UMR CNRS 7253

Thierry Denoeux
Thierry Denoeux
Thierry Denoeux
Thierry Denoeux
Thierry Denoeux

Site Tools


en:software:mdsi

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
en:software:mdsi [2011/02/04 15:37]
tdenoeux
en:software:mdsi [2011/02/04 15:41] (current)
tdenoeux
Line 1: Line 1:
 ====== Multidimensional Scaling of interval-valued dissimilarity data ====== ====== Multidimensional Scaling of interval-valued dissimilarity data ======
  
-An extension of Principal Component Analysis to fuzzy data, based on three layer autoassociative neural network model. The method is described in:+A Multidimensional Scaling (MDS) method for interval-valued dissimilarity ​data. The objects are represented as hyperspheres in p-dimensional space. The minimum and maximum distances between hyperspheres approximate the lower and upper dissimilarities in the least squares sense. The method is described in:
  
-T. Denoeux and M. Masson. ​Principal component analysis ​of fuzzy data using autoassociative neural networksIEEE Transactions on Fuzzy Systems12(3):336-3492004 + T. Denoeux and M.-H. Masson. ​Multidimensional scaling ​of interval-valued dissimilarity ​data. Pattern Recognition Letters21:83-922000. {{en:​revues:​prl00.pdf|pdf}}
-{{en:​revues:​ieee_fs03.ps|postscript}}+
  
 {{en:​software:​mdsi.zip|Download}} {{en:​software:​mdsi.zip|Download}}
  

User Tools