Korean Journal of Agricultural Science (농업과학연구)

Institute of Agricultural Science, CNU (충남대학교 농업과학연구소)
권호 표지
DOI QR코드

DOI QR Code

Discriminant analysis of grain flours for rice paper using fluorescence hyperspectral imaging system and chemometric methods

  • Seo, Youngwook (National Institute of Agricultural Sciences, Department of Agricultural Engineering) ;
  • Lee, Ahyeong (National Institute of Agricultural Sciences, Department of Agricultural Engineering) ;
  • Kim, Bal-Geum (National Institute of Agricultural Sciences, Department of Agricultural Engineering) ;
  • Lim, Jongguk (National Institute of Agricultural Sciences, Department of Agricultural Engineering)
  • Received : 2020.04.17
  • Accepted : 2020.08.05
  • Published : 2020.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

Rice paper is an element of Vietnamese cuisine that can be used to wrap vegetables and meat. Rice and starch are the main ingredients of rice paper and their mixing ratio is important for quality control. In a commercial factory, assessment of food safety and quantitative supply is a challenging issue. A rapid and non-destructive monitoring system is therefore necessary in commercial production systems to ensure the food safety of rice and starch flour for the rice paper wrap. In this study, fluorescence hyperspectral imaging technology was applied to classify grain flours. Using the 3D hyper cube of fluorescence hyperspectral imaging (fHSI, 420 - 730 nm), spectral and spatial data and chemometric methods were applied to detect and classify flours. Eight flours (rice: 4, starch: 4) were prepared and hyperspectral images were acquired in a 5 (L) × 5 (W) × 1.5 (H) cm container. Linear discriminant analysis (LDA), partial least square discriminant analysis (PLSDA), support vector machine (SVM), classification and regression tree (CART), and random forest (RF) with a few preprocessing methods (multivariate scatter correction [MSC], 1st and 2nd derivative and moving average) were applied to classify grain flours and the accuracy was compared using a confusion matrix (accuracy and kappa coefficient). LDA with moving average showed the highest accuracy at A = 0.9362 (K = 0.9270). 1D convolutional neural network (CNN) demonstrated a classification result of A = 0.94 and showed improved classification results between mimyeon flour (MF)1 and MF2 of 0.72 and 0.87, respectively. In this study, the potential of non-destructive detection and classification of grain flours using fHSI technology and machine learning methods was demonstrated.

