Optimization of the synthesis of hyperplane clusters and neurofunctional transforms in signal classification systems

  • Authors:
  • N. F. Kirichenko;Yu. G. Krivonos;N. P. Lepekha

  • Affiliations:
  • V. M. Glushkov Institute of Cybernetics, National Academy of Sciences of Ukraine, Kyiv, Ukraine;V. M. Glushkov Institute of Cybernetics, National Academy of Sciences of Ukraine, Kyiv, Ukraine;V. M. Glushkov Institute of Cybernetics, National Academy of Sciences of Ukraine, Kyiv, Ukraine

  • Venue:
  • Cybernetics and Systems Analysis
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper continues the analysis of clustering and signal classification problems. For problems of point-set clustering in a feature space, an optimal algorithm to synthesize hyperplane clusters and an algorithm to solve a problem on linear separability of a finite point set are obtained, criteria for linear strip separability of points in a feature space into two classes are formulated, and methods of finding optimal nonlinear transform of a coordinate of the feature vector in given classes of functions and its index are developed.