Korean Journal of Remote Sensing (대한원격탐사학회지)

Korean Society of Remote Sensing (대한원격탐사학회)
권호 표지
DOI QR코드

DOI QR Code

Study of Prediction Model Improvement for Apple Soluble Solids Content Using a Ground-based Hyperspectral Scanner

지상용 초분광 스캐너를 활용한 사과의 당도예측 모델의 성능향상을 위한 연구

  • Song, Ahram (Department of Civil Environmental Engineering, Seoul National University) ;
  • Jeon, Woohyun (Department of Civil Environmental Engineering, Seoul National University) ;
  • Kim, Yongil (Department of Civil Environmental Engineering, Seoul National University)
  • 송아람 (서울대학교 건설환경공학부) ;
  • 전우현 (서울대학교 건설환경공학부) ;
  • 김용일 (서울대학교 건설환경공학부)
  • Received : 2017.08.14
  • Accepted : 2017.09.27
  • Published : 2017.10.30
Download PDF
⟨ Previous Next ⟩

Abstract

A partial least squares regression (PLSR) model was developed to map the internal soluble solids content (SSC) of apples using a ground-based hyperspectral scanner that could simultaneously acquire outdoor data and capture images of large quantities of apples. We evaluated the applicability of various preprocessing techniques to construct an optimal prediction model and calculated the optimal band through a variable importance in projection (VIP)score. From the 515 bands of hyperspectral images extracted at wavelengths of 360-1019 nm, 70 reflectance spectra of apples were extracted, and the SSC ($^{\circ}Brix$) was measured using a digital photometer. The optimal prediction model wasselected considering the root-mean-square error of cross-validation (RMSECV), root-mean-square error of prediction (RMSEP) and coefficient of determination of prediction $r_p^2$. As a result, multiplicative scatter correction (MSC)-based preprocessing methods were better than others. For example, when a combination of MSC and standard normal variate (SNV) was used, RMSECV and RMSEP were the lowest at 0.8551 and 0.8561 and $r_c^2$ and $r_p^2$ were the highest at 0.8533 and 0.6546; wavelength ranges of 360-380, 546-690, 760, 915, 931-939, 942, 953, 971, 978, 981, 988, and 992-1019 nm were most influential for SSC determination. The PLSR model with the spectral value of the corresponding region confirmed that the RMSEP decreased to 0.6841 and $r_p^2$ increased to 0.7795 as compared to the values of the entire wavelength band. In this study, we confirmed the feasibility of using a hyperspectral scanner image obtained from outdoors for the SSC measurement of apples. These results indicate that the application of field data and sensors could possibly expand in the future.

본 연구에서는 야외에서 자료 취득이 가능하며 한 번에 다량의 사과를 촬영할 수 있는 지상용 초분광 스캐너를 활용하여 사과의 분광정보와 당도와의 부분최소제곱회귀분석(PLSR, Partial Least Square Regression)을 수행하였으며, 최적의 예측모델을 구축하기 위한 다양한 전처리기법의 적용가능성을 평가하고 VIP(Variable Importance in Projection)점수를 통한 최적밴드를 산출하였다. 이를 위하여 360-1019 nm영역에서 촬영된 515밴드의 초분광 영상에서 70개의 분광곡선을 취득하였으며, 디지털광도계를 이용하여 당도($^{\circ}Brix$)를 측정하였다. 사과의 분광특성과 당도사이의 회귀모델을 구축하였으며, 최적의 예측모델은 모델 예측치와 실측치간의 결정계수($r_p^2$, coefficient of determination of prediction)와 RMSECV(Root Mean Square Error of Cross Validation), RMSEP(Root Mean Square Error of Prediction)등을 고려하여 선정하였다. 그 결과 산란보정 기법의 대표적인 MSC(Multiplicative Scatter Correction)의 기반의 전처리기법이 가장 효과적이었으며, MSC와 SNV(Standard Normal Variate)를 조합한 경우 RMSECV와 RMSEP가 각각 0.8551과 0.8561로 가장 낮았고, $r_c^2$와 $r_p^2$은 각각 0.8533과 0.6546으로 가장 높았다, 또한 360-380, 546-690, 760, 915, 931-939, 942, 953, 971, 978, 981, 988, 992-1019 nm 등이 당도 측정을 위한 가장 영향력 있는 파장영역으로 나타났다. 해당 영역의 분광값을 가지고 PLSR을 수행한 결과, 전파장대를 사용할 때보다 RMSEP가 0.6841로 감소하고 $r_p^2$는 0.7795로 증가하는 것을 확인하였다. 본 연구를 통하여 사과의 당도측정에 있어 야외에서 취득한 초분광 영상자료의 활용 가능성을 확인하였으며, 이는 필드자료 및 센서 활용분야의 확장가능성을 보여준다.

