DETERMINATION AND VISUALIZATION OF DIFFERENT LEVELS OF DEOXYNIVALENOL IN BULK WHEAT KERNELS BY HYPERSPECTRAL IMAGING

A hyperspectral imaging system is proposed as a method to rapidly and non-destructively predict mycotoxin deoxynivalenol (DON) levels in FHB-infected wheat kernels. Standard normal variate transformation and multiplicative scatter correction (MSC) were used in spectral preprocessing. The successive projections algorithm (SPA) and random frog algorithm were used to select the optical wavelengths. Finally, the support vector machine (SVM) technique and partial least squares discriminant analysis were applied to establish different models for determining DON levels. Based on a comparison of the results, the MSC-SPA-SVM model, with the highest classification accuracy (100.00% for the training test and 97.92% for the testing set), gave the best performance, and a visualization map of the DON content level based on this model was created.

гиперспектральное изображение, объем пшеничных зерен, содержание деоксиниваленола, выбор оптических длин волн, классификационная модель, визуализация пространственного распределения, hyperspectral imaging, bulk wheat kernels, deoxynivalenol content, optical wavelength selection, classification model, visualization map

1. http://www.dagz.boku.ac.at/fileadmin/data/H03000/H94000/pdf/Mycotoxin_regulations/ SCF_DON_opinion.pdf Retrieved 3-17-2017.

2. S. Simsek, K. Burgess, K. L. Whitney, Y. Gu, S.Y. Qian, Food Control, 2, 287-292 (2012).

3. L. Smeesters, W. Meulebroeck, S. Raeymaekers, H. Thienpont, Food Control, 70, 48-57 (2016).

4. J. G. A. Barbedo, C. S.Tibola, J. M. C. Fernandes, Biosyst. Eng., 131, 65-76 (2015).

5. J. J. Pestka, Anim. Breed. Feed, 3, 283-298 (2008).

6. A. Abysique, C. Tardivel, J. D. Troadec, B. Félix, PLoS One, 7, e133355 (2015).

7. M. Beyer, F. Pogoda, F. K. Ronellenfitsch, L. Hoffmann, T. Udelhoven, Int. J. Food Microbiol., 3, 370-374 (2010).

8. C. Maragos, M. Busman, Y. Sugita-Konishi, Food Addit. Contam., 8, 816-825 (2006). 851-9

9. A. B. Amar, S. Oueslati, A. Ghorbel, A. Mliki, Food Control, 2, 506-510 (2012).

10. M. S. Hamada, Y. N. Yin, Z. Ma, Cereal Res. Commun., 1, 85-94 (2012).

11. B. Jaillais, P. Roumet, L. Pinson-Gadais, D. Bertrand, Food Control, 54, 250-258 (2015).

12. H. Pettersson, L. Åberg, Food Control, 4, 229-232 (2003).

13. H. Cen, R. Lu, Q. Zhu, F. Mendoza, Postharvest Biol. Technol., 111, 352-361 (2016).

14. M. A. Shahin, S. J. Symons, Comput. Electron. Agric., 1, 107-112 (2011).

15. M. C. U. Araújo, T. C. B. Saldanha, R. K. H. Galvão, T. Yoneyama, H. C. Chame, V. Visani, Chemom. Intell. Lab. Syst., 2, 65-73 (2001).

16. H. Ma, H. Y. Ji, W. S. Lee, Spectrosc. Spectr. Anal., 36, No. 7, 2344-2350 (2017).

17. W. Luo, Y. Z. Du, H. L. Zhang, Spectrosc. Spectr. Anal., 33, No. 11, 3536-3541 (2016).

18. Y. Yuan, W. Wang, X. Chu, M. J. Xi, Spectrosc. Spectr. Anal., 36, No. 1, 226-230 (2016).

19. H. D. Li, Q. S. Xu, Y. Z. Liang, Anal. Chim. Acta, 740, 20-26 (2012).

20. P. J. Green, Biometrika, 4, 711-732 (1995).

21. M. H. Hu, Q. L. Dong, B. L. Liu, U. L.Opara, L. Chen, Postharvest Biol. Technol., 106, 1-10 (2015).

22. X. Li, C. Sun, L. Luo, Y. He, Comput. Electron. Agric., 112, 28-35 (2015).

23. S. Wold, M. Sjostrom, L. Eriksson, Chemom. Intell. Lab. Syst., 58, No. 2, 109-130 (2001).

24. M. Barker, W. Rayens, J. Chemom., 17, 166-173 (2003).

25. V. N. Vapnik, A. Lerner, Autom. Rem. Contr., 6, 774-780 (2008).

26. W. Wang, Z. Xu, W. Lu, X. Zhang, Neurocomputing, 3-4, 643-663 (2003).

27. H. Lin, Q. Chen, J. Zhao, P. Zhou, J. Pharma. Biomed., 5, 803-808 (2009).

28. Q. Yang, D. W. Sun, W. W. Cheng, J. Food Eng., 192, 53-60 (2017).

29. J. H. Cheng, D. W. Sun, LWT-Food Sci. Technol., 2, 892-898 (2015).

30. G. Elmasry, D. W. Sun, P. Allen, Food Res. Int., 9, 2624-2633 (2011).