Rapid spectral analysis of agro-products using an optimal strategy: dynamic backward interval PLS–competitive adaptive reweighted sampling

A Correction to this article is available

This article has been updated

Abstract

A novel strategy of variable selection approach named dynamic backward interval partial least squares–competitive adaptive reweighted sampling (DBiPLS-CARS) was proposed in this study. Near-infrared data sets of three different agro-products, namely corn, crop processing lamina, and plant leaf samples, were collected to investigate the performance of the proposed method. Weak relevant variables were first removed by DBiPLS and a refined selection of the remaining variables was then conducted by CARS. The Monte Carlo uninformative variable elimination (MCUVE) was used as a classical beforehand uninformative variable elimination method for comparison. Results showed that DBiPLS can select informative variables more continuously than MCUVE. Some synergistic variables which may be omitted by MCUVE can be retained by DBiPLS. By contrast, MCUVE can hardly avoid the disturbance of certain weak relevant variables as a result of its calculation based on the full spectrum regression. Therefore, DBiPLS exhibited the advantage of removing the weak relevant variables before CARS, and simultaneously improved the prediction performance of CARS.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Change history

  • 01 October 2020

    The authors would like to call the reader���s attention to the fact that, unfortunately, there was a mistake regarding the affiliations of three of the authors in this manuscript; please find the correct information below

References

  1. 1.

    Li H, Liang Y, Xu Q, Cao D. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. Anal Chim Acta. 2009;648:77–84.

    CAS  Article  Google Scholar 

  2. 2.

    Sarcan ET, Gunay MS, Ozer AY. Theranostic polymeric nanoparticles for NIR imaging and photodynamic therapy. Biosyst Eng. 2018;175:124–32.

    Article  Google Scholar 

  3. 3.

    Barbedo JG, Guarienti EM, Tibola CS. Detection of sprout damage in wheat kernels using NIR hyperspectral imaging. Talanta. 2018;116:266–76.

    Google Scholar 

  4. 4.

    He HJ, Sun DW, Wu D. Rapid and real-time prediction of lactic acid bacteria (LAB) in farmed salmon flesh using near-infrared (NIR) hyperspectral imaging combined with chemometric analysis. Food Res Int. 2014;62:476–83.

    CAS  Article  Google Scholar 

  5. 5.

    Agyekum AA, Kutsanedzie FY, Mintah BK, Annavaram V, Zareef M, Hassan MM, et al. Rapid and nondestructive quantification of trimethylamine by FT-NIR coupled with chemometric techniques. Food Anal Methods. 2019. https://doi.org/10.1007/s12161-019-01537-0.

  6. 6.

    Wei X, Xu N, Wu D, He Y. Determination of branched-amino acid content in fermented Cordyceps sinensis mycelium by using FT-NIR spectroscopy technique. Food Bioprocess Tech. 2014;7:184–90.

    CAS  Article  Google Scholar 

  7. 7.

    Xu F, Huang X, Dai H, Chen W, Ding R, Teye E. Nondestructive determination of bamboo shoots lignification using FT-NIR with efficient variables selection algorithms. Anal Methods. 2014;6:1090–5.

    CAS  Article  Google Scholar 

  8. 8.

    Ncama K, Tesfay SZ, Fawole OA, Opara UL, Magwaza LS. Non-destructive prediction of ‘marsh’ grapefruit susceptibility to postharvest rind pitting disorder using reflectance Vis/NIR spectroscopy. Sci Hortic. 2018;231:265–71.

    Article  Google Scholar 

  9. 9.

    Kucheryavskiy S, Lomborg CJ. Monitoring of whey quality with NIR spectroscopy-a feasibility study. Food Chem. 2015;176:271–7.

    CAS  Article  Google Scholar 

  10. 10.

    Xie C, Xu N, Shao Y, He Y. Using FT-NIR spectroscopy technique to determine arginine content in fermented Cordyceps sinensis mycelium. Spectrochim Acta. 2015;149:971–7.

    CAS  Article  Google Scholar 

  11. 11.

