Food Analytical Methods

, Volume 11, Issue 5, pp 1405–1416 | Cite as

A Novel Strategy of Clustering Informative Variables for Quantitative Analysis of Potential Toxics Element in Tegillarca Granosa Using Laser-Induced Breakdown Spectroscopy

  • Lei-ming Yuan
  • Xiaojing Chen
  • Yongjie Lai
  • Xi Chen
  • Yijian Shi
  • Dehua Zhu
  • Limin Li


Laser-induced breakdown spectroscopy (LIBS) exhibits excellent ability for rapid analysis of potential toxics elements. In this study, LIBS was employed to measure the Cu concentration in contaminated Tegillarca granosa. A framework was carefully developed for sample’s preparation and LIBS acquisition. Univariate models based on Cu characteristic spectral lines were validated, but with unsatisfactory performance. Wavelengths’ loadings and weightings of partial least square (PLS) model exhibited the most uninformative background, while they were selected by the supervised general variable selection methods that showed success in near-infrared spectroscopy. Thus, a strategy for clustering variables by their similar characteristics was proposed to screen the informative wavelengths using the unsupervised Kohonen self-organizing map (SOM). The PLS and least square support vector machine (LSSVM) models were calibrated based on these clustered units using the optimized parameters for the SOM network. LSSVM model exhibited the best performance based on the C3 × 3(2,2) variables with correlation coefficient of prediction of 0.906, as well as root mean squared error of prediction of 19.62 mg kg−1. SOM could more effectively cluster wavelengths from the complex LIBS spectrum than general variable selections, which have been proven their success in near-infrared spectra but fail in the LIBS spectra. Results indicated LIBS coupled with SOM-LSSVM calibration method could be used to quantitatively evaluate the potential toxics element Cu concentration in shellfish Tegillarca granosa. This study can be a good reference for screening the informative variables and measurement of other constituents in LIBS spectra.

Graphical Abstract


Laser-induced breakdown spectroscopy (LIBS) Heavy metal Tegillarca granosa SOM network Variable selection 



This study was funded by National Natural Science Foundation of China (NO.61705168, NO.31571920), Wenzhou science and technology bureau general project (NO.S20170003), and the Science and technology project of Zhejiang Province (NO.2015F50057).

Compliance with Ethical Standards

Conflict of Interest

Leiming Yuan declares that he has no conflict of interest. Xiaojing Chen declares that he has no conflict of interest. Yongjie Lai declares that he has no conflict of interest. Xi Chen declares that he has no conflict of interest. Yijian Shi declares that he has no conflict of interest. Dehua Zhu declares that he has no conflict of interest. Limin Li declares that he has no conflict of interest. This paper does not contain any studies with human or animal subjects.

Ethical Approval

This article does not contain any studies with human participants performed by any of the authors.

Informed Consent

Informed consent was obtained from all individual participants included in the study.

Supplementary material

12161_2017_1096_MOESM1_ESM.docx (373 kb)
ESM 1 (DOCX 372 kb).


