Advertisement

Classifying Unbalanced Pattern Groups by Training Neural Network

  • Bo-Yu Li
  • Jing Peng
  • Yan-Qiu Chen
  • Ya-Qiu Jin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3972)

Abstract

When training set is unbalanced, the conventional least square error (LSE) training strategy is less efficient to train neural network (NN) for classification because it often lead the NN to overcompensate for the dominant group. Therefore, in this paper a dynamic threshold learning algorithm (DTLA) is proposed as the substitute for the conventional LSE algorithm. This method uses multiple dynamic threshold parameters to gradually remove some training patterns that can be classified correctly by current Radial Basis Function (RBF) network out of the training set during training process, which changes the unbalanced training problem into a balanced training problem and improves the classification rate of the small group. Moreover, we use the dynamical threshold learning algorithm to classify the remote sensing images, when the unbalanced level of classes is high, a good effect is obtained.

Keywords

Radial Basis Function Training Process Radial Basis Function Neural Network Output Unit Training Pattern 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Murphey, Y.L., Guo, H., Feldkamp, L.A.: Neural Learning from Unbalanced Data. Applied Intelligence 21(2), 117–128 (2004)MATHCrossRefGoogle Scholar
  2. 2.
    David, L., Andrew, R.W.: Optimized Feature Extraction and the Bayes Decision in Feed-Forward Classifier Networks. IEEE Trans. on PAMI 13(4), 355–364 (1991)Google Scholar
  3. 3.
    Friedhelm, S., Kestler, H.A., Palm, G.: Three Learning Phases for Radial-Basis-Function Networks. Neural Networks 14(4-5), 439–458 (2001)CrossRefGoogle Scholar
  4. 4.
    Sontag, E., Sussman, H.: Backpropagation Separates When Perceptrons Do. In: Proceeding IEEE International Joint Conference on Neural Networks (Washington DC), vol. 1, pp. 639–642 (1989)Google Scholar
  5. 5.
    Francesco, L., Marco, S.: Efficient Training of RBF Neural Networks for Pattern Recognition. IEEE Trans on Neural Networks 12(5), 1235–1241 (2001)CrossRefGoogle Scholar
  6. 6.
    Sami, M.A., Linwood, J., Park, J.D., Shannon, M.F.: A Neural Network Algorithm for Sea Ice Edge Classification. IEEE Trans. on Geosciene and Remote Sensing 35(4), 817–826 (1997)CrossRefGoogle Scholar
  7. 7.
    James, J.S., Timothy, J.M.: A Recurrent Neural Network Classifier for Improved Retrievals of Areal Extent of Snow Cover. IEEE Trans. on Geoscience and Remote Sensing 39(10), 2135–2147 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Bo-Yu Li
    • 1
  • Jing Peng
    • 1
  • Yan-Qiu Chen
    • 1
  • Ya-Qiu Jin
    • 1
  1. 1.Key Laboratory of Wave Scattering and Remote Sensing Information,(Ministry of Education)Fudan UniversityShanghaiChina

Personalised recommendations