[Master Index] [Index for export/lyngby]

lyngby_km_centersim

(export/lyngby/lyngby_km_centersim.m)


Function Synopsis

S = lyngby_km_centersim(X, Centers, assign, varargin) 

Help text

 lyngby_km_centersim  - K-means center similarity

	function S = lyngby_km_centersim(X, Centers, assign)

       Input:    X          Datamatrix, size: objects x variables 
                 Centers    Cluster centers, size: clusters x
                            variables 
                 assign     Assignment vector, size: objects x 1 

       Property: Similarity [ {InverseEuclidean} | corrcoef ]

       Output:   S          Similarity matrix, size: objects x 1 

       This function will calculate the similarity between the
       cluster centers and their assigned data points from the X
       matrix. 
       
       If 'similarity' is 'InverseEuclidean' the similarity is
       calculated as the inverse of the Euclidean distance:
           1/sum( (X-center).^2 )
       For 'CorrCoef' as 'similarity' the similarity is computed as
       the correlation coefficient, that is between -1 and +1 as
       implemented in the corrcoef Matlab function

       See also LYNGBY, LYNGBY_KM_MAIN, LYNGBY_KM_PLOT_DIST.

 $Id: lyngby_km_centersim.m,v 1.3 2003/01/30 12:03:20 fnielsen Exp $

Cross-Reference Information

This function is called by

Produced by mat2html on Wed Jul 29 15:43:40 2009
Cross-Directory links are: OFF