Abstract
(SPLOM) to explore multivariate datasets. The scatterplots of a SPLOM
can help to identify and compare two-dimensional global
patterns. However, local patterns which might only exist within
subsets of records are typically much harder to identify and may go
unnoticed among larger sets of plots in a SPLOM. This paper explores
the notion of local patterns and presents a novel approach to visually
select, search for, and compare local patterns in a multivariate
dataset. Model-based and shape-based pattern descriptors are used to
automatically compare local regions in scatterplots to assist in the
discovery of similar local patterns. Mechanisms are provided to
assess the level of similarity between local patterns and to rank
similar patterns effectively. Moreover, a relevance feedback module is
used to suggest potentially relevant local patterns to the user. The
approach has been implemented in an interactive tool and demonstrated
with two real-world datasets and use cases. It supports the discovery
of potentially useful information such as clusters, functional
dependencies between variables, and statistical relationships in
subsets of data records and dimensions.
Original language | English |
---|---|
Pages (from-to) | 99-109 |
Number of pages | 11 |
Journal | Computer Graphics Forum |
Volume | 37 |
Issue number | 3 |
DOIs | |
Publication status | Published - 2018 |
Fingerprint
Fields of Expertise
- Information, Communication & Computing
Cite this
Interactive Visual Exploration of Local Patterns in Large Scatterplot Spaces. / Chegini, M.; Shao, L.; Gregor, R.; Lehmann, D.; Andrews, K.; Schreck, T.
In: Computer Graphics Forum, Vol. 37, No. 3, 2018, p. 99-109.Research output: Contribution to journal › Article › Research › peer-review
}
TY - JOUR
T1 - Interactive Visual Exploration of Local Patterns in Large Scatterplot Spaces
AU - Chegini, M.
AU - Shao, L.
AU - Gregor, R.
AU - Lehmann, D.
AU - Andrews, K.
AU - Schreck, T.
PY - 2018
Y1 - 2018
N2 - Analysts often use visualisation techniques like a scatterplot matrix(SPLOM) to explore multivariate datasets. The scatterplots of a SPLOMcan help to identify and compare two-dimensional globalpatterns. However, local patterns which might only exist withinsubsets of records are typically much harder to identify and may gounnoticed among larger sets of plots in a SPLOM. This paper exploresthe notion of local patterns and presents a novel approach to visuallyselect, search for, and compare local patterns in a multivariatedataset. Model-based and shape-based pattern descriptors are used toautomatically compare local regions in scatterplots to assist in thediscovery of similar local patterns. Mechanisms are provided toassess the level of similarity between local patterns and to ranksimilar patterns effectively. Moreover, a relevance feedback module isused to suggest potentially relevant local patterns to the user. Theapproach has been implemented in an interactive tool and demonstratedwith two real-world datasets and use cases. It supports the discoveryof potentially useful information such as clusters, functionaldependencies between variables, and statistical relationships insubsets of data records and dimensions.
AB - Analysts often use visualisation techniques like a scatterplot matrix(SPLOM) to explore multivariate datasets. The scatterplots of a SPLOMcan help to identify and compare two-dimensional globalpatterns. However, local patterns which might only exist withinsubsets of records are typically much harder to identify and may gounnoticed among larger sets of plots in a SPLOM. This paper exploresthe notion of local patterns and presents a novel approach to visuallyselect, search for, and compare local patterns in a multivariatedataset. Model-based and shape-based pattern descriptors are used toautomatically compare local regions in scatterplots to assist in thediscovery of similar local patterns. Mechanisms are provided toassess the level of similarity between local patterns and to ranksimilar patterns effectively. Moreover, a relevance feedback module isused to suggest potentially relevant local patterns to the user. Theapproach has been implemented in an interactive tool and demonstratedwith two real-world datasets and use cases. It supports the discoveryof potentially useful information such as clusters, functionaldependencies between variables, and statistical relationships insubsets of data records and dimensions.
UR - https://ftp.isds.tugraz.at/pub/papers/chegini-eurovis2018-sp-patterns-eg.pdf
U2 - 10.1111/cgf.13404
DO - 10.1111/cgf.13404
M3 - Article
VL - 37
SP - 99
EP - 109
JO - Computer Graphics Forum
JF - Computer Graphics Forum
SN - 0167-7055
IS - 3
ER -