Quantitative Analysis of the Concentration of Coumarin in a Binary Mixture Using Terahertz Spectroscopy Combined with Optimized Least Square Support Vector Machine

The purpose of this study was to quantitatively analyze coumarin in a binary mixture system and to provide a more accurate and convenient potential for food safety inspection and supervision. This investigation has presented a novel terahertz time-domain spectroscopy (THz-TDS) approach and an optimized least square support vector machine (LS-SVM) to analyze the content of coumarin in the binary mixture of coumarin and vanillin. Terahertz responses of the binary mixtures have been measured and a Savitzky–Golay algorithm has been applied to process the absorption coefficient spectra. The principal component analysis has been used to extract features from the preprocessed data. The excellent prediction results can be obtained using LS-SVM optimized by sparrow search algorithm (SSA) with the coefficient of determination (R²), root-mean-square error, and residual predictive deviation of the prediction set were more than 0.999, 0.001, and 146, respectively. The research shows that the prediction effect of the LS-SVM algorithm optimized by the SSA model is better than that of the support vector machine (SVM) algorithm and LS-SVM algorithm without the SSA model. Our research shows that the combination of THz spectrum and SSAoptimized LS-SVM is very promising for the analysis of coumarin and vanillin binary mixtures, and has great potential for the quantitative analysis of more complex multicomponent mixtures.

1. Lowri S. de Jager, Gracia A. Perfetti, Gregory W. Diachenko, J. Chromatogr. A, 1145 (2007) 83–88 (2007).

2. Pei Liang, Yong Feng Zhou, De Zhang, Microchim. Acta, 302 (2019).

3. D. Havkin-Frenkel, F. C. Belanger, Appl. Microbiol. Biotech., 56, 296–314 (2001).

4. N. Robledo-O’Ryan, M. J. Matos, Bioorg. Med. Chem. Lett., 25, 621–632 (2017).

5. G. S. Clark, Perfumer &Flavorist, 20, 23–34 (1995).

6. A. W. Archer, J. Chromatogr., 447, N 1, 272–276 (1988).

7. EFSA, The EFSA J.,104, 1–36 (2004).

8. Mirjana Lonˇcar, Martina Jakovljevi´c, Foods, 9, 645 (2020).

9. E. L. Maistro, M. E. De Souza, R. P. Fedato, Environ. Heal., 78A, 109–118 (2015).

10. Harris H. Wisneski, AOAC Int., 84, No. 3 (2001).

11. Afidah A. Rahim, Food Chem., 126, 1412–1416 (2011).

12. Yan Shen, J. Agricult. Food Chem., 10881–10888 (2014).

13. W. Wang, J. Tang, S. Wang, L. Zhou, Z. D. Hu, J. Chromatogr. A, 1148, No. 1, 108–114 (2007).

14. J. Huang, P. Liang, J. Xu, Roy. Soc. Chem., 7, 49097 (2017).

15. Li Fu, J. Food Meas. Charact., 15, 5439–5444 (2021)

16. Lowri S. de Jager, Gracia A. Perfetti, Food Chem., 1701–1709 (2008).

17. Y. Shen, C. Han, B. Liu, Z. Lin, X. Zhou, C. Wang, Z. Zhu, J. Dairy Sci., 97, 679–686 (2014).

18. D. M. Mittleman, Nature Photon., 7, 666–669 (2013).

19. M. Walther, P. Plochocka, B. Fischer, H. Helm, P. U. Jepsen, Biopolymers, 67, 310–313 (2002).

20. J. E. Haddad, F. De Miollis, J. B. Sleiman, L. Canioni, P. Mounaix, B. Bousquet, Anal. Chem., 86, No. 10, 4927–4933 (2014).

21. P. H. Siegel, IEEE Transact. Microwave Theory and Techniques, 52, 2438–2447 (2004).

22. Tao Chen, Lingxiao Yu, Spectrochim. Acta A: Mol. Biomol. Spectrosc., 263, 120159 (2021).

23. Tao Chen, Xin Zhong, IEEE Transact. Terahertz Sci. Tech., 11, No. 3 (2021).

24. Tao Chen, Lingjie Ma, Food Sci., 87, No. 3, 1108–1118 (2022).

25. Noureddine Maamar, Int. Conf. Adv. Electrical Engineering (ICAEE) (2019).

26. J. T. Kindt, C. A. Schmuttenmaer, J. Phys. Chem., 100, 10373–10379 (1996).

27. V. N. Vapnik, The Nature of Statistical Learning Theory, New York, Springer Verlag (1995).

28. J. A. K. Suykens, J. Vandewalle, Neural Process Lett., 9, 293–300 (1999).

29. J. A. K. Suykens, J. Vandewalle, IEEE Trans. Circuits Syst. I, Fund. Theory Appl., 47, No. 7, 1109–1114 (2000).

30. X. Sun, Z. Zhou, C. Liu, F. U. Xinxin, Y. Dou, Food Sci. (2018).

31. Jiankai Xue, Bo Shen, Systems Sci. Control Eng., 22–34 (2020).