Keywords

References

  1. Baek I, Kim MS, Cho BK, Mo C, Barnaby JY, McClung AM, Oh M. 2019. Selection of optimal hyperspectral wavebands for detection of discolored, diseased rice seeds. Applied Sciences 9:1027-1042. https://doi.org/10.3390/app9051027
  2. Bagchi TB, Sharma S, Chattopadhyay K. 2016. Development of NIRS models to predict protein and amylose content of brown rice and proximate compositions of rice bran. Food Chemistry 191:21-27. https://doi.org/10.1016/j.foodchem.2015.05.038
  3. Bao J, Bergman CJ. 2004. The functionality of rice starch. In: Starch in Food: Structure, Functional and Application. Eliasson AC. (ed). pp. 258-292. CRC Press, Inc., Boca Raton, FL, USA.
  4. Bittner LKH, Heigl N, Petter CH, Noisternig MF, Griesser UJ, Bonn GK, Huck CW. 2011. Near-infrared reflection spectroscopy (NIRS) as a successful tool for simultaneous identification and particle size determination of amoxicillin trihydrate. Journal of Pharmaceutical and Biomedical Analysis 54:1059-1064. https://doi.org/10.1016/j.jpba.2010.12.019
  5. Breiman L. 2001. Random forests. Machine Learning 45:5-32. https://doi.org/10.1023/A:1010933404324
  6. Chen X, Kopsaftopoulos F, Wu Q, Ren H, Chang FK. 2019. A self-adaptive 1D convolutional neural network for flightstate identification. Sensors 19:275. https://doi.org/10.3390/s19020275
  7. Delwiche SR, Bean MM, Miller RE, Webb BD, Williams PC. 1995. Apparent amylose content of milled rice by nearinfrared reflectance spectrophotometry. Cereal Chemistry 72:182-187.
  8. Goetz AFH. 2009. Three decades of hyperspectral remote sensing of the Earth: A personal view. Remote Sensing of Environment 113:S5-S16. https://doi.org/10.1016/j.rse.2007.12.014
  9. Gromski PS, Xu Y, Correa E, Ellis DI, Turner ML, Goodacre R. 2014. A comparative investigation of modern feature selection and classification approaches for the analysis of mass spectrometry data. Analytica Chimica Acta 829:1-8. https://doi.org/10.1016/j.aca.2014.03.039
  10. Kim AJ, Kim MW, Woo NRY. 2007. Processing of convenient rice gruels with sericultures. The Korean Journal of Food and Nutrition 20:179-184. [in Korean]
  11. Kim JH, Chun SS, 2017. Quality characteristics of porridge containing rice incubated with Phellinus linteus mycelium. The Korean Journal of Food and Nutrition 30:560-567. [in Korean] https://doi.org/10.9799/ksfan.2017.30.3.560
  12. Kim JM, Min BK, Choi CH. 1997. Emerging technology & information processing: Determination of rice milling ratio by visible/near-infrared spectroscopy. Journal of Biocystems Engineering 22:333-342. [in Korean]
  13. Kim MS, Chen R, Mehl PM. 2001. Hyperspectral reflectance and fluorescence images system for food quality and safety. Transactions of the ASAE 44:721.
  14. Kim TM, Noh SH. 2010. On-line inspection algorithm of brown rice using image processing. Journal of Biocystems Engineering 35:138-145. [in Korean] https://doi.org/10.5307/JBE.2010.35.2.138
  15. Kim WS, Shin M. 2007. The properties of rice flours prepared by dry- and wet-milling of soaked glutinous and normal grains. Korean Journal of Food and Cookery Science 26:727-736. [in Korean]
  16. Lee YK, Lee JH. 1999. Measurement of milling ratio using the visible and the near-infrared rays spectrum. Journal of Biocystems Engineering 24:259-266. [in Korean]
  17. Lin L, He Y, Xiao Z, Zhao K, Dong T, Nie P. 2019. Rapid-detection sensor for rice grain moisture based on NIR spectroscopy. Applied Sciences 9:1654. https://doi.org/10.3390/app9081654
  18. Liu M, Zhang X, Yang B, Li Z, Deng F, Yang Y, Zhang X, Wei Y. 2015. Fluorescent nanoparticles from starch: Facile preparation, tunable luminescence and bioimaging. Carbohydrate Polymers 121:49-55. https://doi.org/10.1016/j.carbpol.2014.12.047
  19. Ma L, Peng Y, Pei Y, Zeng J, Shen H, Cao J, Qiao Y, Wu Z. 2019. Systematic discovery about NIR spectral assignment from chemical structural property to natural chemical compounds. Scientific Reports 9:9503-9503. https://doi.org/10.1038/s41598-019-45945-y
  20. Merzlyak MN, Chivkunova OB. 2000. Light-stress-induced pigment changes and evidence for anthocyanin photoprotection in apples. Journal of Photochemistry and Photobiology B: Biology 55:155-163. https://doi.org/10.1016/S1011-1344(00)00042-7
  21. Mo C, Lim J, Kwon SW, Lim DK, Kim M. 2017. Hyperspectral imaging and partial least square discriminant analysis for geographical origin discrimination of white rice. Journal of Biosystems Engineering 42:293-300. https://doi.org/10.5307/JBE.2017.42.4.293
  22. Noh SH, Hwang CS, Lee JW. 1997. Algorithm for discrimination of brown rice kernels using machine vision. Journal of Biosystems Engineering 22:295-302. [in Korean]
  23. Park BH, Koh KM, Jeon ER. 2020. Quality characteristics of semi-dry noodles prepared with various dry rice flours. Family and Environment Research 58:121-130. [in Korean] https://doi.org/10.6115/fer.2020.009
  24. Rahman A, Park E, Bae H, Cho B. 2019. Hyperspectral imaging technique to evaluate the firmness and the sweetness index of tomatoes. Korean Journal of Agricultural Science 45:823-837. https://doi.org/10.7744/kjoas.20180075
  25. Sampaio PS, Soares A, Castanho A, Almeida AS, Oliveira J, Brites C. 2018. Optimization of rice amylose determination by NIR-spectroscopy using PLS chemometrics algorithms. Food Chemistry 242:196-204. https://doi.org/10.1016/j.foodchem.2017.09.058
  26. Siedliska A, Baranowski P, Zubik M, Mazurek W, Sosnowska B. 2018. Detection of fungal infections in strawberry fruit by VNIR/SWIR hyperspectral imaging. Postharvest Biology and Technology 139:115-126. https://doi.org/10.1016/j.postharvbio.2018.01.018
  27. Sohn M, Barton II FE, McClung AM, Champagne ET. 2004. Near-infrared spectroscopy for determination of protein and amylose in rice flour through use of derivatives. Cereal Chemistry 81:341-344. https://doi.org/10.1094/CCHEM.2004.81.3.341
  28. Weng S, Tang P, Yuan H, Guo B, Yu S, Huang L, Xu C. 2020. Hyperspectral imaging for accurate determination of rice variety using a deep learning network with multi-feature fusion. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 234:118237. https://doi.org/10.1016/j.saa.2020.118237
  29. Wold S, Esbensen K, Geladi P. 1987. Principal component analysis. Chemometrics and Intelligent Laboratory Systems 2:37-52. https://doi.org/10.1016/0169-7439(87)80084-9
  30. Xia J, Ghamisi P, Yokoya N, Iwasaki A. 2018. Random forest ensembles and extended multiextinction profiles for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing 56:202-216. https://doi.org/10.1109/TGRS.2017.2744662
  31. Yang H, Kuang B, Mouazen AM. 2011. Affect of different preprocessing methods on principal component analysis for soil classification. In 2011 Third International Conference on Measuring Technology and Mechatronics Automation 1:355-358. https://doi.org/10.1109/ICMTMA.2011.90
  32. Yoon MR, Oh SK, Kim DJ, Kim CK, Choi IS, Lee JS, Lee JH. 2012. Varietal variation of gelatinization and cooking properties in rice having different amylose contents. The Korean Journal of Food and Nutrition 25:762-769. [in Korean] https://doi.org/10.9799/ksfan.2012.25.4.762