Spectral Preprocessing and Machine Learning Modeling for Discriminating Manufacturing Origins of Mulberry Bast Fiber

Yong Ju Lee; Soon Wan Kweon; Jae Hyeop Kim; Ji Eun Cha; Kwang-Ho Kang; Hyoung Jin Kim

doi:10.7584/JKTAPPI.2023.10.55.5.61

All Issue

2023 Vol.55, Issue 5 Preview Page Next Page

Research Article

Spectral Preprocessing and Machine Learning Modeling for Discriminating Manufacturing Origins of Mulberry Bast Fiber 닥나무 인피섬유의 제조 지역 식별을 위한 적외선 스펙트럼 데이터 전처리 및 기계학습 모델링

30 October 2023. pp. 61-74

PDF XML

Abstract

The objective of this study was exploring the impact of spectral data preprocessing techniques on the performance of machine learning models for classifying the origin of mulberry bast fibers. The findings indicated that a selective spectral region (1800-1200 cm^-1) significantly improves classification model performance. Among the classifiers tested, Partial Least Squares Discriminant Analysis (PLS-DA) and Support Vector Machines (SVM) demonstrated the highest accuracy. Additionally, A spectral preprocessing with the Norris-Williams algorithm effectively improved model performance within the same classifier for this dataset. These results suggest that applying machine learning modeling with spectral preprocessing can enable the origin classification of mulberry bast fibers and provide a chemical basis for classification rules beyond simple categorization.

Keywords

Spectral pre-processing

Savitzky-golay

Norris-Williams

PLS-DA

SVM

KNN

machine learning

classification

infrared spectroscopy

Hanji

mulberry

References

Park, J. Y., Park, C. Y., Jeong, H. S., Lee, J. H., and Kim, H. J., Manufacture of conservational machine-made Hanji based on domestic paper mulberry fibers, Journal of Korea TAPPI 48(6):277-285 (2016). 10.7584/JKTAPPI.2016.12.48.6.277

Kang, K. H., and Kim, H. J., Studies on the reinforcement treatment of aged Hanji using cellulose derivative solutions, Journal of Korea TAPPI 43(2):40-48 (2011).

Kwon, O.H., and Kim, H.C., Preliminary study on automation of bark peeling process for paper mulberry, Journal of Korea TAPPI 43(4):59-66 (2011).

Hyun, K. S., Kim, M. J., and Lee, M. K., Printability improvement of Hanji, Journal of Korea TAPPI 37(4):52-59 (2005).

Jang, K. J., Jung, S. Y., Go, I. H., and Jeong, S. H., Discrimination model for cultivation origin of paper mulberry bast fiber and Hanji based on NIR and MIR spectral data combined with PLS-DA, Analytical Science and Technology 32(1):7-16 (2019).

Kim, K. J., and Eom, T. J., Classification of papers using IR and NIR spectra and principal component analysis, Journal of Korea TAPPI 48(1):34-42 (2016). 10.7584/ktappi.2016.48.1.034

Alexopoulos, E. C., Introduction to multivariate regression analysis, Hippokratia 14(1):23 (2010). 10.1201/b10289-6

Yun, Y. H., Li, H. D., Deng, B. C., and Cao, D. S., An overview of variable selection methods in multivariate analysis of near-infrared spectra, Trends in Analytical Chemistry 113:102-115 (2019). 10.1016/j.trac.2019.01.018

Jang, K. J., Heo, T. Y., and Jeong, S. H., Classification option for Korean traditional paper based on type of raw materials, using near-infrared spectroscopy and multivariate statistical methods, BioResources 15(4):9045-9058 (2020). 10.15376/biores.15.4.9045-9058

Hwang, S. W., Park, G. Y., Kim, J. H., and Jeong, M. J., Predictive modeling of traditional korean paper characteristics using machine learning approaches (part 1): discriminating manufacturing origins with artificial neural networks and infrared spectroscopy, Journal of Korea TAPPI 55(4):57-69 (2023). 10.7584/JKTAPPI.2023.8.55.4.57

Brown, S., Tauler, R., and Walczak, B. (Eds.), Comprehensive chemometrics: chemical and biochemical data analysis, Elsevier (2020).

Lee, L. C., Liong, C. Y., and Jemain, A. A., A contemporary review on Data Preprocessing (DP) practice strategy in ATR-FTIR spectrum, Chemometrics and Intelligent Laboratory Systems 163:64-75 (2017). 10.1016/j.chemolab.2017.02.008

Rinnan, Å., Van Den Berg, F., and Engelsen, S. B., Review of the most common pre-processing techniques for near-infrared spectra, TrAC Trends in Analytical Chemistry, 28(10):1201-1222 (2009). 10.1016/j.trac.2009.07.007

Savitzky, A. and Golay, M. J. E., Smoothing and differentiation of data by simplified least squares procedures, Analytical Chemistry 36(8):1627-1639 (1964). 10.1021/ac60214a047

Norris, K., and Williams, P., Optimization of mathematical treatments of raw near-infrared signal in the, Cereal Chem 61(2):158-165 (1984).

