K-EVCLUS: Clustering large dissimilarity data in the belief function framework

K-EVCLUS: Clustering large dissimilarity data in the belief function framework

© Springer International Publishing Switzerland 2016. In evidential clustering, the membership of objects to clusters is considered to be uncertain and is represented by mass functions, forming a credal partition. The EVCLUS algorithm constructs a credal partition in such a way that larger dissimila...

Full description

Saved in:
Bibliographic Details
Main Authors: Orakanya Kanjanatarakul, Songsak Sriboonchitta, Thierry Denoeux
Format: Book Series
Published: 2018
Subjects:
Computer Science
Mathematics
Online Access:https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84988629130&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/55605
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-55605
record_format dspace
spelling th-cmuir.6653943832-556052018-09-05T03:07:13Z K-EVCLUS: Clustering large dissimilarity data in the belief function framework Orakanya Kanjanatarakul Songsak Sriboonchitta Thierry Denoeux Computer Science Mathematics © Springer International Publishing Switzerland 2016. In evidential clustering, the membership of objects to clusters is considered to be uncertain and is represented by 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 propose to replace the gradient-based optimization procedure in the original EVCLUS algorithm by a much faster iterative rowwise quadratic programming method. We also show that EVCLUS can be provided with only a random sample of the dissimilarities, reducing the time and space complexity from quadratic to linear. These improvements make EVCLUS suitable to cluster large dissimilarity datasets. 2018-09-05T02:58:23Z 2018-09-05T02:58:23Z 2016-01-01 Book Series 16113349 03029743 2-s2.0-84988629130 10.1007/978-3-319-45559-4_11 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84988629130&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/55605
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
topic Computer Science
Mathematics
spellingShingle Computer Science
Mathematics
Orakanya Kanjanatarakul
Songsak Sriboonchitta
Thierry Denoeux
K-EVCLUS: Clustering large dissimilarity data in the belief function framework
description © Springer International Publishing Switzerland 2016. In evidential clustering, the membership of objects to clusters is considered to be uncertain and is represented by 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 propose to replace the gradient-based optimization procedure in the original EVCLUS algorithm by a much faster iterative rowwise quadratic programming method. We also show that EVCLUS can be provided with only a random sample of the dissimilarities, reducing the time and space complexity from quadratic to linear. These improvements make EVCLUS suitable to cluster large dissimilarity datasets.
format Book Series
author Orakanya Kanjanatarakul
Songsak Sriboonchitta
Thierry Denoeux
author_facet Orakanya Kanjanatarakul
Songsak Sriboonchitta
Thierry Denoeux
author_sort Orakanya Kanjanatarakul
title K-EVCLUS: Clustering large dissimilarity data in the belief function framework
title_short K-EVCLUS: Clustering large dissimilarity data in the belief function framework
title_full K-EVCLUS: Clustering large dissimilarity data in the belief function framework
title_fullStr K-EVCLUS: Clustering large dissimilarity data in the belief function framework
title_full_unstemmed K-EVCLUS: Clustering large dissimilarity data in the belief function framework
title_sort k-evclus: clustering large dissimilarity data in the belief function framework
publishDate 2018
url https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84988629130&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/55605
_version_ 1681424537050152960

Similar Items