Contour approximation of data: A duality theory

Creative Commons License

Iyigun C., Ben-Israel A.

LINEAR ALGEBRA AND ITS APPLICATIONS, vol.430, no.10, pp.2771-2780, 2009 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 430 Issue: 10
  • Publication Date: 2009
  • Doi Number: 10.1016/j.laa.2009.01.023
  • Journal Name: LINEAR ALGEBRA AND ITS APPLICATIONS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.2771-2780
  • Middle East Technical University Affiliated: Yes

Abstract

Given a dataset D partitioned in clusters, the joint distance function (JDF)J(x) at any point x is the harmonic mean of the distances between x and the cluster centers. The JDF is a continuous function, capturing the data points in its lower level sets (a property called contour approximation), and is a useful concept in probabilistic clustering and data analysis.