DOI QR코드

DOI QR Code

Discrimination model for cultivation origin of paper mulberry bast fiber and Hanji based on NIR and MIR spectral data combined with PLS-DA

닥나무 인피섬유와 한지의 원산지 판별모델 개발을 위한 NIR 및 MIR 스펙트럼 데이터의 PLS-DA 적용

  • Jang, Kyung-Ju (Korea Restoration Technology Division, National Research Institute of Cultural Heritage) ;
  • Jung, So-Yoon (Korea Restoration Technology Division, National Research Institute of Cultural Heritage) ;
  • Go, In-Hee (Korea Restoration Technology Division, National Research Institute of Cultural Heritage) ;
  • Jeong, Seon-Hwa (Korea Restoration Technology Division, National Research Institute of Cultural Heritage)
  • 장경주 (국립문화재연구소, 복원기술연구실) ;
  • 정소윤 (국립문화재연구소, 복원기술연구실) ;
  • 고인희 (국립문화재연구소, 복원기술연구실) ;
  • 정선화 (국립문화재연구소, 복원기술연구실)
  • Received : 2018.10.15
  • Accepted : 2019.01.22
  • Published : 2019.02.25

Abstract

The objective of this study was the development of a discrimination model for the cultivational origin of paper mulberry bast fiber and Hanji using near infrared (NIR) and mid infrared (MIR) spectroscopy combined with partial least squares discriminant analysis (PLS-DA). Paper mulberry bast fiber was purchased in 10 different regions of Korea, and used to make Hanji. PLS-DA was performed using pre-treated FT-NIR and FT-MIR spectral data for paper mulberry bast fiber and Hanji. PLS-DA of paper mulberry bast fiber and Hanji samples, using FT-NIR spectral data, showed 100 % performance in cross validation and the confusion matrix (accuracy, sensitivity, and specificity). The discrimination models showed four regional groups which demonstrated clearer separation and much superior score plots in the NIR spectral data-based model than in the MIR spectral data-based model. Furthermore, the discrimination model based on the NIR spectral data of paper mulberry bast fiber had highly similar score morphology to that of the discrimination model based on the NIR spectral data of Hanji.

Keywords

Paper mulberry bast fiber;Hanji;Near infrared spectroscopy;Mid infrared spectroscopy;Partial least squares discriminant analysis

BGHHBN_2019_v32n1_7_f0001.png 이미지

Fig. 1. Illustration of PLS-DA for models that includes four classes.24,25

BGHHBN_2019_v32n1_7_f0002.png 이미지

Fig. 2. FT-NIR raw spectra and second derivative spectra of (a) Paper mulberry bast fiber and (b) Hanji.

BGHHBN_2019_v32n1_7_f0003.png 이미지

Fig. 3. FT-MIR raw spectra and second derivative spectra of (a) Paper mulberry bast fiber and (b) Hanji.

BGHHBN_2019_v32n1_7_f0004.png 이미지

Fig. 4. Average second derivative FT-NIR and FT-MIR spectra of major cultivation region of (a) Paper mulberry bast fiber and (b) Hanji.

BGHHBN_2019_v32n1_7_f0005.png 이미지

Fig. 5. A two-dimensional PLS-DA score of the (a) FT-NIR spectral data from Paper mulberry bast fiber, (b) FT-MIR spectral data from Paper mulberry bast fiber, (c) FT-NIR spectral data from Hanji and (d) FT-MIR spectral data from Hanji

Table 1. The sample abbreviation and collection origin of Korean Paper mulberry

BGHHBN_2019_v32n1_7_t0001.png 이미지

Table 2. Term define about TP, FN, FP, TN used for Confusion matrix

BGHHBN_2019_v32n1_7_t0002.png 이미지

Table 3. Summary of the PLS-DA classification result from NIR and MIR spectral data by LOOCV. (a) NIR spectral data from Paper mulberry bast fiber, (b) MIR spectral data from Paper mulberry bast fiber, (c) NIR spectral data from Hanji (d) MIR spectral data from Hanji

BGHHBN_2019_v32n1_7_t0003.png 이미지

Table 4. Confusion matrix of PLS-DA model of the (a) NIR spectral data from Paper mulberry bast fiber, (b) MIR spectral data from Paper mulberry bast fiber, (c) NIR spectral data from Hanji and (d) MIR spectral data from Hanji

