DOI QR코드

DOI QR Code

The Effect of Representative Dataset Selection on Prediction of Chemical Composition for Corn kernel by Near-Infrared Reflectance Spectroscopy

예측알고리즘 적용을 위한 데이터세트 구성이 근적외선 분광광도계를 이용한 옥수수 품질평가에 미치는 영향

  • 최성원 (코리아스펙트랄프로덕츠(주)) ;
  • 이창석 (코리아스펙트랄프로덕츠(주)) ;
  • 박창희 (코리아스펙트랄프로덕츠(주)) ;
  • 김동희 (코리아스펙트랄프로덕츠(주)) ;
  • 박성권 (농촌진흥청 국립축산과학원) ;
  • 김법균 (건국대학교 동물자원학과) ;
  • 문상호 (건국대학교 식품생명과학부)
  • Received : 2014.06.30
  • Accepted : 2014.09.25
  • Published : 2014.09.30

Abstract

The objectives were to assess the use of near-infrared reflectance spectroscopy (NIRS) as a tool for estimating nutrient compositions of corn kernel, and to apply an NIRS-based indium gallium arsenide array detector to the system for collecting spectra and analyzing calibration equations using equipments designed for field application. Partial Least Squares Regression (PLSR) was employed to develop calibration equations based on representative data sets. The kennard-stone algorithm was applied to induce a calibration set and a validation set. As a result, the method for structuring a calibration set significantly affected prediction accuracy. The prediction of chemical composition of corn kernel resulted in the following (kennard-stone algorithm: relative) moisture ($R^2=0.82$, RMSEP=0.183), crude protein ($R^2=0.80$, RMSEP=0.142), crude fat ($R^2=0.84$, RMSEP=0.098), crude fiber ($R^2=0.74$, RMSEP=0.098), and crude ash ($R^2=0.81$, RMSEP=0.048). Result of this experiment showed the potential of NIRS to predict the chemical composition of corn kernel.

Keywords

References

  1. AOAC. 2005. Official methods of analysis (16th ed.), Association of Official Analytical Chemist, Arlington, VA. Washington D.C., USA.
  2. Chin, W.W. 1998. The Partial Least Squares Approach to Structural Equation Modeling. Modern Methods for Business Research. NJ: Lawrence Erlbaum Associates. Mahwah. pp. 295-336.
  3. De Groot, P.J., Postma, G.J., Melssen, W.J. and Buydens, L.M.C. 1999. Selecting a representative training set for the classification of demolition waste using remote NIR sensing. Analytical chimica acta. 392:67-75. https://doi.org/10.1016/S0003-2670(99)00193-2
  4. Lee, H.W., Kim, J.D., Kim, W.H. and Lee, J.K. 2009. Prediction on the quality of forage crop by near infrared reflectance spectroscopy. Journal of The Korean Society of Grassland Science. 29(1):31-36. https://doi.org/10.5333/KGFS.2009.29.1.031
  5. Martens, H. and Naes, T. 1990. Multivariate calibration. Journal of Chemometrics. 4(6):441. https://doi.org/10.1002/cem.1180040607
  6. Norris, K.H., Barnes, R.E.F., Moore, J.E. and Shenk, J.S. 1976. Predicting forages quality by infrared reflectance spectroscopy. Journal of Animal Science. 43:889-897.
  7. Park, H.S., Lee, J.K. and Lee, H.W. 2004. Applications of Near Infrared Reflectance Spectroscopy (NIRS) in Forage Evaluation. Journal of The Korean Society of Grassland Science. 24(1):81-90. https://doi.org/10.5333/KGFS.2004.24.1.081
  8. Park, H.S., Lee, J.K., Lee, H.W., Hwang, K.J., Jung, H.Y. and Ko, M.S. 2006. Effect of sample preparations on prediction of chemical composition for corn silage by near infrared reflectance spectroscopy. Journal of The Korean Society of Grassland Science. 26(1):53-62. https://doi.org/10.5333/KGFS.2006.26.1.053
  9. Paul Gemperline. 2006. Practical Guide To Chemometrics, Second Edition. Taylor&Francis Group. London. pp. 168-211.
  10. Varmuza, K. and Filzmoser, P. 2009. Introduction to Mutivariate Statistical Analysis in Chemometrics. Taylor & Francis Group. USA. pp. 103-190.