We are proud to be presenting two posters at IEEE InfoVis in Berlin this year. Mandy Keck, Dietrich Kammer, and Rainer Groh present Visual Version Comparison of Multidimensional Data Sets using Glyphs. When working with a given high-dimensional data set, data analysts often use different machine-learning algorithms to calculate clusters and classifications. However, it is difficult to ascertain which differences occur across these algorithm versions. For a human-readable visualization, dimensionality reduction methods are used to achieve two-dimensional mappings. In previous work, we proposed to use glyphs to support analysis tasks in these two-dimensional plots. In this paper, we investigate novel glyph-based strategies that can be used for comparison tasks. We present two interface concepts that can be applied on fixed and varying position data to compare different versions of machine-learning algorithms.
Mandy Keck, Alexander Maasch, Romy Bürger chemmedia, and Rainer Groh address Visualizing Learning Experiences Using Conversation Flows. Conversation training is an e-learning method for the transfer of communication-related skills. With the increasing complexity of these conversations, such as length or structure, combined with the number of learners, the evaluation and analysis of the resulting data set become a challenging task. In this paper, we present a visualization approach based on Sankey diagrams that allows the analysis of complex conversation training data sets.
Dietrich Kammer and Mandy Keck from the VANDA project team were involved in conducting the Workshop on Visual Interfaces for Big Data Environments in Industrial Applications at AVI 2018 on 29 May 2018. The workshop was part of the International Conference on Advanced Visual Interfaces (AVI 2018) in Castiglione della Pescaia (Italy). The target of this workshop were Visual Big Data Interfaces in industrial contexts such as e-commerce, e-learning and business intelligence. We addressed interfaces for three different user groups: data scientists, data workers and end users. The workshop was well-attended and offered a forum for discussing the presented position papers as well as general research questions and solutions in industrial applications. The project members from the VANDA team attending the conference enjoyed all of the talks and gained new insights into current visualization research. The proceedings of the workshop including all of the presented papers is available online at the archival website CEUR-WS.org. More Information is available on the workshop website.
Alexander Maasch from project partner chemmedia AG also presented research concerning the visualization of conversation training data. Conversation training is an e-learning method designed for the transfer of communication-related skills. With increasing conversation length and number of learners, creating and evaluating conversations becomes a complex task that needs appropriate visual guidance and data visualization. This paper shows the inherent complexities of conversation trainings and guides through an approach that eases the conversation creation. In the talk, we explained data collection with Experience API and finally we presented a Sankey Diagrams based approach to visualize large amounts of collected learning data.
A poster with research from the VANDA project about Big Data Landscapes was discussed with the international audience at the International Conference on Advanced Visual Interfaces (AVI 2018) at Castiglione della Pescaia, Grosseto (Italy) on 30 May 2018 during the poster session.
The VANDA team seized the opportunity to present the current research of the project at the 20th installation of the Round Table of Visual Engineering (Runder Tisch der Technischen Visualistik). The event was entitled “Learning in a Sea of Data” and was opened by Prof. Rainer Groh, who looked back on the 19 prior events. In the introductory talk, Dietrich Kammer and Mandy Keck addressed the foundations of Visual Analytics Interfaces for Big Data Environments.
The Chair for Media Design at Technische Universität Dresden invites the general public to participate in a round table discussion with the project partners. The event is the 20th installation of the Round Table of Visual Engineering (Runder Tisch der Technischen Visualistik) and will be opened by Prof. Rainer Groh, who will look back on the 19 prior events.
We want to discuss the project topics with researchers and practitioners. First, we introduce the challenges associated with Visual Analytics Interfaces for Big Data Environments. Second, the industrial partners will give short introductory talks outlining their use cases and visualization approaches. Further discussion will take place during a poster session and a small catering for all guests.
The workshop targets Visual Big Data Interfaces in industrial contexts such as e-commerce, e-learning and business intelligence. It addresses interfaces for three different user groups: data scientists, data workers and end users. The workshop is intended to provide a forum for discussing research questions and solutions in industrial applications.
On Sunday, 10th of September, Dietrich Kammer presented the paper „Exploring Big Data Landscapes with Elastic Displays” at the main german conference on Human-Computer Interaction „Mensch und Computer“ in Regensburg, Germany. The conference is organized by the German Informatics Society (Gesellschaft für Informatik e.V. (GI)), which is a non-profit organization with about 20,000 members living across the world. The talk was part of the workshop on Tangible Interaction („Be-greifbare Interaktion“), which was held at the conference for the 10th time. The topic was how novel interaction technologies can assist data analysts in optimizing their clustering algorithms by adapting parameters with instant visual and haptic feedback.