

[28]  Gerard Downey,et al.  Confirmation of food origin claims by fourier transform infrared spectroscopy and chemometrics: extra virgin olive oil from Liguria. , 2009, Journal of agricultural and food chemistry.

[29]  W. T. O'Hare,et al.  Discrimination of Sri Lankan black teas using fluorescence spectroscopy and linear discriminant analysis. , 2013, Journal of the science of food and agriculture.

[30]  A. Sabatini,et al.  Classification of Italian honeys by 2D HR-NMR. , 2008, Journal of agricultural and food chemistry.

[31]  M. Scarpiniti,et al.  Monitoring of marine mucilage formation in Italian seas investigated by infrared spectroscopy and independent component analysis , 2012, Environmental Monitoring and Assessment.

[32]  Colm O'Donnell,et al.  Multivariate Analysis of Attenuated Total Reflection—Fourier Transform Infrared Spectroscopic Data to Confirm the Origin of Honeys , 2008, Applied spectroscopy.

[33]  F. Nuez,et al.  Multivariate analysis applied to tomato hybrid production , 1984, Theoretical and Applied Genetics.

[34]  Gerard Downey,et al.  Geographic Classification of Extra Virgin Olive Oils from the Eastern Mediterranean by Chemometric Analysis of Visible and Near-Infrared Spectroscopic Data , 2003, Applied spectroscopy.

[35]  E. Oja,et al.  Independent Component Analysis , 2013 .

[36]  R. Karoui,et al.  Mid infrared and fluorescence spectroscopies coupled with factorial discriminant analysis technique to identify sheep milk from different feeding systems. , 2011, Food chemistry.

[37]  Wenming Zheng,et al.  Complexity-reduced implementations of complete and null-space-based linear discriminant analysis , 2013, Neural Networks.

[38]  K. Linnet,et al.  On the sensitivity of linear discriminant analysis to sampling variation and analytical errors. , 1988, Computers and biomedical research, an international journal.

[39]  M. Spraul,et al.  Application of automated eightfold suppression of water and ethanol signals in 1H NMR to provide sensitivity for analyzing alcoholic beverages , 2011, Magnetic resonance in chemistry : MRC.

[40]  Mohammadreza Khanmohammadi,et al.  Application of Linear Discriminant Analysis and Attenuated Total Reflectance Fourier Transform Infrared Microspectroscopy for Diagnosis of Colon Cancer , 2011, Pathology & Oncology Research.

[41]  K. Héberger,et al.  Method and model comparison by sum of ranking differences in cases of repeated observations (ties) , 2013 .

[42]  L. Leita,et al.  Traceability of Italian garlic (Allium sativum L.) by means of HRMAS-NMR spectroscopy and multivariate data analysis. , 2012, Food chemistry.

[43]  K. Héberger Sum of ranking differences compares methods or models fairly , 2010 .

[44]  Manfred Spraul,et al.  Targeted and nontargeted wine analysis by (1)h NMR spectroscopy combined with multivariate statistical analysis. Differentiation of important parameters: grape variety, geographical origin, year of vintage. , 2013, Journal of agricultural and food chemistry.

[45]  F. Barbosa,et al.  Identification of species of the Euterpe genus by rare earth elements using inductively coupled plasma mass spectrometry and linear discriminant analysis. , 2014, Food chemistry.

[46]  Feng Wei,et al.  Rapid discrimination of Chinese red ginseng and Korean ginseng using an electronic nose coupled with chemometrics. , 2012, Journal of pharmaceutical and biomedical analysis.

[47]  K. Héberger,et al.  Sum of ranking differences for method discrimination and its validation: comparison of ranks with random numbers , 2011 .

[48]  Remedios Castro Mejías,et al.  A new FT-IR method combined with multivariate analysis for the classification of vinegars from different raw materials and production processes. , 2010, Journal of the science of food and agriculture.

[49]  C. Ruckebusch,et al.  Multivariate curve resolution: a review of advanced and tailored applications and challenges. , 2013, Analytica chimica acta.

[50]  S. D. Jong,et al.  Handbook of Chemometrics and Qualimetrics , 1998 .

[51]  Marit Aursand,et al.  Bioactive compounds in cod (Gadus morhua) products and suitability of 1H NMR metabolite profiling for classification of the products using multivariate data analyses. , 2005, Journal of agricultural and food chemistry.

[52]  Thomas Kuballa,et al.  Independent component analysis (ICA) algorithms for improved spectral deconvolution of overlapped signals in 1H NMR analysis: application to foods and related products , 2014, Magnetic resonance in chemistry : MRC.

[53]  Andrzej Cichocki,et al.  Adaptive blind signal and image processing , 2002 .

[54]  D. Axelson,et al.  (13)C NMR pattern recognition techniques for the classification of Atlantic salmon (Salmo salar L.) according to their wild, farmed, and geographical origin. , 2009, Journal of agricultural and food chemistry.

[55]  C. Jang,et al.  Using multivariate statistical methods to assess the groundwater quality in an arsenic-contaminated area of Southwestern Taiwan , 2012, Environmental Monitoring and Assessment.

[56]  K. Héberger,et al.  Supervised pattern recognition in food analysis. , 2007, Journal of chromatography. A.

[57]  Károly Héberger,et al.  Classification of gilthead sea bream (Sparus aurata) from 1H NMR lipid profiling combined with principal component and linear discriminant analysis. , 2007, Journal of agricultural and food chemistry.

[58]  L Catucci,et al.  Non-targeted 1H NMR fingerprinting and multivariate statistical analyses for the characterisation of the geographical origin of Italian sweet cherries. , 2013, Food chemistry.

[59]  Manfred Spraul,et al.  Synergistic effect of the simultaneous chemometric analysis of ¹H NMR spectroscopic and stable isotope (SNIF-NMR, ¹⁸O, ¹³C) data: application to wine analysis. , 2014, Analytica chimica acta.