Medicine Discrimination of NIRS Based on Regularized Collaborative Representation Classification with Gabor Optimizer

  • Zhenbing LiuEmail author
  • Huanhuan Ji
  • Shujie Jiang
Part of the Studies in Computational Intelligence book series (SCI, volume 810)


Counterfeit medicine still exists widely, which have affected our health and life. So the discrimination (classification) of medicine is becoming more and more important. Then near-infrared spectroscopy (NIRS) is a popular and effective technique used on the medicine classification with nondestructive characteristics. To solve the discrimination of medicines, the sparse signal representation model is established in the presence of spectrum crossover and overlapping. However, the sparsity of nonzero representation coefficients is low during solving the \( L_{ 2} \)-norm on representation model. To overcome this problem, in this paper a novel classification model—regularized collaborative representation classification with Gabor optimizer (RCRCG) is proposed. Gabor filter is adopted to control the \( L_{2} \)-norm for the more relevant factor vectors. Then Lasso regulation on local classification is proved to improve the accuracy on the medicine discrimination. The experiments using NIRS samples from the three datasets (active substance, Erythromycin Ethylsuccinate and Domperidone) show that the proposed method is more effective and robust than the existing ones, and it has speed-up about 1 times compared with the Sparse Representation based Classification (SRC) and Class \( L_{1} \)-optimizer classifier with the closeness rule (C_CL1C).


Medicines discrimination Near-infrared spectroscopy (NIRS) Collaborative representation classification Gabor filter Sparsity representation 



This work was supported by the National Natural Science Foundation of China (Grant No. 61562013), Natural Science Foundation of Guangxi Province (CN) (2017GXNSFDA198025), and Guangxi Key Lab of Trusted Software (kx201730). We thank Xi’an-Janssen Pharmaceutical Factory for useful datasets of Near Infrared spectra samples. We would like to express our appreciation to all supporters above mentioned for their strongly financial support.


  1. 1.
    Lu, H.Y., Wang, S.S., Cai, R., et al.: Rapid discrimination and quantification of alkaloids in Corydalis Tuber by near-infrared spectroscopy. J. Pharm. Biomed. Anal. 59, 44–49 (2012)CrossRefGoogle Scholar
  2. 2.
    Li, X., Yong, H., Hui, F.: Non-destructive discrimination of Chinese bayberry varieties using Vis/NIRS spectroscopy. J. Food Eng. 81(2), 357–363 (2007)CrossRefGoogle Scholar
  3. 3.
    Qu, J.H., Liu, D., Cheng, J.H., et al.: Applications of near-infrared spectroscopy in food safety evaluation and control: a review of recent research advances. Crit. Rev. Food Sci. Nutr. 55(13), 1939–1954 (2015)CrossRefGoogle Scholar
  4. 4.
    Reilly, A.O., Coffey, R., Gowen, A., et al.: Evaluation of near-infrared chemical imaging for the prediction of surface water quality parameters. Int. J. Environ. Anal. Chem. 95(5), 403–418 (2015)CrossRefGoogle Scholar
  5. 5.
    Shao, X., Cui, X., Liu, Y., et al.: Understanding the molecular interaction in solutions by chemometric resolution of near-infrared spectra. Chem. Select. 2(31), 10027–10032 (2017)Google Scholar
  6. 6.
    Xu, Z., Liu, Y., Li, X., et al.: Discriminant analysis of Chinese patent medicines based on near-infrared spectroscopy and principal component discriminant transformation. Spectrochim. Acta Part A Mol. Biomol. Spectrosc. 149, 985–990 (2015)CrossRefGoogle Scholar
  7. 7.
    Haughey, S.A., Graham, S.F., Cancouët, E., et al.: The application of Near-Infrared Reflectance Spectroscopy (NIRS) to detect melamine adulteration of soya bean meal. J. Food Chem. 136, 1557–1561 (2013)CrossRefGoogle Scholar
  8. 8.
    Sacré, P.Y., Deconinck, E., Beer, T.D., et al.: Comparison and combination of spectroscopic techniques for the detection of counterfeit medicines. J. Pharm. Biomed. Anal. 53, 445–453 (2010)CrossRefGoogle Scholar
  9. 9.
    Luo, W., Huan, S., Fu, H., et al.: Preliminary study on the application of near infrared spectroscopy and pattern recognition methods to classify different types of apple samples. J. Food Chem. 128, 555–561 (2011)CrossRefGoogle Scholar
  10. 10.
    Lyndgaard, L.B., Berg, F.V.D., Juan, A.D.: Quantification of paracetamol through tablet blister packages by Raman spectroscopy and multivariate curve resolution-alternating least squares. J. Chemom. Intell. Lab. Syst. 125, 58–66 (2013)CrossRefGoogle Scholar
  11. 11.
    Storme-Paris, I., Rebiere, H., Matoga, M., et al.: Challenging near infrared spectroscopy discriminating ability for counterfeit pharmaceuticals detection. J. Analytica chimica acta 658, 163–174 (2010)CrossRefGoogle Scholar
  12. 12.
    Yang, J., Zhang, L., Xu, Y., et al.: Beyond sparsity: The role of L1-optimizer in pattern classification. J. Pattern Recogn. 45, 1104–1118 (2012)CrossRefGoogle Scholar
  13. 13.
    Zhang, L., Yang, M.: Sparse representation or collaborative representation: which helps face recognition? In: IEEE International Conference on Computer Vision, pp. 471–478. IEEE (2012)Google Scholar
  14. 14.
    Wright, J., Yang, A.Y., Ganesh, A., et al.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31, 210–227 (2009)CrossRefGoogle Scholar
  15. 15.
    Yang, M., Zhang, L., Shiu, S.C.K., et al.: Gabor feature based robust representation and classification for face recognition with Gabor occlusion dictionary. J. Pattern Recogn. 46, 1865–1878 (2013)CrossRefGoogle Scholar
  16. 16.
    Lu, H., Li, Y., Chen, M., et al.: Brain intelligence: go beyond artificial intelligence. Mob. Netw. Appl. 23(2), 368–375 (2018)CrossRefGoogle Scholar
  17. 17.
    Rakotomamonjy, A., Flamary, R., Yger, F.: Learning with Infinitely Many Features. Kluwer Academic Publishers (2013)Google Scholar
  18. 18.
    Zhang, W., Shan, S., Gao, W., et al.: Local gabor binary pattern histogram sequence (LGBPHS): a novel non-statistical model for face representation and recognition. In: International Conference on Computer Vision, vol. 1, pp. 786–791 (2005)Google Scholar
  19. 19.
    Dyrby, M., Engelsen, S.B., Nørgaard, L., et al.: Chemometric quantitation of the active substance (containing C≡N) in a pharmaceutical tablet using Near-Infrared (NIRS) transmittance and NIRS FT-Raman Spectra. J. Appl. Spectrosc. 56, 579–585 (2002)CrossRefGoogle Scholar
  20. 20.
    Zhang, Z., Jung, T.P., Makeig, S., et al.: Compressed sensing for energy-efficient wireless telemonitoring of noninvasive fetal ECG via block sparse Bayesian learning. IEEE Trans Biomed Eng. 60, 300–309 (2013)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Guangxi Key Lab of Trusted SoftwareGuilin University of Electronic TechnologyGuilinChina
  2. 2.School of Electronic Engineering and AutomationGuilin University of Electronic TechnologyGuilinChina

Personalised recommendations