Skip to Main content Skip to Navigation
Journal articles

Evidential clustering of large dissimilarity data

Abstract : In evidential clustering, the membership of objects to clusters is considered to be uncertain and is represented by Dempster-Shafer mass functions, forming a credal partition. The EVCLUS algorithm constructs a credal partition in such a way that larger dissimilarities between objects correspond to higher degrees of conflict between the associated mass functions. In this paper, we present several improvements to EVCLUS, making it applicable to very large dissimilarity data. First, the gradient-based optimization procedure in the original EVCLUS algorithm is replaced by a much faster iterative row-wise quadratic programming method. Secondly, we show that EVCLUS can be provided with only a random sample of the dissimilarities, reducing the time and space complexity from quadratic to roughly linear. Finally, we introduce a two-step approach to construct credal partitions assigning masses to selected pairs of clusters, making the algorithm outputs more informative than those of the original EVCLUS, while remaining manageable for large numbers of clusters.
Document type :
Journal articles
Complete list of metadata

Cited literature [34 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01324491
Contributor : Thierry Denoeux <>
Submitted on : Wednesday, June 1, 2016 - 9:54:10 AM
Last modification on : Monday, March 29, 2021 - 2:45:43 PM
Long-term archiving on: : Friday, September 2, 2016 - 10:27:14 AM

File

evclus_kbs_v2_clean.pdf
Files produced by the author(s)

Identifiers

Citation

Thierry Denoeux, Songsak Sriboonchitta, Orakanya Kanjanatarakul. Evidential clustering of large dissimilarity data. Knowledge-Based Systems, Elsevier, 2016, 106, pp.179-195. ⟨10.1016/j.knosys.2016.05.043⟩. ⟨hal-01324491⟩

Share

Metrics

Record views

353

Files downloads

492