Rinnan, Å., Van Den Berg, F., and Engelsen, S. B., Review of the most common pre-processing techniques for near-infrared spectra, Trends in Analytical Chemistry 28(10):1201-1222 (2009). 10.1016/j.trac.2009.07.007

Indahl, U. G., Martens, H., and Næs, T., From dummy regression to prior probabilities in PLS-DA, Journal of Chemometrics: A Journal of the Chemometrics Society 21(12): 529-536 (2007). 10.1002/cem.1061

Samanta, B. I. S. W. A. J. I. T., Al-Balushi, K. R., and Al-Araimi, S. A., Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection, Engineering applications of artificial intelligence 16(7-8):657-665 (2003). 10.1016/j.engappai.2003.09.006

Vert, J. P., Tsuda, K., and Schölkopf, B., A primer on kernel methods, Kernel Methods in Computational Biology 47:35-70 (2004).

Tsuchikawa, S., Yamato, K., and Inoue, K. Discriminant analysis of wood-based materials using near-infrared spectroscopy, Journal of Wood Science 49:275-280 (2003). 10.1007/s10086-002-0471-0

Guo, G., Wang, H., Bell, D., Bi, Y., and Greer, K., KNN model-based approach in classification, In On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE: OTM Confederated International Conferences, CoopIS, DOA, and ODBASE 2003, Catania, Sicily, Italy, November 3-7, Proceedings pp. 986-996, Springer Berlin Heidelberg (2003). 10.1007/978-3-540-39964-3_62

Piras, P., Sheridan, R., Sherer, E. C., Schafer, W., Welch, C. J., and Roussel, C., Modeling and predicting chiral stationary phase enantioselectivity: An efficient random forest classifier using an optimally balanced training dataset and an aggregation strategy, Journal of separation science 41(6):1365-1375 (2018). 10.1002/jssc.20170133429383846

Kim, J. W., Park, S. R., Han, K. O., and Jeong, S. H., Study on the evaluation of thermal damage according to the manufacturing conditions of korean paper, Journal of Conservation Science 37(6):648-658 (2021). 10.12654/JCS.2021.37.6.04

Maréchal, Y., and Chanzy, H., The hydrogen bond network in Iβ cellulose as observed by infrared spectrometry, Journal of Molecular Structure 523(1-3):183-196 (2000). 10.1016/S0022-2860(99)00389-0

Horikawa, Y., Hirano, S., Mihashi, A., Kobayashi, Y., Zhai, S. and Sugiyama, J., Pre- diction of lignin contents from infrared spectroscopy: chemical digestion and lignin/biomass ratios of cryptomeria japonica, Applied Biochemistry and Biotechnology 188:1066-1076 (2019). 10.1007/s12010-019-02965-830783948

Široky, J., Blackburn, R. S., Bechtold, T., Taylor, J. and White, P., Attenuated total reflectance Fourier-transform Infrared spectroscopy analysis of crystallinity changes in lyocell following continuous treatment with sodium hydroxide, Cellulose 17:103-115 (2010). 10.1007/s10570-009-9378-x

Fahey, L. M., Nieuwoudt, M. K. and Harris, P. J., Predicting the cell-wall compositions of Pinus radiata (radiata pine) wood using ATR and transmission FTIR spectroscopies, Cellulose 24:5275-5293 (2017). 10.1007/s10570-017-1506-4

Kim, K. J., and Eom, T. J., Study on the aging characteristics of paper with principal component analysis, Journal of Korea TAPPI 48(6):144-149 (2016). 10.7584/JKTAPPI.2016.12.48.6.144

Lee, Y. J., Cha, J. E., Kang, N. Y., Kim, J. H., and Kim, H. J., Application of spectroscopy to analyze the degree of substitution of carboxymethyl cellulose, Journal of Korea TAPPI 55(1):103-111 (2023). 10.7584/JKTAPPI.2023.2.55.1.103

Delmotte, L., Ganne-Chedeville, C., Leban, J. M., Pizzi, A., and Pichelin, F., CP-MAS 13C NMR and FT-IR investigation of the degradation reactions of polymer constituents in wood welding, Polymer Degradation and Stability 93(2):406-412 (2008). 10.1016/j.polymdegradstab.2007.11.020

Lee, Y. J., A Study on the quality characterization of printing and writing paper using surface parameters and data mining techniques, Master thesis, Kookmin University, Korea (2022).

Information

Publisher :Korea Technical Association of The Pulp and Paper Industry
Publisher(Ko) :한국펄프종이공학회
Journal Title :Journal of Korea TAPPI
Journal Title(Ko) :펄프종이기술
Volume : 55
No :5
Pages :61-74
Received Date : 2023-09-20
Revised Date : 2023-10-22
Accepted Date : 2023-10-24
DOI :https://doi.org/10.7584/JKTAPPI.2023.10.55.5.61

Journal of Korea TAPPI ISSN:0253-3200(Print) 펄프종이기술

All Issue