Generalized Kernel Discriminant Analysis using Weighting Function with Applications to Feature Extraction

@inproceedings{Yang2016GeneralizedKD,
  title={Generalized Kernel Discriminant Analysis using Weighting Function with Applications to Feature Extraction},
  author={Jing Yang},
  year={2016}
}
Linear discriminant analysis (LDA) is a classical approach for dimensionality reduction. However, LDA has shortcomings in that one of the scatter matrices is required to be nonsingular and the nonlinearly clustered structure is not easily captured, moreover, the adverse effects due to outlier classes also affect the performance of LDA. In order to solve these problems, in this paper, several nonlinear generalizations of LDA using weighting function are presented and called them weighted… CONTINUE READING

Similar Papers

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

Fractional-Step Dimensionality Reduction

  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 2000
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

A comparison of generalized linear discriminant analysis algorithms

C. H. Park, H. Park
  • Pattern Recognition,
  • 2008
VIEW 1 EXCERPT