Advertisement

Computing

, Volume 16, Issue 4, pp 379–387 | Cite as

Algorithm 30 L1 cluster analysis

  • H. Späth
Algorithm

Abstract

The FORTRAN implementation of an algorithm is given for approximating an optimal clustering ofm objects inton classes such that the total sum of the sums of absolute deviations from the class members to the class centers (medians) is minimized.

Keywords

Cluster Analysis Computational Mathematic Absolute Deviation Optimal Cluster Class Member 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

L1-Cluster-Analyse

Zusammenfassung

Die FORTRAN-Implementation eines Verfahrens zur näherungsweisen Gewinnung einer optimalen Klassifikation vonm Objekten inn Klassen derart, daß die Gesamtsumme der Summen der absoluten Abweichungen der Klassenmitglieder zu den Klassenzentren (Zentralwerte) minimiert wird, wird angegeben.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Späth, H.: Algorithm. Clustering of One-dimensional Ordered Data. Computing11, 175–177 (1973).Google Scholar
  2. [2]
    Späth, H.: Cluster-Analyse-Algorithmen zur Objektklassifizierung und Datenreduktion. München: R. Oldenbourg 1975.Google Scholar
  3. [3]
    Sparks, D. N.: Algorithm AS 58: Euclidean Cluster Analysis. Apl. Stat.22, 126–130 (1973).Google Scholar

Copyright information

© Springer-Verlag 1976

Authors and Affiliations

  • H. Späth
    • 1
  1. 1.Universität OldenburgOldenburgFederal Republic of Germany

Personalised recommendations