Detection of adulterants such as sweeteners materials in honey using near-infrared spectroscopy and chemometrics

Abstract Near-infrared (NIR) spectroscopy combined with chemometrics methods has been used to detect adulteration of honey samples. The sample set contained 135 spectra of authentic (n = 68) and adulterated (n = 67) honey samples. Spectral data were compressed using wavelet transformation (WT) and principal component analysis (PCA), respectively. In this paper, five classification modeling methods including least square support vector machine (LS-SVM), support vector machine (SVM), back propagation artificial neural network (BP-ANN), linear discriminant analysis (LDA), and K-nearest neighbors (KNN) were adopted to correctly classify pure and adulterated honey samples. WT proved more effective than PCA, as a means for variables selection. Best classification models were achieved with LS-SVM. A total accuracy of 95.1% and the area under the receiver operating characteristic curves (AUC) of 0.952 for test set were obtained by LS-SVM. The results showed that WT-LS-SVM can be as a rapid screening technique for detection of this type of honey adulteration with good accuracy and better generalization.

[1]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[2]  D. Cabrol-Bass,et al.  Honey characterization and adulteration detection by pattern recognition applied on HPAEC-PAD profiles. 1. Honey floral species characterization. , 2003, Journal of agricultural and food chemistry.

[3]  D. Massart,et al.  Application of wavelet transform to extract the relevant component from spectral data for multivariate calibration. , 1997, Analytical chemistry.

[4]  Yong He,et al.  Discriminating varieties of tea plant based on Vis/NIR spectral characteristics and using artificial neural networks , 2008 .

[5]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[6]  J. Irudayaraj,et al.  Rapid Determination of Invert Cane Sugar Adulteration in Honey Using FTIR Spectroscopy and Multivariate Analysis , 2003 .

[7]  Jordi Coello,et al.  NIR calibration in non-linear systems: different PLS approaches and artificial neural networks , 2000 .

[8]  Dusan Stulik,et al.  Simple encoding of infrared spectra for pattern recognition Part 2. Neural network approach using back-propagation and associative Hopfield memory , 1995 .

[9]  Mauro Bacci,et al.  Principal component analysis of near-infrared spectra of alteration products in calcareous samples: An application to works of art , 1997 .

[10]  Roberto Muñoz,et al.  Multivariate calibration model from overlapping voltammetric signals employing wavelet neural networks , 2006 .

[11]  Mohamed Cheriet,et al.  Model selection for the LS-SVM. Application to handwriting recognition , 2009, Pattern Recognit..

[12]  Desire L. Massart,et al.  Feature selection in principal component analysis of analytical data , 2002 .

[13]  P. Hopke,et al.  Comparison of rule-building expert systems with pattern recognition for the classification of analytical data , 1987 .

[14]  Davide Bertelli,et al.  Classification of Italian honeys by mid-infrared diffuse reflectance spectroscopy (DRIFTS) , 2007 .

[15]  Ana I Cabañero,et al.  Liquid chromatography coupled to isotope ratio mass spectrometry: a new perspective on honey adulteration detection. , 2006, Journal of agricultural and food chemistry.

[16]  M. Grenier-loustalot,et al.  Study and validity of 13C stable carbon isotopic ratio analysis by mass spectrometry and 2H site-specific natural isotopic fractionation by nuclear magnetic resonance isotopic measurements to characterize and control the authenticity of honey. , 2007, Analytica chimica acta.

[17]  Gerard Downey,et al.  Potential of near Infrared Transflectance Spectroscopy to Detect Adulteration of Irish Honey by Beet Invert Syrup and High Fructose Corn Syrup , 2006 .

[18]  Daniel Cabrol-Bass,et al.  Detection and quantification of honey adulteration via direct incorporation of sugar syrups or bee-feeding: preliminary study using high-performance anion exchange chromatography with pulsed amperometric detection (HPAEC-PAD) and chemometrics , 2005 .

[19]  C. Biliaderis,et al.  Composition, thermal and rheological behaviour of selected Greek honeys , 2004 .

[20]  T. B. Murphy,et al.  A comparison of model-based and regression classification techniques applied to near infrared spectroscopic data in food authentication studies , 2007 .

[21]  Nieves Corzo,et al.  HPAEC-PAD oligosaccharide analysis to detect adulterations of honey with sugar syrups , 2008 .

[22]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[23]  G. Osorio-Revilla,et al.  Application of FTIR-HATR spectroscopy and multivariate analysis to the quantification of adulterants in Mexican honeys. , 2009 .

[24]  David H. Burns,et al.  Parsimonious calibration models for near-infrared spectroscopy using wavelets and scaling functions , 2006 .

[25]  F Despagne,et al.  Neural networks in multivariate calibration. , 1998, The Analyst.

[26]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[27]  Joseph Maria Kumar Irudayaraj,et al.  Classification of simple and complex sugar adulterants in honey by mid-infrared spectroscopy , 2002 .

[28]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[29]  N. Sbirrazzuoli,et al.  Application of DSC as a tool for honey floral species characterization and adulteration detection , 2003 .

[30]  Yi-Zeng Liang,et al.  A non‐linear mapping‐based generalized backpropagation network for unsupervised learning , 1996 .

[31]  Gerard Downey,et al.  Application of Fourier transform midinfrared spectroscopy to the discrimination between Irish artisanal honey and such honey adulterated with various sugar syrups. , 2006, Journal of agricultural and food chemistry.

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

[33]  Gerard Downey,et al.  Initial study of honey adulteration by sugar solutions using midinfrared (MIR) spectroscopy and chemometrics. , 2004, Journal of agricultural and food chemistry.

[34]  Joseph Maria Kumar Irudayaraj,et al.  Detection of inverted beet sugar adulteration of honey by FTIR spectroscopy , 2001 .

[35]  David De Jong,et al.  Detection of adulteration of commercial honey samples by the 13C/12C isotopic ratio , 2003 .