Analytical and Bioanalytical Chemistry

, Volume 392, Issue 3, pp 515–521 | Cite as

An ensemble method based on a self-organizing map for near-infrared spectral calibration of complex beverage samples

Original Paper


Based on a so-called ensemble strategy, an algorithm is proposed for near-infrared (NIR) spectral calibration of complex beverage samples. This algorithm is a combination of a novel training set/test set sample-selection procedure based on a Kohonen self-organizing map (SOM) with a simple procedure to calculate an average partial least-squares (PLS) calibration model, which is therefore named SOMEPLS. In order to verify the proposed SOMEPLS, two NIR beverage datasets involving the determination of sugar content are considered, and three kinds of reference algorithm, i.e., conventional PLS (CPLS), the Kennard-Stone (KS) algorithm in combination with PLS (KSPLS), and sample set partitioning based on the joint x-y distance (SPXY) algorithm in combination with PLS (SPXYPLS), are used. Of these, both KS and SPXY are well-known representative sample-selection algorithms. By comparison, it was found that when there is a training set of appropriate size, SOMEPLS can achieve better prediction accuracy than the three reference algorithms, but without increasing the complexity of the corresponding calibration model for the future application, indicating that SOMEPLS can serve as a promising tool for NIR spectral calibration.


Near-infrared Calibration Accuracy Ensemble Self-organizing map Sugar concentration 



This work was supported by Scientific Research Fund of Sichuan Provincial Education Department of China


  1. 1.
    Cen HY, He Y (2007) Trends Food Sci Technol 18:72–83CrossRefGoogle Scholar
  2. 2.
    Tan C, Li ML, Qin X (2007) Anal Bioanal Chem 389:667–674CrossRefGoogle Scholar
  3. 3.
    González-Martín I, Hernández-Hierro JM, González-Cabrera JM (2007) Anal Bioanal Chem 387:2199–2205CrossRefGoogle Scholar
  4. 4.
    Roggo Y, Chalus P, Maurer L, Lema-Martinez C, Edmond A, Jent N (2007) J Pharm Biomed Anal 44:683–700CrossRefGoogle Scholar
  5. 5.
    Olesberg JT, Liu LZ, Zee VV, Arnold MA (2006) Anal Chem 78:215–223CrossRefGoogle Scholar
  6. 6.
    Felício CC, Brás LP, Lopes JA, Cabrita L, Menezes JC (2005) Chemom Intell Lab Syst 78:74–80CrossRefGoogle Scholar
  7. 7.
    González-Martín I, Hernández-Hierro JM, Barros-Ferreiro N (2006) Anal Bioanal Chem 386:1553–1558CrossRefGoogle Scholar
  8. 8.
    Cocciardi RA, Ismail AA, Wang Y, Sedman J (2006) J Agric Food Chem 54:6475–6481CrossRefGoogle Scholar
  9. 9.
    Benoudjit N, Francois D, Meurens M, Verleysen M (2004) Chemom Intell Lab Syst 74:243–251CrossRefGoogle Scholar
  10. 10.
    Viscarra Rossel RA (2007) J Near Infrared Spectrosc 15:39–47CrossRefGoogle Scholar
  11. 11.
    Jiang JH, Berry RJ, Siesier HW, Ozaki Y (2002) Anal Chem 74:3555–3565CrossRefGoogle Scholar
  12. 12.
    Leardi R (2000) J Chemometr 14:643–655CrossRefGoogle Scholar
  13. 13.
    Nørgaard L, Saudland A, Wagner J, Nielsen JP, Munck L, Engelsen SB (2000) Appl Spectrosc 54:413–419CrossRefGoogle Scholar
  14. 14.
    Leardi R, Nørgaard L (2004) J Chemometr 18:486–497CrossRefGoogle Scholar
  15. 15.
    Kennard RW, Stone LA (1969) Technometrics 11:137–148CrossRefGoogle Scholar
  16. 16.
    Galváo RKH, Araújo MCU, José GE, Pontes MJC, Silva EC, Saldanha TCB (2005) Talanta 67:736–740CrossRefGoogle Scholar
  17. 17.
    Brown G, Wyatt JL, Tino P (2005) J Mach Learn Res 6:1621–1650Google Scholar
  18. 18.
    Galváo RKH, Araújo MCU, Martins MN, José GE, Pontes MJC, Silva EC, Saldanha TCB (2006) Chemom Intell Lab Syst 81:60–67CrossRefGoogle Scholar
  19. 19.
    Zhang MH, Xu QS, Massart DL (2005) Anal Chem 77:1423–1431CrossRefGoogle Scholar
  20. 20.
    Dumoulin ED, Bernard AP, Guerain JT (1987) J Food Sci 52:626–630CrossRefGoogle Scholar
  21. 21.
    Luinge HJ, van der Maas JH, Visser T (1995) Chemom Intell Lab Syst 28:129–138CrossRefGoogle Scholar
  22. 22.
    Zupan J, Novič M, Ruisanchez I (1997) Chemom Intell Lab Syst 38:1–23CrossRefGoogle Scholar
  23. 23.
    Kiang MY (2001) Comput Stat Data Anal 38:161–180CrossRefGoogle Scholar
  24. 24.
    Breiman L (1996) Mach Learn 24:123–140Google Scholar
  25. 25.
    Benoudjit N, Cools E, Meurens M, Verleysen M (2004) Chemom Intell Lab Syst 70:47–53CrossRefGoogle Scholar
  26. 26.
    Christensen J, Nørgaard L, Heimdal H, Pedersen JG, Engelsen SB (2004) J Near Infrared Spectrosc 12:63–75Google Scholar

Copyright information

© Springer-Verlag 2008

Authors and Affiliations

  1. 1.Department of Chemistry and Chemical EngineeringYibin UniversityYibinChina
  2. 2.College of ChemistrySichuan UniversityChengduChina

Personalised recommendations