34-Issue 3
Permanent URI for this collection
Browse
Browsing 34-Issue 3 by Subject "General"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Data-driven Evaluation of Visual Quality Measures(The Eurographics Association and John Wiley & Sons Ltd., 2015) Sedlmair, Michael; Aupetit, Michael; H. Carr, K.-L. Ma, and G. SantucciVisual quality measures seek to algorithmically imitate human judgments of patterns such as class separability, correlation, or outliers. In this paper, we propose a novel data-driven framework for evaluating such measures. The basic idea is to take a large set of visually encoded data, such as scatterplots, with reliable human ''ground truth'' judgements, and to use this human-labeled data to learn how well a measure would predict human judgements on previously unseen data. Measures can then be evaluated based on predictive performance-an approach that is crucial for generalizing across datasets but has gained little attention so far. To illustrate our framework, we use it to evaluate 15 state-of-the-art class separation measures, using human ground truth data from 828 class separation judgments on color-coded 2D scatterplots.Item Visual Analytics for Exploring Local Impact of Air Traffic(The Eurographics Association and John Wiley & Sons Ltd., 2015) Buchmüller, Juri; Janetzko, Halldor; Andrienko, Gennady; Andrienko, Natalia; Fuchs, Georg; Keim, Daniel A.; H. Carr, K.-L. Ma, and G. SantucciThe environmental and noise impact of airports often causes extensive political discussion which in some cases even lead to transnational tensions. Analyzing local approach and departure patterns around an airport is difficult since it depends on a variety of complex variables like weather, local and general regulations and many more. Yet, understanding these movements and the expected amount of flights during arrival and departure is of great interest to both casual and expert users, as planes have a higher impact on the areas beneath during these phases. We present a Visual Analytics framework that enables users to develop an understanding of local flight behavior through visual exploration of historical data and interactive manipulation of prediction models with direct feedback, as well as a classification quality visualization using a random noise metaphor. We showcase our approach using real world data from the Zurich International Airport region, where aircraft noise has led to an ongoing conflict between Germany and Switzerland. The use cases, findings and expert feedback demonstrate how our approach helps in understanding the situation and to substantiate the otherwise often subjective discourse on the topic.