Advertisement

Quantization of Adulteration Ratio of Raw Cow Milk by Least Squares Support Vector Machines (LS-SVM) and Visible/Near Infrared Spectroscopy

  • Ching-Lu Hsieh
  • Chao-Yung Hung
  • Ching-Yun Kuo
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 363)

Abstract

Raw cow milk has short supply market in summer and over supply in winter, which causes consumers and dairy industry concern about the quality of raw milk whether is adulated with reconstituted milk (powdered milk). This study prepared 307 raw cow milk samples with various adulteration ratios 0%, 2%, 5%, 10%, 20%, 30%, 50%, 75%, and 100% of powdered milk. Least square support vector machine (LS-SVM) was applied to calibrate the prediction model for adulteration ratio. Grid search approach was used to find the better value of network parameters of γ and σ 2. Results show that R2 ranges from 0.9662 to 0.9777 for testing data set with plate surface and four concave regions. Scatter plot of testing data showed that adulteration ratio above 10% clearly differs from 0% samples.

Keywords

LS-SVM Raw milk Cow milk Adulteration detection NIR 

References

  1. 1.
    COA, Agricultural Statistics Yearbook. Council of Agriculture, Executive Yuan, Taipei, Taiwan, p. 126 (2009) (in Chinese) Google Scholar
  2. 2.
  3. 3.
    Hu, Y.W.: Analysis of consumer’s behavior for cow milk and goat milk in Taiwan. Grains and Livestock 241, 18–27 (1993) (in Chinese)Google Scholar
  4. 4.
    Ding, H.C., Chang, T.C.: Detection of reconstituted milk in fresh milk. Journal of the Chinese Agricultural Chemical Society 23(4), 406–411 (1986) (in Chinese) Google Scholar
  5. 5.
    Harding, F.: Adulteration of milk. In: Harding, F. (ed.) Milk Quality, ch. 5, pp. 60–74. Chapman & Hall, Wiltshire (1995a)CrossRefGoogle Scholar
  6. 6.
    Borin, A., Ferrao, M., Mello, C., Maretto, D., Poppi, R.: Least-squares support vector machines and near infrared spectroscopy for quantification of common adulterants in powdered milk. Analytica Chimica Acta 579, 25–32 (2006)CrossRefGoogle Scholar
  7. 7.
    Lin, C.W., Chen, S.H., Su, H.P., Ju, C.C.: Detection of reconstituted milk in raw milk through determination of milk Dnase activity. Journal of the Chinese Agricultural Chemical Society 25(3), 332–340 (1987) (in Chinese)Google Scholar
  8. 8.
    Berg, J.: Diary Technology in the Tropics and Subtropics, Pudoc Wageningen, the Netherlands, pp. 223–242, 1–45 (1988)Google Scholar
  9. 9.
    Harding, F.: Composition quality. In: Harding, F. (ed.) Milk Quality, ch. 6, pp. 75–96. Chapman & Hall, Wiltshire (1995b)CrossRefGoogle Scholar
  10. 10.
    AOAC official methods of analysis. 972.16 Fat, lactose, protein, and solids in milk. Mid-infrared spectroscopic method. Association of Official Analytical Chemists, Arlington, VA, pp. 816–818 (1990) Google Scholar
  11. 11.
    Norris, K.H.: Making Light Work: Advances in Near Infrared Spectroscopy. In: Murray, I., Cowe, I.A. (eds.), pp. 596–602. VCH Press, New York (1991)Google Scholar
  12. 12.
    Schmilovitch, Z., Maltz, E., Austerweill, M.: Fresh raw milk composition analysis by NIR spectroscopy. In: Ipema, A.H., Lippus, A.C., Metz, J.H.M., Rossing, W. (eds.) Proceedings of the International Symposium on Prospects for Automatic Milking, Wageningen, Netherlands, EAAP Publication No.65 (1992)Google Scholar
  13. 13.
    Chen, J.Y., Iyo, C., Terada, F., Kawano, S.: Effect of multiplicative scatter correction on wavelength selection for near infrared calibration to determine fat content in raw milk. Journal of Near Infrared Spectroscopy 10(4), 301–307 (2002)CrossRefGoogle Scholar
  14. 14.
    Kawasaki, M., Kawamura, S., Tsukahara, M., Morita, S., Komiya, M., Natsuga, M.: Near-infrared spectroscopic sensing system for on-line milk quality assessment in a milking robot. Computers and Electronics in Agriculture 63, 22–27 (2008)CrossRefGoogle Scholar
  15. 15.
    Suykens, J.A.K., Vandewalle, J.: Least squares support vector machine classifiers. Neural Processing Letters 9, 293–300 (1999)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Yu, H.Y., Niu, X.Y., Lin, H.J., Ying, Y.B., Li, B.B., Pan, X.X.: A feasibility study on on-line determination of rice wine composition by Vis–NIR spectroscopy and least-squares support vector machines. Food Chemistry 113, 291–296 (2009)CrossRefGoogle Scholar
  17. 17.
    Siuly, Y., Wen, P.: Clustering technique-based least square support vector machine for EEG signal classification. Computer Methods and Programs in Biomedicine (2010), doi:10.1016/j.cmpb.2010.11.014Google Scholar
  18. 18.
    Zuao, X., Wang, G., Zhao, K., Tan, D.: On-line least squares support vector machine algorithm in gas prediction. Mining Science and Technology 19, 194–198 (2009)Google Scholar
  19. 19.
    Wu, D., He, Y., Feng, S., Sun, D.W.: Study on infrared spectroscopy technique for fast measurement of protein content in milk powder based on LS-SVM. Journal of Food Engineering 84, 124–131 (2008)CrossRefGoogle Scholar
  20. 20.

Copyright information

© International Federation for Information Processing 2011

Authors and Affiliations

  • Ching-Lu Hsieh
    • 1
  • Chao-Yung Hung
    • 1
  • Ching-Yun Kuo
    • 2
  1. 1.Department of Biomechatronics EngineeringNational Pingtung University of Science and TechnologyTaiwan, R.O.C.
  2. 2.Animal Research Institute, Council of Agriculture, Executive YuanTaiwan, R.O.C.

Personalised recommendations