Application Areas and Software Solutions




Eye Movement Studies

Even though a focus of our research is on visual analysis of physical-world movement, our developed methodologies are useful in application areas with rather different kinds of moves:

 

Visual Analytics Methodology for Eye Movement Studies
Gennady Andrienko, Natalia Andrienko, Michael Burch, Daniel Weiskopf
IEEE Transactions on Visualization and Computer Graphics,
vol. 18(12), pp.2889-2898, Dec. 2012
(IEEE VAST 2012 best paper)

 

Eye movement analysis is gaining popularity as a tool for evaluation of visual displays and interfaces. However, the existing methods and tools for analyzing eye movements and scan paths are limited in terms of the tasks they can support and their effectiveness for large and high-variation data.

We have performed an extensive empirical evaluation of a broad range of visual analytics methods originally devised for analysis of geographic movement data. The methods have been tested for the applicability to eye tracking data and the capability to extract useful knowledge about users' viewing behaviors. This allowed us to select the suitable methods and match them to possible analysis tasks they can support.

The paper describes how the methods work in application to eye tracking data and provides guidelines for method selection depending on the analysis tasks.

 

Find more information on the paper's web site which contains

  • Illustrated guidelines for selecting eye tracking analysis methods depending on analysis tasks
  • Enlarged figures from the paper with extended explanations
  • Methods that have not been included in the paper
  • Methodology of the empirical study and data that were used for it
  • Data for download

Traffic Modelling and Simulation

To support analysis and modelling of large amounts of spatio-temporal data having the form of spatially referenced time series (TS) of numeric values, we combine interactive visual techniques with computational methods from machine learning and statistics.

One application area were such data is encountered in massive quantities is the analysis, evaluation and prediction of regional (e.g., city-wide) traffic volumes based on positional records (e.g., GPS tracks).

We developed a visual analytics toolkit for data-driven modelling and simulation of constrained traffic. This framework includes interactive visual interfaces to a library of modelling methods, supports the selection of a suitable method, adjustment of model parameters, and evaluation of constructed traffic volume models. Subsequently, these models can be used to simulate traffic flows and predict traffic situations, thus providing planers with a valuable, visual-interactive tool for their needs.

 

This website contains a five-minute video explaining the analysis procedure. The framework demonstrator is based on the following papers:

  •  N. Andrienko, G. Andrienko.
    Spatial Generalization and Aggregation of Massive Movement Data.
    IEEE Transactions on Visualization and Computer Graphics, 2011, v.17(2), pp.205-219.
  • N. Andrienko, G. Andrienko.
    A Visual Analytics Framework for Spatio-temporal Analysis and Modelling.
    Data Mining and Knowledge Discovery, 2013, v.27(1), pp.55-83.

Online geospatial VA with GeoTempCo

Flickr and Twitter, digital libraries and archives are examples of huge collections with spatial and temporal metadata. Today's browsing and search options hardly help to orient oneself in these assets, to overview a particular topic, and to recognize spatial, temporal and thematic structures.

GeoTemCo facilitates such investigations. This interactive web application offers a map, a timeline and other synchronized graphics in order to analyze different aspects in a number of hits.

GeoTemCo is an open-source software, which we have elaborated for the German Digital Library, for biodiversity research and for business applications.