SEP/COP: An efficient method to find the best partition in hierarchical clustering based on a new cluster validity index

Gurrutxaga, Ibai; Albisua, Iñaki; Arbelaitz, Olatz; Martín, Jesús Izquierdo; Muguerza, Javier; Pérez, Jesús M.; Perona, Iñigo

doi:10.1016/j.patcog.2010.04.021

Cited by 74 publications

(21 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, the idea of searching for the representative partition of a hierarchy, not only in the explicit levels of the hierarchy, but in an extended partition set was proposed [5]. As future work, we will generalize our current approach to this extended partition set, where better results could be found.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Partition Selection Approach for Hierarchical Clustering Based on Clustering Ensemble

Vega-Pons

Ruiz-Shulcloper

2010

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

Abstract. Hierarchical clustering algorithms are widely used in many fields of investigation. They provide a hierarchy of partitions of the same dataset. However, in many practical problems, the selection of a representative level (partition) in the hierarchy is needed. The classical approach to do so is by using a cluster validity index to select the best partition according to the criterion imposed by this index. In this paper, we present a new approach based on the clustering ensemble philosophy. The representative level is defined here as the consensus partition in the hierarchy. In the consensus computation process, we take into account the similarity between partitions and information from the evaluation of partitions with different cluster validity indexes. An experimental comparison on several datasets shows the superiority of the proposed approach with respect to the classical approach.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Nowadays, classical CVIs like Calinski-Harabasz (CH) index, Hartigan (HA) index and the Dunn index [3] together with the Highest-Lifetime(HL) index [4] are some of the most used. However, new indexes still appear every year in the literature, e.g., the COP index [5].…”

Section: Introductionmentioning

confidence: 99%

Partition Selection Approach for Hierarchical Clustering Based on Clustering Ensemble

Vega-Pons

Ruiz-Shulcloper

2010

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

show abstract

“…On some data sets, noises randomly uniformly distributed are added. There are seven data sets assigned, D1-4g, D2-3g, D2-3gr10 (data sets D2-3g, with 10% noise), D3-3g, D3-3gr10 (data sets D3-3g, with 10% noise), D4-10g [12] (data set having overlapped clusters) and D4-10gSS [12] (data set D4-10g, without overlapped clusters).…”

Section: Data Setsmentioning

confidence: 99%

“…This data can be split into six clusters, Carcinoma, Fibroadenoma, Mastopathy, Glandular, Connective and Adipose [36]. [12]. …”

Section: Real Data Setsmentioning

confidence: 99%

Variability analysis of the hierarchical clustering algoritms and its implication on consensus clustering

Sousa¹

2017

IJAERS

View full text Add to dashboard Cite

show abstract

“…More recently, Gurrutxaga et al (2010) combined a new cluster validity index with a searching strategy (SEP/COP) for exploring the extended hierarchy housed in a dendrogram, i.e. a strategy able to select partitions not necessarily corresponding to horizontal cuts of the dendrogram.…”

Section: Introductionmentioning

confidence: 99%

DESPOTA: DEndrogram Slicing through a PemutatiOn Test Approach

Bruzzese

Vistocco

2015

J Classif

View full text Add to dashboard Cite

Hierarchical clustering represents one of the most widespread analytical approaches to tackle classification problems mainly due to the visual powerfulness of the associated graphical representation, the dendrogram. That said, the requirement of appropriately choosing the number of clusters still represents the main difficulty for the final user. We introduce DESPOTA (DEndrogram Slicing through a PermutatiOn Test Approach), a novel approach exploiting permutation tests in order to automatically detect a partition among those embedded in a dendrogram. Unlike the traditional approach, DESPOTA includes in the search space also partitions not corresponding to horizontal cuts of the dendrogram. Applications on both real and syntethic datasets will show the effectiveness of our proposal

show abstract

SEP/COP: An efficient method to find the best partition in hierarchical clustering based on a new cluster validity index

Cited by 74 publications

References 32 publications

Partition Selection Approach for Hierarchical Clustering Based on Clustering Ensemble

Partition Selection Approach for Hierarchical Clustering Based on Clustering Ensemble

Variability analysis of the hierarchical clustering algoritms and its implication on consensus clustering

DESPOTA: DEndrogram Slicing through a PemutatiOn Test Approach

Contact Info

Product

Resources

About