    Deng BC, Yun YH, Liang YZ, Yi LZ. A novel variable selection approach that iteratively optimizes variable space using weighted binary matrix sampling. Analyst. 2014;139:4836–45.

    CAS  Article  Google Scholar 

  12. 12.

    Weitz S, Blanco S, Charon J, Dauchet J, Hafi ME, Eymet V, et al. Monte Carlo efficiency improvement by multiple sampling of conditioned integration variables. J Comput Phys. 2016;326:30–4.

    Article  Google Scholar 

  13. 13.

    Wang W, Yun Y, Deng B, Fan W, Liang Y. Iteratively variable subset optimization for multivariate calibration. RSC Adv. 2015;5:95771–80.

    CAS  Article  Google Scholar 

  14. 14.

    Yun YH, Wang WT, Deng BC, Lai GB, Liu XB, Ren DB, et al. Using variable combination population analysis for variable selection in multivariate calibration. Anal Chim Acta. 2015;862:14–23.

    CAS  Article  Google Scholar 

  15. 15.

    Deng BC, Yun YH, Ma P, Lin CC, Ren DB, Liang YZ. A new method for wavelength interval selection that intelligently optimizes the locations, widths and combinations of the intervals. Analyst. 2015;140:1876–85.

    CAS  Article  Google Scholar 

  16. 16.

    Lin Z, Pan X, Xu B, Zhang J, Shi X, Qiao Y. Evaluating the reliability of spectral variables selected by subsampling methods. J Chemom. 2015;29:87–95.

    CAS  Article  Google Scholar 

  17. 17.

    Zheng KY, Li QQ, Wang JJ, Geng JP, Cao P, Sui T, et al. Stability competitive adaptive reweighted sampling (SCARS) and its applications to multivariate calibration of NIR spectra. Chemometr Intel Lab Syst. 2012;112:48–54.

    CAS  Article  Google Scholar 

  18. 18.

    Centner V, Massart DL, Noord OE, Jong S, Vandeginste BM, Sterna C. Elimination of uninformative variables for multivariate calibration. Anal Chem. 1996;68:3851–8.

    CAS  Article  Google Scholar 

  19. 19.

    Cai W, Li Y, Shao X. A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra. Chemometr Intel Lab Syst. 2008;90:188–94.

    CAS  Article  Google Scholar 

  20. 20.

    Andries JP, Heyden YV, Buydens LM. Improved variable reduction in partial least squares modelling by global-minimum error uninformative-variable elimination. Anal Chim Acta. 2017;982:37–47.

    CAS  Article  Google Scholar 

  21. 21.

    Tang G, Huang Y, Tian KD, Song XZ, Yan H, Hu J, et al. A new spectral variable selection pattern using competitive adaptive reweighted sampling combined with successive projections algorithm. Analyst. 2014;139:4894–902.

    CAS  Article  Google Scholar 

  22. 22.

    Ye SF, Wang D, Min SG. Successive projections algorithm combined with uninformative variable elimination for spectral variable selection. Chemometr Intel Lab Syst. 2008;91:194–9.

    CAS  Article  Google Scholar 

  23. 23.

    Amjad W, Crichton SO, Munir A, Hensel O, Sturm B. Hyperspectral imaging for the determination of potato slice moisture content and chromaticity during the convective hot air drying process. Biosyst Eng. 2018;166:170–83.

    Article  Google Scholar 

  24. 24.

    Leardi R, Norgaard L. Sequential application of backward interval partial least squares and genetic algorithms for the selection of relevant spectral regions. J Chemom. 2004;18:486–97.

    CAS  Article  Google Scholar 

  25. 25.

    Hosseini M, Agereh SR, Khaledian Y, Zoghalchali HJ, Naeini SA, Brevik EC. Comparison of multiple statistical techniques to predict soil phosphorus. Appl Soil Ecol. 2017;114:123–31.

    Article  Google Scholar 

  26. 26.

    Gomes AA, Galvão RK, Araújo MC, Veras G, Da Silva EC. The successive projections algorithm for interval selection in PLS. Microchem J. 2013;110:202–8.

