Proceedings of the 2007 Winter Simulation Conference
S. G. Henderson, B. Biller, M.-H. Hsieh, J. Shortle, J. D. Tew, and R. R. Barton, eds.
TOWARDS A CONCEPTUAL FRAMEWORK FOR VISUAL ANALYTICS OF
TIME AND TIME-ORIENTED DATA
Wolfgang Aigner
Alessio Bertone
Silvia Miksch
Department of Information and Knowledge Engineering
Dr.-Karl-Dorrek-Strasse 30, Danube University Krems
A-3500 Krems, AUSTRIA
Christian Tominski
Heidrun Schumann
Department of Computer Science
Albert-Einstein-Strasse 21, University of Rostock
D-18059 Rostock, GERMANY
ABSTRACT
Time is an important data dimension with distinct charac-
teristics that is common across many application domains.
This demands specialized methods in order to support proper
analysis and visualization to explore trends, patterns, and
relationships in different kinds of time-oriented data.
The human perceptual system is highly sophisticated
and specifically suited to spot visual patterns. For this reason,
visualization is successfully applied in aiding these tasks.
But facing the huge volumes of data to be analyzed today,
applying purely visual techniques is often not sufficient.
Visual analytics systems aim to bridge this gap by combining
both, interactive visualization and computational analysis.
In this paper, we introduce a concept for designing visual
analytics frameworks and tailored visual analytics systems
for time and time-oriented data. We present a number
of relevant design choices and illustrate our concept by
example.
1 MOTIVATION AND BACKGROUND
During the last decade, capabilities to both generate and
collect data have seen an explosive growth. Advances in
scientific and business data collection (e.g., from remote
sensors, from space satellites, or from retail and production
devices as well as growingly complex simulation systems)
have generated a flood of data and information. Advances in
data storage technology such as faster and cheaper storage
devices with higher capacity, better database management
systems, and data warehousing technology have allowed
us to transform this data into “mountains” of stored data.
Such volumes of data and information overwhelm most
traditional manual methods of data analysis such as spread-
sheets, ad-hoc queries, or simple visualizations. The need
for new methods and tools which can intelligently and
(semi-)automatically transform data into information and
furthermore, synthesize knowledge are a core area of the
emerging field of Visual Analytics.
The basic idea of Visual Analytics (Thomas and Cook
2005) is the integration of the outstanding capabilities of
humans in terms of visual information exploration and the
enormous processing power of computers to form a powerful
knowledge discovery environment. Both visual as well
as analytical methods are combined intertwinedly to fully
support this process. Most importantly, the user is not
merely a passive element who interprets the outcome of
visual and analytical methods but she is the core entity who
drives the whole process.
Time is an important data dimension that is common
across many application domains, like transport, call cen-
ters, retail, production, health care, police, or financial
services as well as for research in medicine, biology, and
economics. Particularly, in the area of simulation systems,
time is central to simulating dynamic system behavior as
reflected by Robinson in his definition of computer-based
dynamic simulation as being “an imitation (on a computer)
of a system as it progresses through time” (Robinson 2004).
Exploring trends, patterns, and relationships are particularly
important tasks when dealing with time-oriented data and
information. In contrast to other quantitative data dimen-
sions that are usually “flat”, time has an inherent semantic
structure which increases its complexity dramatically. The
hierarchical structure of granularities in time, as for exam-
ple minutes, hours, days, weeks, months, is unlike most
other quantitative dimensions. Specifically, time comprises
different forms of divisions (e.g., 60 minutes resemble one
hour while 24 hours resemble one day) and granularities are
combined to form calendar systems (e.g., Gregorian, Julian,
Business, or Academic calendars). Moreover, time contains
natural cycles and re-occurrences, as for example seasons,
but also social–somehow irregular–cycles, like holidays or
school breaks. Therefore, time-oriented data need to be
721 1-4244-1306-0/07/$25.00 ©2007 IEEE