  1. Araújo MCU, Saldanha TCB, Galvão RKH, Yoneyama T, Chame HC, Visani V (2001) The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemometr Intell Lab 57(2):65–73. CrossRefGoogle Scholar
  2. Aragón C, Aguilera JA (2008) Characterization of laser induced plasmas by optical emission spectroscopy: a review of experiments and methods. Spectrochimica Acta Part B Atomic Spectroscopy 63(9):893–916. CrossRefGoogle Scholar
  3. Balabin RM, Smirnov SV (2012) Interpolation and extrapolation problems of multivariate regression in analytical chemistry: benchmarking the robustness on near-infrared (NIR) spectroscopy data. Analyst 137:1604–1610. CrossRefGoogle Scholar
  4. Bao Y, Yang T, Wang S, Wang C, You Z, Jiao H, Lin Z (2013) Hemoglobin and its derived peptides from blood clam (Tegillarca granosa) exhibiting an antimicrobial activity. Fish Shellfish Immunology 34(6):1696–1701. CrossRefGoogle Scholar
  5. Baveye PC, Laba M (2015) Visible and near-infrared reflectance spectroscopy is of limited practical use to monitor soil contamination by heavy metals. J Hazard Mater 285:137–139CrossRefGoogle Scholar
  6. Brode WR (1958) Chemical spectroscopy. Wiley, New YorkGoogle Scholar
  7. Centner V, Massart D-L, de Noord OE, de Jong S, Vandeginste BM, Sterna C (1996) Elimination of uninformative variables for multivariate calibration. Anal Chem 68:3851–3858. CrossRefGoogle Scholar
  8. Chen X, Liu K, Cai J, Zhu D, Chen H (2015) Identification of heavy metal-contaminated Tegillarca granosa using infrared spectroscopy. Anal Methods 7:2172–2181CrossRefGoogle Scholar
  9. Chen X, Wu D, Guan X, Liu B, Liu G, Yan M, Chen H (2013) Feasibility of infrared and Raman spectroscopies for identification of juvenile black seabream (Sparus macrocephalus) intoxicated by heavy metals. J Agricultural Food Chemistry 61(50):12429–12435. CrossRefGoogle Scholar
  10. Dong JL, Guo WC, Wang ZW, Liu DY, Zhao F (2016) Nondestructive determination of soluble solids content of ‘Fuji’ apples produced in different areas and bagged with different materials during ripening. Food Anal Methods 9(5):1087–1095. CrossRefGoogle Scholar
  11. Farrokhnia M, Karimi S (2016) Variable selection in multivariate calibration based on clustering of variable concept Anal Chim Acta 902Google Scholar
  12. Garcimuño M, Pace DMD, Bertuccelli G (2013) Laser-induced breakdown spectroscopy for quantitative analysis of copper in algae. Opt Laser Technol 47:26–30. CrossRefGoogle Scholar
  13. Ghaseminezhad MH, Karami A (2011) A novel self-organizing map (SOM) neural network for discrete groups of data clustering. Appl Soft Comput 11:3771–3778CrossRefGoogle Scholar
  14. Haddad JE, Canioni L, Bousquet B (2014) Good practices in LIBS analysis: review and advices. Spectrochimica Acta Part B Atomic Spectroscopy 101:171–182. CrossRefGoogle Scholar
  15. Lazic V, Jovićević S (2014) Laser induced breakdown spectroscopy inside liquids: processes and analytical aspects. Spectrochimica Acta Part B Atomic Spectroscopy 101:288–311. CrossRefGoogle Scholar
  16. Leardi R, Boggia R, Terrile M (1992) Genetic algorithms as a strategy for feature selection. J Chemom 6:267–281CrossRefGoogle Scholar
  17. Li H, Liang Y, Xu Q, Cao D (2009) Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. Anal Chim Acta 648:77–84CrossRefGoogle Scholar
  18. Mangiameli P, Chen SK, West D (1996) A comparison of SOM neural network and hierarchical clustering methods. Eur J Oper Res 93:402–417CrossRefGoogle Scholar
  19. Mehmood T, Liland KH, Snipen L, Sæbø S (2012) A review of variable selection methods in partial least squares regression. Chemometr Intell Lab 118:62–69. CrossRefGoogle Scholar
  20. Mohamed WTY (2008) Improved LIBS limit of detection of Be, Mg, Si, Mn, Fe and Cu in aluminum alloy samples using a portable Echelle spectrometer with ICCD camera. Opt Laser Technol 40:30–38. CrossRefGoogle Scholar
  21. Naser HA (2013) Assessment and management of heavy metal pollution in the marine environment of the Arabian Gulf: a review. Mar Pollut Bull 72:6–13CrossRefGoogle Scholar