    CAS  Article  Google Scholar 

  27. 27.

    Norgaard L, Saudland A, Wagner J, Nielsen JP, Munck L. Interval partial least-squares regression (iPLS): a comparative chemometric study with an example from near-infrared spectroscopy. Appl Spectrosc. 2000;54:413–9.

    CAS  Article  Google Scholar 

  28. 28.

    Goicoechea HC, Olivieri AC. A new family of genetic algorithms for wavelength interval selection in multivariate analytical spectroscopy. J Chemom. 2003;17:338–45.

    CAS  Article  Google Scholar 

  29. 29.

    Krepper G, Romeo F, Fernandes DD, Diniz PH, Araujo MC, Nezio MS, et al. Determination of fat content in chicken hamburgers using NIR spectroscopy and the successive projections algorithm for interval selection in PLS regression (iSPA-PLS). Spectrochim Acta A. 2018;189:300–6.

    CAS  Article  Google Scholar 

  30. 30.

    Ouyang Q, Zhao J, Chen Q. Measurement of non-sugar solids content in Chinese rice wine using near infrared spectroscopy combined with an efficient characteristic variables selection algorithm. Spectrochim Acta. 2015;151:280–5.

    CAS  Article  Google Scholar 

  31. 31.

    Arakawa M, Yamashita Y, Funatsu K. Genetic algorithm-based wavelength selection method for spectral calibration. J Chemom. 2011;25:10–9.

    CAS  Article  Google Scholar 

  32. 32.

    Mariani NC, Teixeira GH, Lima KM, Morgenstern TB, Nardini V, Junior LC. NIRS and iSPA-PLS for predicting total anthocyanin content in Jaboticaba fruit. Food Chem. 2015;174:643–8.

    CAS  Article  Google Scholar 

  33. 33.

    Song XZ, Huang Y, Tian KD, Min SG. Near infrared spectral variable optimization by final complexity adapted models combined with uninformative variables elimination-a validation study. Optik. 2020;203:164019. https://doi.org/10.1016/j.ijleo.2019.164019.

    CAS  Article  Google Scholar 

  34. 34.

    Official Methods of Analysis, 17th ed., AOAC International, Arlington, VA, 2000.

  35. 35.

    Kennard RW, Stone LA. Computer aided design of experiments. Technometrics. 1969;11:137–48.

    Article  Google Scholar 

  36. 36.

    Workman J, Weyer L. Practical guide to interpretive near-infrared spectroscopy. Boca Raton: CRC. 2007.

  37. 37.

    Moros J, Kuligowski J, Quintás G, Garrigues S, Guardia M. New cut-off criterion for uninformative variable elimination in multivariate calibration of near-infrared spectra for the determination of heroin in illicit street drugs. Anal Chim Acta. 2008;630:150–60.

    CAS  Article  Google Scholar 

  38. 38.

    Fu GH, Xu QS, Li HD, Cao DS, Liang YZ. Elastic net grouping variable selection combined with partial least squares regression (EN-PLSR) for the analysis of strongly multi-collinear spectroscopic data. App Spectrosc. 2011;65:402–8.

    CAS  Article  Google Scholar 

Download references

Acknowledgements

This research is financially supported by National Natural Science Foundation of China (Grant No.31301685), and Fundamental Research Funds for the Central Universities of China (No. 3142017100).

Author information

Affiliations

Authors

Corresponding author

Correspondence to Yue Huang.

Ethics declarations

Conflict of interest

The authors have declared no conflicts of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Song, X., Du, G., Li, Q. et al. Rapid spectral analysis of agro-products using an optimal strategy: dynamic backward interval PLS–competitive adaptive reweighted sampling. Anal Bioanal Chem 412, 2795–2804 (2020). https://doi.org/10.1007/s00216-020-02506-x

Download citation

Keywords

  • Variable selection
  • Dynamic backward interval partial least squares (DBiPLS)
  • Competitive adaptive reweighted sampling (CARS)
  • Monte Carlo uninformative variable elimination (MCUVE)
  • Agro-products