A New Feature Extraction Method Based on the Partial Least Squares Algorithm and Its Applications

  • Pawel Blaszczyk
  • Katarzyna Stapor
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 57)


The aim of this paper is to present a new feature extraction method. Our method is an extension of the classical Partial Least Squares (PLS) algorithm. However, a new weighted separation criterion is applied which is based on the within and between scatter matrices. In order to compare the performance of the classification the biological and spam datasets are used.


Feature Extraction Partial Little Square Extraction Algorithm Feature Extraction Method Scatter Matrix 
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.
    Blaszczyk, P.: Data classification by using modified partial least squares method. PhD thesis. Silesian University of Technology (2008)Google Scholar
  2. 2.
    Duda, R., Hart, P.: Pattern Classification. John Wiley & Sons, New York (2000)Google Scholar
  3. 3.
    Garthwaite, P.H.: An interpretation of Partial Least Squares. Journal of the American Statistical Association 89, 122 (1994)Google Scholar
  4. 4.
    Höskuldsson, A.: PLS Regression methods. Journal of Chemometrics 2, 211–228 (1988)Google Scholar
  5. 5.
    Gren, J.: Mathematical Statistic. PWN, Warsow (1987)Google Scholar
  6. 6.
    Wold, H.: Soft Modeling by Latent Variables: The Non-Linear Iterative Partial Least Squares (NIPALS) Approach. In: Perspectives in Probability and Statistics, pp. 117–142. Papers in Honour of M. S. Bartlett (1975)Google Scholar
  7. 7.
  8. 8.
  9. 9.
  10. 10.

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Pawel Blaszczyk
    • 1
  • Katarzyna Stapor
    • 2
  1. 1.Institute of MathematicsUniversity of SilesiaPoland
  2. 2.Institute of Computer ScienceSilesian University of TechnologyPoland

Personalised recommendations