Keywords

References

  1. Afanador, N., T. Tran, and L. Buydens, 2013. Use of the bootstrap and permutation methods for a more robust variable importance in the projection metric for partial least squares regression, Analytica chimica acta, 768: 49-56. https://doi.org/10.1016/j.aca.2013.01.004
  2. Bae, H., Y. Seo, D. Kim, S. Lohumi, E. Park, and B. Cho, 2016. Development of non-destructive sorting technique for viability of watermelon seed by using hyperspectral image processing, Journal of the Korean Society for Nondestructive Testing, 36(1): 35-44. https://doi.org/10.7779/JKSNT.2016.36.1.35
  3. Chong, I. and C. Jun, 2005. Performance of some variable selection methods when multicollinearity is present, Chemometrics and Intelligent Laboratory Systems, 78(1): 103-112. https://doi.org/10.1016/j.chemolab.2004.12.011
  4. Dong, J. and W. Guo, 2015. Nondestructive determination of apple internal qualities using near-infrared hyperspectral reflectance imaging, Food Analytical Methods, 8(10): 2635-2646. https://doi.org/10.1007/s12161-015-0169-8
  5. Fan, S., B. Zhang, J. Li, C. Liu, W. Huang, and X. Tian, 2016. Prediction of soluble solids content of apple using the combination of spectra and textural features of hyperspectral reflectance imaging data, Postharvest Biology and Technology, 121: 51-61. https://doi.org/10.1016/j.postharvbio.2016.07.007
  6. Gomez, C., P. Lagacherie, and G. Coulouma, 2008. Continuum removal versus PLSR method for clay and calcium carbonate content estimation from laboratory and airborne hyperspectral measurements, Geoderma, 148(2): 141-148. https://doi.org/10.1016/j.geoderma.2008.09.016
  7. Guo, W., Y. Du, Y. Zhou, S. Yang, J. Lu, Y. Zhao, and L. Teng, 2012. At-line monitoring of key parameters of nisin fermentation by near infrared spectroscopy, chemometric modeling and model improvement, World Journal of Microbiology and Biotechnology, 28(3): 993-1002. https://doi.org/10.1007/s11274-011-0897-x
  8. Karpouzli, E. and T. Malthus, 2003. The empirical line method for the atmospheric correction of IKONOS imagery, International Journal of Remote Sensing, 24(5): 1143-1150. https://doi.org/10.1080/0143116021000026779
  9. Kim, D., B. Cho, and Y. Kim, 2012. Non-destructive quality prediction of truss tomatoes using hyperspectral reflectance imagery, Journal of Agriculutral Science, 39(3): 413-420.
  10. Liu, D., X. Zeng, and D. Sun, 2015. Recent developments and applications of hyperspectral imaging for quality evaluation of agricultural products: a review, Critical reviews in food science and nutrition, 55(12): 1744-1757. https://doi.org/10.1080/10408398.2013.777020
  11. Mendoza, F., R. Lu, D. Ariana, H. Cen, and B. Bailey, 2011. Integrated spectral and image analysis of hyperspectral scattering data for prediction of apple fruit firmness and soluble solids content, Postharvest Biology and Technology, 62(2): 149-160. https://doi.org/10.1016/j.postharvbio.2011.05.009
  12. Mo, C., M. Kim, G. Kim, J. Lim, S. Delwiche, K. Chao, H. Lee, and B. Cho, 2017. Spatial assessment of soluble solid contents on apple slices using hyperspectral imaging, Biosystems Engineering, 159: 10-21. https://doi.org/10.1016/j.biosystemseng.2017.03.015
