A Novel Approach to Pattern Recognition Based on PCA-ANN in Spectroscopy

  • Xiaoli Li
  • Yong He
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4093)


Pattern recognition problems that involve functional predictors has developed, specifically for spectral data. The classification of three peach varieties based on near infrared spectra was researched in the practical context. Principal component analysis (PCA) and artificial neural networks (ANN) were used for pattern recognition in this research. PCA is a very effective data mining way; it is applied to enhance species features and reduce data dimensionality. ANN with back propagation algorithm was used for the data compression tasks as well as class discrimination tasks. The first 9 principal components computed by PCA were applied as inputs to a back propagation neural network with one hidden layer. This model was used to predict the varieties of 15 unknown samples. The recognition rate of the model for the unknown sample was 100%. So this paper could offer an effective pattern recognition way.


Artificial Neural Network Linear Discriminant Analysis Back Propagation Neural Network Near Infrared Spectroscopy Back Propagation Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Esteban, D.I., Gonzalez-Saiz, J.M., Pizarro, C.: An Evaluation of Orthogonal Signal Correction Methods for the Characterisation of Arabica and Robusta Coffee Varieties by NIRS. Analytica. Chimica. Acta. 514, 57–67 (2004)CrossRefGoogle Scholar
  2. 2.
    Lopez, M.: Authentication and Classification of Strawberry Varieties by Near Infrared Spectral Analysis of Their Leaves. In: Cho, R.K., Davies, A.M.C. (eds.) Near Infrared Spectroscopy: Proceedings of the 10th International Conference, pp. 335–338. NIR Publications, Chichester, UK (2002)Google Scholar
  3. 3.
    Seregely, Z., Deak, T., Bisztray, G.D.: Distinguishing Melon Genotypes Using NIR Spectroscopy. Chemometrics and Intelligent Laboratory Systems 72, 195–203 (2004)CrossRefGoogle Scholar
  4. 4.
    Turza, S., Toth, A., Varadi, M.: Multivariate Classification of Different Soybean Varieties. In: Davies, A.M.C. (ed.) Journal of Near Infrared Spectroscopy: Proceedings of the 8th International Conference, pp. 183–187. NIR Publications, Chichester, UK (1998)Google Scholar
  5. 5.
    He, Y., Li, X.L., Shao, Y.N.: Discrimination of Varieties of Apple Using Near Infrared Spectral by Principal Component Analysis and BP model. Spectroscopy and Spectral Analysis. 5 (2006)Google Scholar
  6. 6.
    Osborne, B.G., Fearn, T., Hindle, P.H.: Practical NIR Spectroscopy. Longman, Harlow (1993)Google Scholar
  7. 7.
    Krzanowski, W.J., Jonathan, P., McCarthy, W.V., Thomas, M.R.: Discriminant Analysis with Singular Covariance Matrices: Methods and Applications to Spectroscopic Data. Applied Statistics 44, 105–115 (1995)CrossRefGoogle Scholar
  8. 8.
    Wu, B., Abbott, T., Fishman, D., McCurray, W., Mor, G., Stone, K., Ward, D., Williams, K., Zhao, H.: Comparison of Statistical Methods for Classification of Ovarian Cancer Using Mass Spectrometry Data. Bioinformatics 19, 1636–1643 (2003)CrossRefGoogle Scholar
  9. 9.
    Qu, Y., Adam, B.L., Thornquist, M., Potter, J.D., Thompson, M.L., Yasui, Y., Davis, J., Schellhammer, P.F., Cazares, L., Clements, M.A., Wright Jr., G.L., Feng, Z.: Data Reduction Using a Discrete Wavelet Transform in Discriminant Analysis of Very High Dimensionality Data. Biometrics 59, 143–151 (2003)CrossRefMATHMathSciNetGoogle Scholar
  10. 10.
    Vannucci, M., Sha, N.J., Brown, J.P.: NIR and Mass Spectra Classification: Bayesian Methods for Wavelet-based Feature Selection. Chemometrics and Intelligent Laboratory System 77, 139–148 (2005)CrossRefGoogle Scholar
  11. 11.
    Pereira, A.G., Gomez, A.H., He, Y.: Advances in Measurement and Application of Physical Properties of Agricultural Products. Transactions of the CSAE 19(5), 7–11 (2003)Google Scholar
  12. 12.
    Qi, X.M., Zhang, L.D., Du, X.L.: Quantitative Analysis Using NIR by Building PLS-BP Model. Spectroscopy and Spectral Analysis 23(5), 870–872 (2003)Google Scholar
  13. 13.
    He, Y., Feng, S.J., Deng, X.F., Li, X.L.: Study on Lossless Discrimination of Varieties of Yogurt Using the Visible/NIR-spectroscopy. Food Research International 39(6) (2006)Google Scholar
  14. 14.
    Dai, S.X., Xie, C.J., Chen, D.: Principal Component Analysis on Aroma Constituents of Seven High-aroma Pattern Oolong Teas. Journal of South China Agriculture University 20(1), 113–117 (1999)Google Scholar
  15. 15.
    Zhao, C., Qu, H.B., Cheng, Y.Y.: A New Approach to the Fast Measurement of Content of Amino Acids in Cordyceps Sinensis by ANN-NIR. Spectroscopy and Spectral Analysis 24(1), 50–53 (2004)Google Scholar
  16. 16.
    Galvao, L.S., Formaggio, A.R., Tisot, D.A.: Discrimination of Sugarcane Varieties in Southeastern Brazil with EO-1 Hyperion Data. Remote Sensing of Environment 94, 523–534 (2005)CrossRefGoogle Scholar
  17. 17.
    Utku, H.: Application of the Feature Selection Method to Discriminate Digitized Wheat Varieties. Journal of Food Engineering 46, 211–216 (2000)CrossRefGoogle Scholar
  18. 18.
    Krzanowski, W.J., Jonathan, P., McCarthy, W.V., Thomas, M.R.: Discriminant Analysis with Singular Covariance Matrices: Methods and Applications to Spectroscopic Data. Applied Statistics 44, 105–115 (1995)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Xiaoli Li
    • 1
  • Yong He
    • 1
  1. 1.College of Biosystems Engineering and Food ScienceZhejiang UniversityHangzhouChina

Personalised recommendations