Visualisation and Exploration of Scientific Data Using Graphs - Data Mining: Theory, Methodology, Techniques, and Applications - page 14

Visualisation and Exploration of Scientific Data
Using Graphs

Ben Raymond and Lee Belbin

Australian Government, Department of the Environment and Heritage,
Australian Antarctic Division, Channel Highway,
Kingston 7050, Australia
[e-mail]

Abstract. We present a prototype application for graph-based explo-
ration and mining of online databases, with particular emphasis on sci-
entific data. The application builds structured graphs that allow the user
to explore patterns in a data set, including clusters, trends, outliers, and
relationships. A number of different graphs can be rapidly generated,
giving complementary insights into a given data set. The application has
a Flash-based graphical interface and uses semantic information from the
data sources to keep this interface as intuitive as possible. Data can be
accessed from local and remote databases and files. Graphs can be ex-
plored using an interactive visual browser, or graph-analytic algorithms.
We demonstrate the approach using marine sediment data, and show
that differences in benthic species compositions in two Antarctic bays
are related to heavy metal contamination.

1 Introduction

Structured graphs have been recognised as an effective framework for scientific
data mining — e.g. [1, 2]. A graph consists of a set of nodes connected by edges. In
the simplest case, each node represents an entity of interest, and edges between
nodes represent relationships between entities. Graphs thus provide a natural
framework for investigating relational, spatial, temporal, and geometric data [2],
and give insights into clusters, trends, outliers, and other structures. Graphs
have also seen a recent explosion in popularity in science, as network structures
have been found in a variety of fields, including social networks [3, 4], trophic
webs [5], and the structures of chemical compounds [6, 7]. Networks in these
fields provide both a natural representation of data, as well as analytical tools
that give insights not easily gained from other perspectives.
The Australian Antarctic Data Centre (AADC) sought a graph-based visual-
isation and exploration tool that could be used both as a component of in-house
mining activities, as well as by clients undertaking scientific analyses.
The broad requirements of this tool were:

1. Provide functionality to construct, view, and explore graph structures, and
apply graph-theoretic algorithms.