  13. Noh, S. and D. Ryu, 2002. Preprocessing of Transmitted Spectrum Data for Development of a Robust Non-destructive Sugar Prediction Model of Intact Fruits, Journal of the Korean Society for Nondestructive Testing, 22(4): 361-368.
  14. Noh, H. and R. Lu, 2007. Hyperspectral laser-induced fluorescence imaging for assessing apple fruit quality, Postharvest Biology and Technology, 43(2): 193-201. https://doi.org/10.1016/j.postharvbio.2006.09.006
  15. Peng, Y. and R. Lu, 2008, Analysis of spatially resolved hyperspectral scattering images for assessing apple fruit firmness and soluble solids content, Postharvest Biology and Technology, 48(1): 52-62. https://doi.org/10.1016/j.postharvbio.2007.09.019
  16. Pu, Y., Y. Feng, and D. Sun, 2015. Recent progress of hyperspectral imaging on quality and safety inspection of fruits and vegetables: a review, Comprehensive Reviews in Food Science and Food Safety, 14(2): 176-188. https://doi.org/10.1111/1541-4337.12123
  17. Qin, J., R. Lu, and Y. Peng, 2009. Prediction of apple internal quality using spectral absorption and scattering properties, Transactions of the ASABE, 52(2): 499-486. https://doi.org/10.13031/2013.26807
  18. Rinnan, A., L. Norgaard, F. van den Berg, J. Thygesen, R. Bro, and S. Engelsen, 2009. Data preprocessing. Infrared spectroscopy for food quality analysis and control, 29-50.
  19. Saeys, W., A. Mouazen, and H. Ramon, 2005. Potential for onsite and online analysis of pig manure using visible and near infrared reflectance spectroscopy, Biosystems Engineering, 91(4): 393-402 https://doi.org/10.1016/j.biosystemseng.2005.05.001
  20. Stellacci, A., A. Castrignano, A. Troccoli, B. Basso, and G. Buttafuoco, 2016. Selecting optimal hyperspectral bands to discriminate nitrogen status in durum wheat: a comparison of statistical approaches. Environmental Monitoring and Assessment, 188(3): 199. https://doi.org/10.1007/s10661-016-5171-0
  21. Wang, Z, Q. He, and J. Wang, 2014. Comparison of different variable selection methods for partial least squares soft sensor development, Proc. of 2014 IEEE In American Control Conference (ACC), OR, USA, June. 4-6, pp. 3116-3121.
  22. Xu, L., Y. Zhou, L. Tang, H. Wu, J. Jiang, G. Shen, and R. Yu, 2008. Ensemble preprocessing of near-infrared (NIR) spectra for multivariate calibration, Analytica Chimica Acta, 616(2): 138-143. https://doi.org/10.1016/j.aca.2008.04.031
  23. Zhao, J., S. Vittayapadung, Q. Chen, S. Chaitep, and R. Chuaviroj, 2009. Nondestructive measurement of sugar content of apple using hyperspectral imaging technique, Maejo International Journal of Science and Technology, 3(1): 130-142.
  24. Zhang, C., F. Liu, W. Kong, and Y. He, 2015. Application of visible and near-infrared hyperspectral imaging to determine soluble protein content in oilseed rape leaves, Sensors, 15(7): 16576-16588. https://doi.org/10.3390/s150716576
  25. Zhu, Q., M. Huang, X. Zhao, and S. Wang, 2013. Wavelength selection of hyperspectral scattering image using new semi-supervised affinity propagation for prediction of firmness and soluble solid content in apples, Food Analytical Methods, 6(1): 334-342. https://doi.org/10.1007/s12161-012-9442-2