A Novel Approach to Pattern Recognition Based on PCA-ANN in Spectroscopy
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.
KeywordsArtificial Neural Network Linear Discriminant Analysis Back Propagation Neural Network Near Infrared Spectroscopy Back Propagation Algorithm
Unable to display preview. Download preview PDF.
- 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
- 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.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.Osborne, B.G., Fearn, T., Hindle, P.H.: Practical NIR Spectroscopy. Longman, Harlow (1993)Google Scholar
- 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
- 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.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.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.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.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