Combining Cluster and Outlier Analysis with Visual Analytics

Jürgen Bernard, Eduard Dobermann, Michael Sedlmair, Dieter W. Fellner

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

Cluster and outlier analysis are two important tasks. Due to their nature these tasks seem to be opposed to each other, i.e., data objects either belong to a cluster structure or a sparsely populated outlier region. In this work, we present a visual analytics tool that allows the combined analysis of clusters and outliers. Users can add multiple clustering and outlier analysis algorithms, compare results visually, and combine the algorithms' results. The usefulness of the combined analysis is demonstrated using the example of labeling unknown data sets. The usage scenario also shows that identified clusters and outliers can share joint areas of the data space.
Original languageUndefined/Unknown
Title of host publicationEuroVA 2017
PublisherEurographics - European Association for Computer Graphics
Pages19-23
Number of pages5
DOIs
Publication statusPublished - 2017

Fields of Expertise

  • Information, Communication & Computing

Cite this

Bernard, J., Dobermann, E., Sedlmair, M., & Fellner, D. W. (2017). Combining Cluster and Outlier Analysis with Visual Analytics. In EuroVA 2017 (pp. 19-23). Eurographics - European Association for Computer Graphics. https://doi.org/10.2312/eurova.20171114

Combining Cluster and Outlier Analysis with Visual Analytics. / Bernard, Jürgen; Dobermann, Eduard; Sedlmair, Michael; Fellner, Dieter W.

EuroVA 2017. Eurographics - European Association for Computer Graphics, 2017. p. 19-23.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Bernard, J, Dobermann, E, Sedlmair, M & Fellner, DW 2017, Combining Cluster and Outlier Analysis with Visual Analytics. in EuroVA 2017. Eurographics - European Association for Computer Graphics, pp. 19-23. https://doi.org/10.2312/eurova.20171114
Bernard J, Dobermann E, Sedlmair M, Fellner DW. Combining Cluster and Outlier Analysis with Visual Analytics. In EuroVA 2017. Eurographics - European Association for Computer Graphics. 2017. p. 19-23 https://doi.org/10.2312/eurova.20171114
Bernard, Jürgen ; Dobermann, Eduard ; Sedlmair, Michael ; Fellner, Dieter W. / Combining Cluster and Outlier Analysis with Visual Analytics. EuroVA 2017. Eurographics - European Association for Computer Graphics, 2017. pp. 19-23
@inproceedings{1ada23f96b894077997e8d8e4f77f3e4,
title = "Combining Cluster and Outlier Analysis with Visual Analytics",
abstract = "Cluster and outlier analysis are two important tasks. Due to their nature these tasks seem to be opposed to each other, i.e., data objects either belong to a cluster structure or a sparsely populated outlier region. In this work, we present a visual analytics tool that allows the combined analysis of clusters and outliers. Users can add multiple clustering and outlier analysis algorithms, compare results visually, and combine the algorithms' results. The usefulness of the combined analysis is demonstrated using the example of labeling unknown data sets. The usage scenario also shows that identified clusters and outliers can share joint areas of the data space.",
author = "J{\"u}rgen Bernard and Eduard Dobermann and Michael Sedlmair and Fellner, {Dieter W.}",
year = "2017",
doi = "10.2312/eurova.20171114",
language = "undefiniert/unbekannt",
pages = "19--23",
booktitle = "EuroVA 2017",
publisher = "Eurographics - European Association for Computer Graphics",
address = "Schweiz",

}

TY - GEN

T1 - Combining Cluster and Outlier Analysis with Visual Analytics

AU - Bernard, Jürgen

AU - Dobermann, Eduard

AU - Sedlmair, Michael

AU - Fellner, Dieter W.

PY - 2017

Y1 - 2017

N2 - Cluster and outlier analysis are two important tasks. Due to their nature these tasks seem to be opposed to each other, i.e., data objects either belong to a cluster structure or a sparsely populated outlier region. In this work, we present a visual analytics tool that allows the combined analysis of clusters and outliers. Users can add multiple clustering and outlier analysis algorithms, compare results visually, and combine the algorithms' results. The usefulness of the combined analysis is demonstrated using the example of labeling unknown data sets. The usage scenario also shows that identified clusters and outliers can share joint areas of the data space.

AB - Cluster and outlier analysis are two important tasks. Due to their nature these tasks seem to be opposed to each other, i.e., data objects either belong to a cluster structure or a sparsely populated outlier region. In this work, we present a visual analytics tool that allows the combined analysis of clusters and outliers. Users can add multiple clustering and outlier analysis algorithms, compare results visually, and combine the algorithms' results. The usefulness of the combined analysis is demonstrated using the example of labeling unknown data sets. The usage scenario also shows that identified clusters and outliers can share joint areas of the data space.

U2 - 10.2312/eurova.20171114

DO - 10.2312/eurova.20171114

M3 - Beitrag in einem Konferenzband

SP - 19

EP - 23

BT - EuroVA 2017

PB - Eurographics - European Association for Computer Graphics

ER -