2005
DOI: 10.1057/palgrave.ivs.9500086
|View full text |Cite
|
Sign up to set email alerts
|

Constructing and Reconstructing the Reorderable Matrix

Abstract: We consider the backgrounds, applications, implementations, and user interfaces of the reorderable matrix originally introduced by Jacques Bertin. As a new tool for handling the matrix, we propose a new kind of interface for interactive cluster analysis. As the main tool to order the rows and columns, we use the well-known barycenter heuristic. Two user tests are performed to verify the usefulness of the automatic tools. Information Visualization (2005) 4, 32-48.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
31
0
3

Year Published

2007
2007
2014
2014

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 52 publications
(34 citation statements)
references
References 12 publications
0
31
0
3
Order By: Relevance
“…While fully automated analysis yields tremendous benefits such as speed, scientific objectivity and reproducibility [31], full automation also has a number of issues: i) it ignores the analyst's knowledge that cannot be formalized [57]; ii) it yields only minimal exposure to the data and therefore does not encourage deep understanding [22]; iii) it may produce errors that can be way more costly than the effects of human subjectivity [58]; and iv) it often produces visualizations that are suboptimal for communication. For example, cluster analysis throw out lots of data and can produce results that are controversial, subject to misinterpretation, or meaningless [32,39,51].…”
Section: Automatic Vs Manual Approachesmentioning
confidence: 99%
See 1 more Smart Citation
“…While fully automated analysis yields tremendous benefits such as speed, scientific objectivity and reproducibility [31], full automation also has a number of issues: i) it ignores the analyst's knowledge that cannot be formalized [57]; ii) it yields only minimal exposure to the data and therefore does not encourage deep understanding [22]; iii) it may produce errors that can be way more costly than the effects of human subjectivity [58]; and iv) it often produces visualizations that are suboptimal for communication. For example, cluster analysis throw out lots of data and can produce results that are controversial, subject to misinterpretation, or meaningless [32,39,51].…”
Section: Automatic Vs Manual Approachesmentioning
confidence: 99%
“…He concluded that automatic reordering can save time but needs to be interlaced with manual tweaking. Semi-automatic approaches to matrix reordering have been argued for since then [33,51]. Devising semi-automatic methods however requires a good understanding of automatic methods.…”
Section: Automatic Vs Manual Approachesmentioning
confidence: 99%
“…In the latter, structural and temporal patterns could be exhibited on correlation matrices. Although the orderability of matrices can enhance user performance with regards to certain tasks [8], finding the appropriate order on a correlation matrix is a task-dependent question that will be receiving increasing interest [18,10].…”
Section: Related Workmentioning
confidence: 99%
“…The algorithm also minimizes the summed length of all links, ensuring that the vertical layout is as packed as possible. To order individuals and families within each layer, we minimize link crossings using the "barycenter heuristic" published by Siirtola & Mäkinen [35]. dot implements a slightly improved version.…”
Section: Layer Assignmentmentioning
confidence: 99%