  22. National Institute of Standards and Technology Electronic database
  23. Olumegbon IA, Oloyede A, Afara IO (2016) Near-infrared (NIR) spectroscopic evaluation of articular cartilage: a review of current and future trends. Appl Spectrosc Rev 52(6):1–19. Google Scholar
  24. Pathak AK, Kumar R, Singh VK, Agrawal R, Rai S, Rai AK (2012) Assessment of LIBS for Spectrochemical analysis: a review. Appl Spectrosc Rev 47:14–40. CrossRefGoogle Scholar
  25. Pořízka P, Demidov A, Kaiser J, Keivanian J, Gornushkin I, Panne U, Riedel J (2014) Laser-induced breakdown spectroscopy for in situ qualitative and quantitative analysis of mineral ores. Spectrochimica Acta Part B Atomic Spectroscopy 101:155–163. CrossRefGoogle Scholar
  26. Rakovský J, Čermák P, Musset O, Veis P (2014) A review of the development of portable laser induced breakdown spectroscopy and its applications. Spectrochimica Acta Part B Atomic Spectroscopy 101:269–287. CrossRefGoogle Scholar
  27. Rezk RA, Galmed AH, Abdelkreem M, Ghany NAA, Harith MA (2016) Quantitative analysis of Cu and Co adsorbed on fish bones via laser-induced breakdown spectroscopy. Opt Laser Technol 83:131–139CrossRefGoogle Scholar
  28. Shi RJ, Pan XZ, Wang CK, Liu Y, Li YL, Li ZT (2015) Prediction of cadmium content in the leaves of navel orange in heavy metal contaminated soil using VIS-NIR reflectance spectroscopy. Guang Pu Xue Yu Guang Pu Fen Xi 35:3140–3145Google Scholar
  29. Sirven JB, Mauchien P, Sallé B (2008) Analytical optimization of some parameters of a laser-induced breakdown spectroscopy experiment. Spectrochim Acta B At Spectrosc 63(10):1077–1084. CrossRefGoogle Scholar
  30. Suykens JAK, Gestel TV, Brabanter JD, Moor BD, Vandewalle J (2002) Least Squares Support Vector Machines. World Scientific Pub. Co., SingaporeGoogle Scholar
  31. Wu D, Chen X, Cao F, Sun D-W, He Y, Jiang Y (2014) Comparison of infrared spectroscopy and nuclear magnetic resonance techniques in tandem with multivariable selection for rapid determination of ω-3 polyunsaturated fatty acids in fish oil. Food Bioprocess Tech 7(6):1555–1569. CrossRefGoogle Scholar
  32. Wu D, Chen XJ, Zhu XG, Guan XC, GC W (2011) Uninformative variable elimination for improvement of successive projections algorithm on spectral multivariable selection with different calibration algorithms for the rapid and non-destructive determination of protein content in dried laver. Anal Methods 3(8):1790–1796. CrossRefGoogle Scholar
  33. Wu D, He Y (2014) Potential of spectroscopic techniques and chemometric analysis for rapid measurement of docosahexaenoic acid and eicosapentaenoic acid in algal oil. Food Chem 158:93–100. CrossRefGoogle Scholar
  34. Xiaobo Z, Jiewen Z, Povey MJW, Holmes M, Hanpin M (2010) Variables selection methods in near-infrared spectroscopy. Anal Chim Acta 667:14–32. CrossRefGoogle Scholar
  35. Yi C, Lv Y, Xiao H et al (2017) Laser induced breakdown spectroscopy quantitative analysis based on low-rank matrix approximation[J]. J Anal At Spectrom 32:2164–2172.
  36. Yuan L-M, Sun L, Lin H, Han E, Liu H-L, Cai J-R (2013) Simplification of NIR model for citrus’s sugar content based on sensory methods. Spectrosc Spect Anal 33:2387–2391. Google Scholar
  37. Yuan L-M, Cai J, Sun L, Han E, Ernest T (2016) Nondestructive measurement of soluble solids content in apples by a portable fruit analyzer. Food Anal Methods 9(3):785–794.
  38. Zhu D, Wu L, Wang B, Chen J, Lu J, Ni X (2011) Determination of Ca and Mg in aqueous solution by laser-induced breakdown spectroscopy using absorbent paper substrates. Appl Opt 50(29):5695–5699CrossRefGoogle Scholar
  39. Zhu N, Lin M, Nie Y, Wu D, Chen K (2016) Study on the quantitative measurement of firmness distribution maps at the pixel level inside peach pulp 130Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2017

Authors and Affiliations

  1. 1.College of Physics and Electronic Information EngineeringWenzhou UniversityWenzhouChina
  2. 2.College of Mechanical & Electrical EngineeringWenzhou UniversityWenzhouChina

Personalised recommendations