Integrating Cluster Formation and Cluster Evaluation in Interactive Visual Analysis
Abstract
Cluster analysis is a popular method for data investigation wheredata items are structured into groups called clusters. This analysisinvolves two sequential steps, namely cluster formation and clusterevaluation. In this paper, we propose the tight integration of clusterformation and cluster evaluation in interactive visual analysis in orderto overcome the challenges that relate to the black-box nature ofclustering algorithms. We present our conceptual framework in theform of an interactive visual environment. In this realization of ourframework, we build upon general concepts such as cluster comparison,clustering tendency, cluster stability and cluster coherence.Additionally, we showcase our framework on the cluster analysis ofmixed lipid bilayers.
C. Turkay, J. Parulek, N. Reuter, and H. Hauser, "Integrating Cluster Formation and Cluster Evaluation in Interactive Visual Analysis," in Proc. Spring Conference on Computer Graphics (SCCG 2011) – second best paper, 2011, p. ??–??.
[BibTeX]
Cluster analysis is a popular method for data investigation wheredata items are structured into groups called clusters. This analysisinvolves two sequential steps, namely cluster formation and clusterevaluation. In this paper, we propose the tight integration of clusterformation and cluster evaluation in interactive visual analysis in orderto overcome the challenges that relate to the black-box nature ofclustering algorithms. We present our conceptual framework in theform of an interactive visual environment. In this realization of ourframework, we build upon general concepts such as cluster comparison,clustering tendency, cluster stability and cluster coherence.Additionally, we showcase our framework on the cluster analysis ofmixed lipid bilayers.
@INPROCEEDINGS {turkay11cluster,
author = "Cagatay Turkay and Julius Parulek and Nathalie Reuter and Helwig Hauser",
title = "Integrating Cluster Formation and Cluster Evaluation in Interactive Visual Analysis",
booktitle = "Proc. Spring Conference on Computer Graphics (SCCG 2011) -- second best paper",
year = "2011",
pages = "??--??",
abstract = "Cluster analysis is a popular method for data investigation wheredata items are structured into groups called clusters. This analysisinvolves two sequential steps, namely cluster formation and clusterevaluation. In this paper, we propose the tight integration of clusterformation and cluster evaluation in interactive visual analysis in orderto overcome the challenges that relate to the black-box nature ofclustering algorithms. We present our conceptual framework in theform of an interactive visual environment. In this realization of ourframework, we build upon general concepts such as cluster comparison,clustering tendency, cluster stability and cluster coherence.Additionally, we showcase our framework on the cluster analysis ofmixed lipid bilayers.",
pdf = "pdfs/turkay11cluster.pdf",
images = "images/turkay11cluster2.jpg, images/turkay11cluster1.jpg, images/turkay11cluster3.jpg",
thumbnails = "images/turkay11cluster2_thumb.jpg, images/turkay11cluster1_thumb.jpg, images/turkay11cluster3_thumb.jpg",
location = "Budmerice, Slovakia"
}