Advertisement

Journal of Mathematical Chemistry

, Volume 52, Issue 8, pp 2197–2209 | Cite as

Sparse matrix transform based weight updating in partial least squares regression

  • Jiangtao Peng
Original Paper

Abstract

Regression from high dimensional observation vectors is particularly difficult when training data is limited. Partial least squares (PLS) partly solves the high dimensional regression problem by projecting the data to latent variables space. The key issue in PLS is the computation of weight vector which describes the covariance between the responses and observations. For small-sample-size and high-dimensional regression problem, the covariance estimation is usually inaccurate and the correlated components in the predictors will distort the PLS weight. In this paper, we propose a sparse matrix transform (SMT) based PLS (SMT-PLS) method for high-dimensional spectroscopy regression. In SMT-PLS, the observation data is first decorrelated by SMT. Then, in the decorrelated data space, the PLS loading weight is computed by least squares regression. SMT technique provides an accurate data covariance estimation, which can overcome the effect of small-sample-size and benefit both the PLS weight computation and subsequent regression prediction. The proposed SMT-PLS method is compared, in terms of root mean square errors of prediction, to PLS, Power PLS and PLS with orthogonal scatter correction on four real spectroscopic data sets. Experimental results demonstrate the efficacy and effectiveness of our proposed method.

Keywords

Partial least squares Sparse matrix transform Weight updating High-dimensional small-sample Spectroscopy regression 

Notes

Acknowledgments

This work was supported by the National Natural Science Foundation of China under Grants No. 11071058.

References

  1. 1.
    R. Tibshirani, J. R. Stat. Soc. B 58, 267 (1996)Google Scholar
  2. 2.
    H. Wold, Perspectives in Probability and Statistics (Academic Press, London, 1975)Google Scholar
  3. 3.
    H. Martens, T. Nas, Multivariate Calibration (Wiley, New York, 1989)Google Scholar
  4. 4.
    G. Cao, C.A. Bouman, Adv. Neural Inf. Process. Syst. 21, 225 (2009)Google Scholar
  5. 5.
    G. Cao, L.R. Bachega, C.A. Bouman, IEEE Trans. Image Process. 20, 625 (2011)CrossRefGoogle Scholar
  6. 6.
    J. Theiler, G. Cao, L.R. Bachega, C.A. Bouman, IEEE J. Sel. Topic Signal Process. 5, 424 (2011)CrossRefGoogle Scholar
  7. 7.
    J. Peng, S. Peng, Q. Xie, J. Wei, Anal. Chim. Acta 690, 162 (2011)CrossRefGoogle Scholar
  8. 8.
    Q.S. Xu, Y.Z. Liang, H.L. Shen, J. Chemom. 15, 135 (2001)CrossRefGoogle Scholar
  9. 9.
  10. 10.
    M. Dyrby, S.B. Engelsen, L. Nørgaard, M. Bruhn, L. Nielsen, Appl. Spectrosc. 56, 579 (2002)CrossRefGoogle Scholar
  11. 11.
    R.W. Kennard, L.A. Stone, Technometrics 11, 137 (1969)CrossRefGoogle Scholar
  12. 12.
    J. Christensen, L. Nørgaard, H. Heimda, J.G. Pedersen, S.B. Engelsen, J. Near Infrared Spectrosc. 12, 63 (2004)CrossRefGoogle Scholar
  13. 13.
  14. 14.
    D.M. Haaland, E.V. Thomas, Anal. Chem. 60, 1193 (1988)CrossRefGoogle Scholar
  15. 15.
    J.S. Shenk, M.O. Westerhaus, Crop Sci. 31, 469 (1991)CrossRefGoogle Scholar
  16. 16.
    U. Indahl, J. Chemom. 19, 32 (2005)CrossRefGoogle Scholar
  17. 17.
    A. Höskuldsson, Chemom. Intell. Lab. Syst. 55, 23 (2001)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Faculty of Mathematics and StatisticsHubei UniversityWuhan China

Personalised recommendations