Cluster Analysis using Spherical SOM

DOI Web Site 4 Citations 11 References

Bibliographic Information

Other Title
  • 球面SOMを用いたクラスタ分析
  • キュウメン SOM オ モチイタ クラスタ ブンセキ

Search this article

Description

A cluster analysis method is proposed in this paper. This method is able to visualize a multi-dimensional dataset as a graphical object, or Glyph, and extract a tree structure from the object as a dendrogram. As benchmark data, the Fisher's iris dataset and Wine recognition data were used. As a result of the numerical experiment, a clustering method by the dendrogram took 97% in accuracy from Group Average, Flexible, and Centroid methods using Glyph Analysis Setting of 1.0. To be compared with the usual dendrogram method, our proposed method has the corresponding visualization on the polygon surface as well as dendrogram. Also, the classification of the unconfirmed dataset will be possible by this method. It is difficult to display a multi-dimensional data by the dendrogram in the one dimension. The ultimate of the visualization is 3 dimensional expression. We can conclude that it should be the best way that a multi-dimensional data is expressed by a sphere where the phase relationship is smooth.

Journal

Citations (4)*help

See more

References(11)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top