Cluster Ensemble Methods: from Single Clusterings to Combined Solutions

Fred, Ana; Lourenço, André

doi:10.1007/978-3-540-78981-9_1

Cited by 44 publications

(28 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 and Fig 2 show the NMI scores and F1 measures of the nine clustering integration algorithms over six datasets, respectively. In the figures, EASL, EACL, EAAL and EAWL represent the single linkage, complete linkage, average linkage and ward linkage algorithms proposed in [3], respectively, SGTA is the spectral graph theory-based algorithm proposed in [4], and SMSA is the similarity matrix-based spectral algorithm proposed in [5]. Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Strehl and Ghosh propose CSPA (Cluster-based Similarity Partitioning Algorithm), HGPA (Hyper-graph Partitioning Algorithm) and MCLA (Meta-Clustering Algorithm) based on graph partitioning algorithms [2]. Fred and Jain [3] use agglomerative clustering algorithms such as single linkage, complete linkage, average linkage and ward linkage algorithms to produce a final clustering according to the similarity matrix. Recently, Xu et al [4,5] introduce the key ideas of spectral graph theory and proposed two spectral clustering algorithms to solve document clustering combination problem.…”

Section: Clustering Integrationmentioning

confidence: 99%

“…There have been thousands of clustering algorithms, but in practice no one is able to identify clusters with different sizes, shapes, and densities [1]. Recently, many studies show that the combination of multiple clustering algorithms could result in novel and robust clustering results [2][3][4][5]. The key problem in clustering combination is how to design a consensus function so to as obtaining a final superior result.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis and Comparisons of Clustering Consensus Functions

Xu¹,

Zhou

2012

Proceedings of the 2nd International Conference on Electronic and Mechanical Engineering and Information Technology (2012)

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Clustering Integrationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis and Comparisons of Clustering Consensus Functions

Xu¹,

Zhou

2012

Proceedings of the 2nd International Conference on Electronic and Mechanical Engineering and Information Technology (2012)

View full text Add to dashboard Cite

show abstract

“…Ensemble clustering methods (Hornik and Leisch 2005;Fred and Lourenço 2008) aim at combining multiple clustering solutions or partitions into a single one, offering a better description of the data. In this section, we explain how to address this fusion problem using the general framework introduced in Sect.…”

Section: Belief Functions On Partitionsmentioning

confidence: 99%

Evidential reasoning in large partially ordered sets

Denœux

Masson

2011

Ann Oper Res

View full text Add to dashboard Cite

The Dempster-Shafer theory of belief functions has proved to be a powerful formalism for uncertain reasoning. However, belief functions on a finite frame of discernment are usually defined in the power set 2 , resulting in exponential complexity of the operations involved in this framework, such as combination rules. When is linearly ordered, a usual trick is to work only with intervals, which drastically reduces the complexity of calculations. In this paper, we show that this trick can be extrapolated to frames endowed with an arbitrary lattice structure, not necessarily a linear order. This principle makes it possible to apply the Dempster-Shafer framework to very large frames such as the power set, the set of partitions, or the set of preorders of a finite set. Applications to multi-label classification, ensemble clustering and preference aggregation are demonstrated.

show abstract

“…Studies in the last few years have tended to combinational methods. Cluster ensemble methods attempt to find better and more robust clustering solutions by fusing information from several primary data partitionings [8].…”

Section: Introductionmentioning

confidence: 99%

A New Criterion for Clusters Validation

Alizadeh

Minaei

Parvïn

2011

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Abstract. In this paper a new criterion for clusters validation is proposed. This new cluster validation criterion is used to approximate the goodness of a cluster. The clusters which satisfy a threshold of this measure are selected to participate in clustering ensemble. For combining the chosen clusters, a co-association based consensus function is applied. Since the Evidence Accumulation Clustering method cannot derive the co-association matrix from a subset of clusters, a new EAC based method which is called Extended EAC, EEAC, is applied for constructing the co-association matrix from the subset of clusters. Employing this new cluster validation criterion, the obtained ensemble is evaluated on some well-known and standard data sets. The empirical studies show promising results for the ensemble obtained using the proposed criterion comparing with the ensemble obtained using the standard clusters validation criterion.

show abstract

Cluster Ensemble Methods: from Single Clusterings to Combined Solutions

Cited by 44 publications

References 20 publications

Analysis and Comparisons of Clustering Consensus Functions

Analysis and Comparisons of Clustering Consensus Functions

Evidential reasoning in large partially ordered sets

A New Criterion for Clusters Validation

Contact Info

Product

Resources

About