Interaction in visualization is often complicated and tedious. Brushing data in a visualization such as parallel
coordinates is a central part of the data analysis process, and sets visualization apart from static charts. Modifying
a brush, or combining it with another one, usually requires a lot of effort and mode switches, though,
slowing down interaction and even discouraging more complex questions.
We propose the use of multi-touch interaction to provide fast and convenient interaction with parallel coordinates.
By using a multi-touch trackpad rather than the screen directly, the user's hands do not obscure the
visualization during interaction. Using one, two, three, or four fingers, the user can easily and quickly perform
complex selections. Being able to change the selections rapidly, the user can explore the data set more easily
and effectively, and can focus on the data rather than the interaction.
The proliferation of data in the past decade has created demand for innovative tools in different areas of exploratory
data analysis, like data mining and information visualization. However, the problem with real-world
datasets is that many of their attributes can identify individuals, or the data are proprietary and valuable. The
field of data mining has developed a variety of ways for dealing with such data, and has established an entire
subfield for privacy-preserving data mining. Visualization, on the other hand, has seen little, if any, work on
handling sensitive data. With the growing applicability of data visualization in real-world scenarios, the handling
of sensitive data has become a non-trivial issue we need to address in developing visualization tools.
With this goal in mind, in this paper, we analyze the issue of privacy from a visualization perspective and
propose a privacy-preserving visualization technique based on clustering in parallel coordinates. We also outline
the key differences in approach from the privacy-preserving data mining field and compare the advantages and
drawbacks of our approach.
With the increase of terrorist activity around the world, it has become more important than ever to analyze and
understand these activities over time. Although the data on terrorist activities are detailed and relevant, the complexity of
the data has rendered the understanding and analysis difficult. We present a visual analytical approach to effectively
identify related entities such as terrorist groups, events, locations, etc. based on a 2D layout. Our methods are based on
sequence comparison from bioinformatics, modified to incorporate the element of time. By allowing the user the
freedom to link entities by their activities over time, we provide a new framework for comparison of event sequences.
Our scoring mechanism is robust and flexible, giving the user the flexibility to define the extent to which time is
considered in aligning entities. Incorporated with high interactivity, the user can efficiently navigate through tens of
thousands of records recorded in over a hundred dimensions of data by choosing combinations of categories to examine.
Exploration of the terrorist activities in our system reveals relationships between entities that are not easily detectable
using traditional methods.
Conference Committee Involvement (3)
Visualization and Data Analysis 2012
23 January 2012 | Burlingame, California, United States
Visualization and Data Analysis 2011
24 January 2011 | San Francisco Airport, California, United States
Visual Analytics for Homeland Defense and Security