Identification of edible oils using terahertz spectroscopy combined with genetic algorithm and partial least squares discriminant analysis

The authentication and identification of different edible oils have become a focus of attention in the food safety field. In this work, we propose a method for distinction of edible oils by using a terahertz (THz) spectrum combined with genetic algorithm (GA) and partial least squares discriminant analysis (PLS-DA). To evaluate the robustness of the model, we also employ full spectra PLS (fsPLS), interval PLS (iPLS), and backward interval (biPLS) algorithms to verify the classification performance through variable selection. The results demonstrate that the GA-PLS-DA model has a smaller root mean square error of prediction (RESEP), a larger correlation coefficient of prediction (Rp), and higher classification accuracy than other models. In conclusion, the THz spectrum coupled with chemometrics is an effective method for differentiating various types of edible oils.

[1]  Colm P. O'Donnell,et al.  Terahertz time domain spectroscopy and imaging: Emerging techniques for food process monitoring and quality control , 2012 .

[2]  Kimito Funatsu,et al.  GA Strategy for Variable Selection in QSAR Studies: GA-Based PLS Analysis of Calcium Channel Antagonists , 1997, J. Chem. Inf. Comput. Sci..

[3]  Kurt Varmuza,et al.  Determination of the total acid number (TAN) of used gas engine oils by IR and chemometrics applying a combined strategy for variable selection , 2010 .

[4]  R. Leardi.  Genetic algorithms in chemometrics and chemistry: a review , 2001 .

[5]  Jinrong Li,et al.  Rapid identification of edible oil and swill-cooked dirty oil by using near-infrared spectroscopy and sparse representation classification , 2015 .

[6]  Mark A. Arnold,et al.  Terahertz Time-Domain Spectroscopy of Solid Samples: Principles, Applications, and Challenges , 2011 .

[7]  Bingpo Zhang,et al.  Quantitative analysis of adulteration of extra virgin olive oil using Raman spectroscopy improved by Bayesian framework least squares support vector machines , 2012 .

[8]  Sudjadi,et al.  Use of Fourier Transform Infrared Spectroscopy in Combination with Partial Least Square for Authentication of Black Seed Oil , 2015 .

[9]  Yinchao Zhang,et al.  Classification of edible oils using 532 nm laser-induced fluorescence combined with support vector machine , 2013 .

[10]  Zou Xiaobo,et al.  Use of FT-NIR spectrometry in non-invasive measurements of soluble solid contents (SSC) of ‘Fuji’ apple based on different PLS models , 2007 .

[11]  R. Leardi,et al.  Sequential application of backward interval partial least squares and genetic algorithms for the selection of relevant spectral regions , 2004 .

[12]  Zhicheng Zhou,et al.  Feasibility study of discriminating edible vegetable oils by 2D-NIR , 2012 .

[13]  Yinchao Zhang,et al.  Fluorescence polarization technique: a new method for vegetable oils classification , 2015 .

[14]  A. Höskuldsson.  Variable and subset selection in PLS regression , 2001 .

[15]  Yibin Ying,et al.  The Application of Terahertz Spectroscopy to Protein Detection: A Review , 2014 .

[16]  I. Helland.  Some theoretical aspects of partial least squares regression , 2001 .

[17]  Yinchao Zhang,et al.  Characterization of edible oils using time-resolved fluorescence , 2014 .

[18]  S. Engelsen,et al.  Interval Partial Least-Squares Regression (iPLS): A Comparative Chemometric Study with an Example from Near-Infrared Spectroscopy , 2000 .

[19]  Qiang Wang,et al.  Qualitative and quantitative identification of nitrofen in terahertz region , 2013 .

[20]  Emma Pickwell-MacPherson,et al.  Terahertz spectroscopy: Its future role in medical diagnoses , 2011 .

[21]  Yibin Ying,et al.  The Detection of Agricultural Products and Food Using Terahertz Spectroscopy: A Review , 2013 .

[22]  Tahir Mehmood,et al.  A review of variable selection methods in Partial Least Squares Regression , 2012 .

[23]  S. Keleş,et al.  Sparse partial least squares regression for simultaneous dimension reduction and variable selection , 2010, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[24]  Riccardo Leardi,et al.  Application of genetic algorithm–PLS for feature selection in spectral data sets , 2000 .

[25]  P. Valderrama,et al.  Ultraviolet spectroscopy and supervised pattern recognition methods for authentication of transgenic and non-transgenic soybean oils , 2015 .

[26]  Hua Wang,et al.  Characterization and authentication of four important edible oils using free phytosterol profiles established by GC-GC-TOF/MS , 2014 .

[27]  Liangxiao Zhang,et al.  Advanced detection methods for traceability of origin and authenticity of olive oils , 2015 .