Terahertz Spectroscopy Determination of Benzoic Acid Additive in Wheat Flour by Machine Learning

  • Xudong SunEmail author
  • Ke Zhu
  • Junbin Liu
  • Jun Hu
  • Xiaogang Jiang
  • Yande Liu
  • Zhiyuan Gong


Investigations were carried out to develop terahertz (THz) techniques combined with machine learning methods for rapidly measuring benzoic acid (BA) additive in wheat flour. The absorption coefficient had a significant characteristic peak at 1.94 THz, which usually varies with the increase of BA additive concentrations. Correlation analysis was initiated to choose a frequency pair of 1.94 and 1.86 THz that improved the predictive ability of multiple linear regressions (MLR) model. Then, quantitative determination models were modeled between BA concentrations and THz absorption coefficients using partial least square (PLS) regression and least square support vector machine (LS-SVM). Compared with MLR and PLS models, the LS-SVM model could be regarded as an effective tool for quality control of wheat flour with a correlation coefficient of prediction (Rp) of 0.994 and root mean square error of prediction (RMSEP) of 0.12%. The results suggest that combining THz spectroscopy with LS-SVM has the potential to quantitatively analyze BA additive in wheat flour.


Food additive Terahertz spectroscopy Machine learning Benzoic acid Wheat flour 


Funding Information

This study received financial support from the Outstanding Youth Talent Program of Jiangxi Province (20171BCB23060), Education Department Project of Jiangxi Province (GJJ160478), China Scholarship Council (201808360317), Jiangxi Association for Science and Technology (JAST), and Doctor Start-up Program (368).


  1. 1.
    M. Winter, A consumer’s dictionary of food additives, New York: Three Rivers Press (2009).Google Scholar
  2. 2.
    Y. Abe-Onishi, C. Yomota, N. Sugimoto, H. Kubota, L. Tanamoto. Determination of benzoyl peroxide and benzoic acid in wheat flour by high-performance liquid chromatography and its identification by high-performance liquid chromatography-mass spectrometry. Food Chem. 1004 (2004) 209–214.Google Scholar
  3. 3.
    S. K. Mathanker, P. R. Weckler, N. Wang. Terahertz (THz) application in food and agriculture: a review. T. ASABE. 56(3) (2013) 1213–1226.Google Scholar
  4. 4.
    J. Qin, Y. Ying, L. Xie. The detection of agricultural products and food using terahertz spectroscopy: a review. Appl. Spectrosc. Rev. 48(6) (2013) 439–457.CrossRefGoogle Scholar
  5. 5.
    H. Ge, Y. Jiang, F. Lian, Y. Zhang, S. Xia. Quantitative determination of aflatoxin B1 concentration in acetonitrile by chemometric methods using terahertz spectroscopy. Food Chem. 209 (2016) 286–292.CrossRefGoogle Scholar
  6. 6.
    Z. Zheng, W. Fan, B. Xue. Study on benzoic acid by THz time-domain spectroscopy and density functional theory. Chin. Opt. Lett. 9 (2011) 1–3.Google Scholar
  7. 7.
    L. Jiang, M. Li, C. Li, H. Sun, L. Xu, B. Jin, Y. Liu. Terahertz spectra of L-ascorbic acid and Thiamine hydrochloride studied by terahertz spectroscopy and density functional theory. J. Infrared Millim. Terahertz Waves. 35 (2014) 871–880.CrossRefGoogle Scholar
  8. 8.
    W. Liu, C. Liu, J. Yu, Y. Zhang, J. Li, Y. Chen, L. Zhang. Discrimination of geographical origin of extra virgin olive oils using terahertz spectroscopy combined with chemometrics. Food Chem. 251 (2018) 86–92.CrossRefGoogle Scholar
  9. 9.
    J. Liu. Terahertz spectroscopy and chemometric tools for rapid identification of adulterated dairy product. Opt. Quan. Electron. 49 (2017) 1–8.CrossRefGoogle Scholar
  10. 10.
    Z. Li. Genetic algorithm that considers scattering for THz quantitative analysis. IEEE Trans. Terahertz Sci. Technol. 5(6) (2015) 1062–1067.CrossRefGoogle Scholar
  11. 11.
    Z. Li, A. Guan, H. Ge, F. Lian. Wavelength selection of amino acid THz absorption spectra for quantitative analysis by a self-adaptive genetic algorithm and comparison with mwPLS. Microchem. J. 132 (2017) 185–189.CrossRefGoogle Scholar
  12. 12.
    S. H. Lu, B. Q. Li, H. L. Zhai, X. Zhang, Z. Y. Zhang. An effective approach to quantitative analysis of ternary amino acids in foxtail millet substrate based on terahertz spectroscopy. Food Chem. 246 (2018) 220–227.CrossRefGoogle Scholar
  13. 13.
    S. Lu, X. Zhang, Z. Zhang, Y. Yang, Y. Xiang. Quantitative measurements of binary amino acids mixtures in yellow foxtail millet by terahertz time domain spectroscopy. Food Chem. 211 (2016) 494–501.CrossRefGoogle Scholar
  14. 14.
    J. Qin, L. Xie, and Y. Ying. Determination of tetracycline hydrochloride by terahertz spectroscopy with PLSR model. Food Chem. 170 (2015) 415–422.CrossRefGoogle Scholar
  15. 15.
    L. Duvillaret, F. Garet, and J. Coutaz. A reliable method for extraction of material parameters in terahertz time-domain spectroscopy. IEEE Journal of Selected Topics in Quantum Electronics, 2(1996) 739–746.CrossRefGoogle Scholar
  16. 16.
    P. U. Jepsen, D. G. Cooke, and M. M. Koch. Terahertz spectroscopy and imaging – modern techniques and application. Laser Photonics Rev. 5(2011) 124–166.CrossRefGoogle Scholar
  17. 17.
    X. Zhang, J. Xu. Introduction to THz wave photonics, New York: Springer Verlag (2009).Google Scholar
  18. 18.
    S. Mehrkanoon, J. A. K. Suykens. LS-SVM approximate solution to linear time varying descriptor systems. Automatica 48(10) (2012) 2502–2511.MathSciNetCrossRefzbMATHGoogle Scholar
  19. 19.
    Z. Chen, Z. Zhang, R. Zhu, Y. Xiang, Y. Yang, P. B. Harrington. Application of terahertz time-domain spectroscopy combined with chemometrics to quantitative analysis of imidacloprid in rice sample. J. Quant. Spectrosc. Radiat. 167 (2015) 1–9.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Mechatronics & Vehicle EngineeringEast China Jiaotong UniversityNanchangPeople’s Republic of China

Personalised recommendations