Repository logo
 
Publication

A MAP approach to evidence accumulation clustering

dc.contributor.authorLourenço, André Ribeiro
dc.contributor.authorBulo, Samuel Rota
dc.contributor.authorRebagliati, Nicola
dc.contributor.authorFred, Ana
dc.contributor.authorFigueiredo, Mário
dc.contributor.authorPelillo, Marcello
dc.date.accessioned2016-04-27T17:00:51Z
dc.date.available2016-04-27T17:00:51Z
dc.date.issued2015
dc.description.abstractThe Evidence Accumulation Clustering (EAC) paradigm is a clustering ensemble method which derives a consensus partition from a collection of base clusterings obtained using different algorithms. It collects from the partitions in the ensemble a set of pairwise observations about the co-occurrence of objects in a same cluster and it uses these co-occurrence statistics to derive a similarity matrix, referred to as co-association matrix. The Probabilistic Evidence Accumulation for Clustering Ensembles (PEACE) algorithm is a principled approach for the extraction of a consensus clustering from the observations encoded in the co-association matrix based on a probabilistic model for the co-association matrix parameterized by the unknown assignments of objects to clusters. In this paper we extend the PEACE algorithm by deriving a consensus solution according to a MAP approach with Dirichlet priors defined for the unknown probabilistic cluster assignments. In particular, we study the positive regularization effect of Dirichlet priors on the final consensus solution with both synthetic and real benchmark data.pt_PT
dc.identifier.citationLOURENÇO, André; [et al] - A MAP approach to evidence accumulation clustering. ICPRAM 2013 - 2nd International Conference on Pattern Recognition Applications and Methods. ISSN 2194-5357. Vol. 318 (2015), pp. 85-100pt_PT
dc.identifier.doi10.1007/978-3-319-12610-4_6pt_PT
dc.identifier.isbn978-3-319-12610-4
dc.identifier.isbn978-3-319-12609-8
dc.identifier.issn2194-5357
dc.identifier.urihttp://hdl.handle.net/10400.21/6104
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherSpringer-Verlag Berlinpt_PT
dc.subjectClustering algorithmpt_PT
dc.subjectClustering ensemblespt_PT
dc.subjectProbabilistic modelingpt_PT
dc.subjectEvidence accumulation clusteringpt_PT
dc.subjectPrior knowledgept_PT
dc.titleA MAP approach to evidence accumulation clusteringpt_PT
dc.typeconference object
dspace.entity.typePublication
oaire.citation.conferencePlaceBarcelona, Spainpt_PT
oaire.citation.endPage100pt_PT
oaire.citation.startPage85pt_PT
oaire.citation.titleICPRAM 2013, 2nd International Conference on Pattern Recognition Applications and Methodspt_PT
oaire.citation.volume318pt_PT
rcaap.rightsclosedAccesspt_PT
rcaap.typeconferenceObjectpt_PT

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
A MAP approach to evidence accumulation clustering.pdf
Size:
333.24 KB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: