On local orthonormal bases for classification and regression

  title={On local orthonormal bases for classification and regression},
  author={Naoki Saito and Ronald R. Coifman},
We describe extensions to the \best-basis" method to select orthonormal bases suitable for signal classiica-tion and regression problems from a large collection of orthonormal bases. For classiication problems, we select the basis which maximizes relative entropy of time-frequency energy distributions among classes. For regression problems, we select the basis which tries to minimize the regression error. Once these bases are selected, the most signiicant coordinates are fed into a traditional… CONTINUE READING
9 Citations
10 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 10 references

Classi cation and Regression Trees

  • L. Breiman, J. H. Friedman, R. A. Olshen, C. J. Stone
  • Chap- man & Hall, Inc., New York
  • 1993
Highly Influential
6 Excerpts

Constructions of local orthonormal bases for classi cation and regression

  • R. R. Coifman, N. Saito
  • Comptes Rendus Acad. Sci. Paris, S erie I, vol…
  • 1994
1 Excerpt

Local Feature Extraction and Its Applica- tions Using a Library of Bases

  • N. Saito
  • Ph.D. thesis, Dept. of Mathematics, Yale…
  • 1994
2 Excerpts

Distance measures for signal pro- cessing and pattern recognition

  • M. Basseville
  • Signal Processing, vol. 18, no. 4, pp. 349{369
  • 1989

Coifman , \ Local discriminantbases " , inMathematical Imaging : Wavelet Applications in Signal and Image Processing ( A

  • R. R.

Cover , \ The best two independent measurements are not the two best "

  • M. T.
  • IEEE Trans . Syst . Man Cybern .

Similar Papers

Loading similar papers…