Mid-Infrared Spectroscopy for Coffee Variety Identification: Comparison of Pattern Recognition Methods

The potential of using mid-infrared transmittance spectroscopy combined with pattern recognition algorithm to identify coffee variety was investigated. Four coffee varieties in China were studied, including Typica Arabica coffee from Yunnan Province, Catimor Arabica coffee from Yunnan Province, Fushan Robusta coffee from Hainan Province, and Xinglong Robusta coffee from Hainan Province. Ten different pattern recognition methods were applied on the optimal wavenumbers selected by principal component analysis loadings. These methods were classified as highly effective methods (soft independent modelling of class analogy, support vector machine, back propagation neural network, radial basis function neural network, extreme learning machine, and relevance vector machine), methods of medium effectiveness (partial least squares-discrimination analysis, nearest neighbors, and random forest), and methods of low effectiveness (Naive Bayes classifier) according to the classification accuracy for coffee variety identification.

[1]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001 .

[2]  P. Szefer,et al.  Differentiation of market coffee and its infusions in view of their mineral composition. , 2007, The Science of the total environment.

[3]  Han Zhao,et al.  Extreme learning machine: algorithm, theory and applications , 2013, Artificial Intelligence Review.

[4]  B. Lendl,et al.  Rapid method for the discrimination of red wine cultivars based on mid-infrared spectroscopy of phenolic wine extracts. , 2001, Journal of agricultural and food chemistry.

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[6]  Barry J. Wythoff,et al.  Backpropagation neural networks , 1993 .

[7]  Nathalie Dupuy,et al.  Comparison of PLS1-DA, PLS2-DA and SIMCA for classification by origin of crude petroleum oils by MIR and virgin olive oils by NIR for different spectral regions , 2011 .

[8]  M. Barker,et al.  Partial least squares for discrimination , 2003 .

[9]  F. Thomas,et al.  Rapid approach to identify the presence of Arabica and Robusta species in coffee using 1H NMR spectroscopy. , 2015, Food chemistry.

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

[11]  Peter Bode,et al.  Organic coffee discrimination with INAA and data mining/KDD techniques: new perspectives for coffee trade , 2002 .

[12]  J. M. González-Sáiz,et al.  An evaluation of orthogonal signal correction methods for the characterisation of arabica and robusta coffee varieties by NIRS , 2004 .

[13]  Károly Héberger,et al.  Botanical and geographical characterization of green coffee (Coffea arabica and Coffea canephora): chemometric evaluation of phenolic and methylxanthine contents. , 2009, Journal of agricultural and food chemistry.

[14]  S. Jun,et al.  Fourier transform infrared spectroscopy for Kona coffee authentication. , 2009, Journal of food science.

[15]  V. Krivan,et al.  Multielement analysis of green coffee and its possible use for the determination of origin , 1993 .

[16]  C. Pizarro,et al.  Coffee varietal differentiation based on near infrared spectroscopy. , 2007, Talanta.

[17]  C. Barron.  Prediction of relative tissue proportions in wheat mill streams by fourier transform mid-infrared spectroscopy. , 2011, Journal of agricultural and food chemistry.

[18]  Siegfried Wartewig,et al.  Pharmaceutical applications of Mid-IR and Raman spectroscopy. , 2005, Advanced drug delivery reviews.

[19]  Julio Nogales-Bueno,et al.  Determination of technological maturity of grapes and total phenolic compounds of grape skins in red and white cultivars during ripening by near infrared hyperspectral image: a preliminary approach. , 2014, Food chemistry.

[20]  U. Halici,et al.  Intelligent biometric techniques in fingerprint and face recognition , 2000 .

[21]  Luis E Rodriguez-Saona,et al.  Rapid authentication of concord juice concentration in a grape juice blend using Fourier-Transform infrared spectroscopy and chemometric analysis. , 2014, Food chemistry.

[22]  Roman M. Balabin,et al.  Gasoline classification using near infrared (NIR) spectroscopy data: comparison of multivariate techniques. , 2010, Analytica chimica acta.

[23]  L. Lim,et al.  Feasibility study on chemometric discrimination of roasted Arabica coffees by solvent extraction and Fourier transform infrared spectroscopy. , 2011, Journal of agricultural and food chemistry.

[24]  R. Shaw,et al.  Exploration of attenuated total reflectance mid-infrared spectroscopy and multivariate calibration to measure immunoglobulin G in human sera. , 2015, Talanta.

[25]  Sarah Jane Delany.  k-Nearest Neighbour Classifiers , 2007 .

[26]  Bernard Van Eerdenbrugh,et al.  Application of mid-IR spectroscopy for the characterization of pharmaceutical systems. , 2011, International journal of pharmaceutics.

[27]  Zhengyu Jin,et al.  Monitoring of fermentation process parameters of Chinese rice wine using attenuated total reflectance mid-infrared spectroscopy , 2015 .

[28]  D. Sali,et al.  In Situ Nondestructive Identification of Natural Dyes in Ancient Textiles by Reflection Fourier Transform Mid-Infrared (FT-MIR) Spectroscopy , 2015, Applied spectroscopy.

[29]  O. Busto,et al.  Identification of olive oil sensory defects by multivariate analysis of mid infrared spectra. , 2015, Food chemistry.

[30]  P. Hildebrandt,et al.  Discrimination of green arabica and Robusta coffee beans by Raman spectroscopy. , 2010, Journal of agricultural and food chemistry.

[31]  Daniel Cozzolino,et al.  Varietal discrimination of Australian wines by means of mid-infrared spectroscopy and multivariate analysis. , 2008, Analytica chimica acta.

[32]  Laura Ruth Cagliani,et al.  NMR based geographical characterization of roasted coffee. , 2012, Talanta.

[33]  E. K. Kemsley,et al.  Discrimination between Coffea arabica and Coffea canephora variant robusta beans using infrared spectroscopy , 1995 .

[34]  Douglas Fernandes Barbin,et al.  Grape seed characterization by NIR hyperspectral imaging , 2013 .

[35]  Serge Kokot,et al.  A near-infrared reflectance spectroscopy method for direct analysis of several chemical components and properties of fruit, for example, Chinese hawthorn. , 2013, Journal of agricultural and food chemistry.

[36]  Marc Meurens,et al.  Chemical discrimination of arabica and robusta coffees by Fourier transform Raman spectroscopy. , 2005, Journal of agricultural and food chemistry.

[37]  J. Wist,et al.  Coffee's country of origin determined by NMR: the Colombian case. , 2015, Food chemistry.

[38]  Márcia M. C. Ferreira,et al.  Pattern recognition applied to mineral characterization of Brazilian coffees and sugar-cane spirits ☆ , 2005 .

[39]  N. Dupuy,et al.  Rapid quantitative determination of oleuropein in olive leaves (Olea europaea) using mid-infrared spectroscopy combined with chemometric analyses , 2012 .

[40]  Gozde Gurdeniz,et al.  Classification of Turkish olive oils with respect to cultivar, geographic origin and harvest year, using fatty acid profile and mid-IR spectroscopy , 2008 .

[41]  A. Materny,et al.  Discrimination between Arabica and Robusta green coffee using visible micro Raman spectroscopy and chemometric analysis , 2011 .

[42]  J. A. Fernández Pierna,et al.  Origin identification of dried distillers grains with solubles using attenuated total reflection Fourier transform mid-infrared spectroscopy after in situ oil extraction. , 2015, Food chemistry.

[43]  E. K. Kemsley,et al.  Discriminant analysis and class modelling of spectroscopic data , 1998 .

[44]  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.