2011
DOI: 10.1198/jcgs.2010.09139
|View full text |Cite
|
Sign up to set email alerts
|

Dissimilarity Plots: A Visual Exploration Tool for Partitional Clustering

Abstract: For hierarchical clustering, dendrograms provide convenient and powerful visualization. Although many visualization methods have been suggested for partitional clustering, their usefulness deteriorates quickly with increasing dimensionality of the data and/or they fail to represent structure between and within clusters simultaneously. In this paper we extend (dissimilarity) matrix shading with several reordering steps based on seriation. Both methods, matrix shading and seriation, have been well-known for a lo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
13
0

Year Published

2012
2012
2023
2023

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 13 publications
(13 citation statements)
references
References 34 publications
(26 reference statements)
0
13
0
Order By: Relevance
“…To further enhance the visualization of the sequences' features in our flagged index plots, we order cases resorting to seriation algorithms (Hahsler and Hornik 2011;Hahsler et al 2008). In particular, we obtained satisfactory results using the so-called Traveling salesperson problem (TSP; Gutin and Punnen 2007).…”
Section: Visualization Of Deviating Sequencesmentioning
confidence: 98%
“…To further enhance the visualization of the sequences' features in our flagged index plots, we order cases resorting to seriation algorithms (Hahsler and Hornik 2011;Hahsler et al 2008). In particular, we obtained satisfactory results using the so-called Traveling salesperson problem (TSP; Gutin and Punnen 2007).…”
Section: Visualization Of Deviating Sequencesmentioning
confidence: 98%
“…(3.4) for both large and small pore-size modes, which are summarized in the form of 30x30 matrices, as shown in Fig. 3 (Hahsler and Hornik, 2011) is next applied to the orthogonality matrices and classify the 30 core samples into 5 rock types, denoted as A, B1, B2, C, and D with descending reservoir quality.…”
Section: Rock Classification By Clustering Orthogonality Matricesmentioning
confidence: 99%
“…The matrices rank all core samples in terms of reservoir quality, whereby they become suitable for petrophysical rock classification. We apply the dissimilarity matrix clustering technique (Hahsler and Hornik, 2011) to orthogonality matrices and classify MICP core samples into BRTs with descending order of reservoir quality.…”
Section: Rock Classification With Pore-system Orthogonalitymentioning
confidence: 99%
See 1 more Smart Citation
“…Finally, we can use dissimilarity plots (Hahsler and Hornik 2011) to visualize the quality of the obtained partition (see Figure 1 This again illustrates that the two Thompson clusters are rather markedly separated from themselves and the Baum clusters, with the last two less well separated from each other.…”
Section: Examplementioning
confidence: 99%