BGHHBN_2019_v32n1_7_t0004.png 이미지

Acknowledgement

Supported by : 국립문화재연구소

References

  1. O. H. Kwon and H. C. Kim, J. Korea TAPPI, 43(4), 59-66 (2011).
  2. J. G. Kwon, C. Seo, S. S. Hong, D. W. Seo, J. S. Oh, and J. K. Kim, J. Korean Soc. Food Sci. Nutr., 45(11), 1604-1609 (2016). https://doi.org/10.3746/jkfn.2016.45.11.1604
  3. J. H. Cho, K. J. Kim, S. B. Park, and T. J. Eom, J. Korea TAPPI, 41(3), 42-48 (2009).
  4. H. C. Kim and U. Y. Kim, Fiber Technol. Industry, 13(1), 13-20 (2009).
  5. S. I. Lee, W. H. Chung, W. S. Kwon, J. H. Lim, and S. C. Kim, J. Health Info. Stat., 36(2), 183-192 (2011).
  6. K. J. Kim and T. J. Eom, J. Korea TAPPI, 48(1), 34-42 (2016).
  7. H. Lee, Y. Lee, C. H. Jun, and J. H. Hong, KJAS, 23(2), 295-304 (2010).
  8. I. Santoni, E. Callone, A. Sandak, J. Sandak, and S. Dire, Carbohydr. Polym., 117, 710-721 (2015). https://doi.org/10.1016/j.carbpol.2014.10.057
  9. D. C. Silva, T. C. M. Pastore, L. F. Soares, F. A. S. de Barros, M. C. J. Bergo, V. T. H. Coradin, A. B. Gontijo, M. H. Sosa, C. B. Chacon, and J. W. B. Braga, Holzforschung, 72(7), 521-530 (2018). https://doi.org/10.1515/hf-2017-0160
  10. C. J. Lee, J. W. Ko, and G. B. Lee, Korean Chem. Eng. Res., 48(6), 717-724 (2010).
  11. S. N. Ismail, M. Maulidiani, M. T. Akhtar, F. Abas, I. S. Ismail, A. Khatib, N. A. M. Ali, and K. Shaari, Molecules, 22(10), 1-13 (2017).
  12. J. Y. Leem, Yakhak Hoeji, 60(1), 29-35 (2016). https://doi.org/10.17480/psk.2016.60.1.29
  13. G. Jiang and J. Y. Leem, Korean J. Medicinal Crop. Sci., 24(2), 93-100 (2016). https://doi.org/10.7783/KJMCS.2016.24.2.93
  14. D. Y. Kim, C. Mo, J. S. Kang, and B. K. Cho, J. Korean Soc. Nondestruc. Test., 35(1), 1-11 (2015). https://doi.org/10.7779/JKSNT.2015.35.1.1
  15. M. S. Lee, H. M. Park, B. I. Kim, and T. Y. Heo, J. Korea Industr. Inf. Syst. Res., 17(5), 89-96 (2012). https://doi.org/10.9723/jksiis.2012.17.5.089
  16. Y. D, Kim, C. H. Jun, and H. S. Lee, JKDIS, 22(5), 931-940 (2011).
  17. M. Schwanninger, J. C. Rodrigues, and K. Fackler, J. Near Infrared Spectrosc., 19(5), 287-308 (2011). https://doi.org/10.1255/jnirs.955
  18. S. W. Hwang, W. H. Lee, Y. Horikawa, and J. Sugiyama, J. Korean Wood Sci. Technol., 43(6), 701-713 (2015). https://doi.org/10.5658/WOOD.2015.43.6.701
  19. J. P. McLean, G. Jin, M. Brennan, M. K. Nieuwoudt, and P. J. Harris, Can. J. For. Res., 44(7), 820-830 (2014). https://doi.org/10.1139/cjfr-2013-0329
  20. S. Jiangtao, X. Dong, and L. Jian, Energy Procedia, 16(B), 758-762 (2012). https://doi.org/10.1016/j.egypro.2012.01.122
  21. R. Rana, R. Langenfeld-Heyser, R. Finkeldey, and A. Polle, Wood Sci. Technol., 44(2), 225-242 (2010). https://doi.org/10.1007/s00226-009-0281-2
  22. S. Durmaz, O. Ozgenc, I. H. Boyaci, U. C. Yildiz, and E. Erisir, Vib Spectroscopy, 85, 202-207 (2016). https://doi.org/10.1016/j.vibspec.2016.04.020
  23. M. Traore, J. Kaal, and A. M. Cortizas, Wood Sci. Technol., 52(2), 487-504 (2018). https://doi.org/10.1007/s00226-017-0967-9
  24. R. G. Brereton and G. R. Lloyed, J. Chemometrics, 28(4), 213-225 (2014). https://doi.org/10.1002/cem.2609
  25. J. Trygg, E. Holmes, and T. Lundstedt, J. Proteome Res., 6(2), 469-79 (2007). https://doi.org/10.1021/pr060594q