Josua Krause

Learn More
Predictive modeling techniques are increasingly being used by data scientists to understand the probability of predicted outcomes. However, for data that is high-dimensional, a critical step in predictive modeling is determining which features should be included in the models. Feature selection algorithms are often used to remove non-informative features(More)
Many researchers across diverse disciplines aim to analyze the behavior of cohorts whose behaviors are recorded in large event databases. However, extracting cohorts from databases is a difficult yet important step, often overlooked in many analytical solutions. This is especially true when researchers wish to restrict their cohorts to exhibit a particular(More)
Understanding predictive models, in terms of interpreting and identifying actionable insights, is a challenging task. Often the importance of a feature in a model is only a rough estimate condensed into one number. However, our research goes beyond these naïve estimates through the design and implementation of an interactive visual analytics system,(More)
We report on the observation of γ-rays above 25 GeV from the Crab pulsar (PSR B0532+21) using the MAGIC I telescope. Two data sets from observations during the winter period 2007/2008 and 2008/2009 are used. In order to discuss the spectral shape from 100 MeV to 100 GeV, one year of public Fermi Large Area Telescope (Fermi-LAT) data are also analyzed to(More)
MAGIC is a system of two Imaging Atmospheric Cherenkov Telescopes located in the Canary island of La Palma. Since autumn 2009 both telescopes have been working together in stereoscopic mode, providing a significant improvement with respect to the previous single-telescope observations. We use observations of the Crab Nebula taken at low zenith angles to(More)
It is commonly believed that increasing the inter-pretability of a machine learning model may decrease its predictive power. However, inspecting input-output relationships of those models using visual analytics, while treating them as black-box, can help to understand the reasoning behind outcomes without sacrificing predictive quality. We identify a space(More)
We present a study aimed at understanding how human observers judge scatter plot similarity when presented with a large set of iconic scatter plot representations. The work we present involves 18 participants with a scientific background in a similarity perception study. The study asks participants to group a carefully selected set of plots according to(More)
Figure 1: Visualization of the bus transportation system of Konstanz (Germany) created with BusVis. Left: Geographical layout. Abstract On-line journey planners encourage the use of public transport systems by easing the task of finding " optimal " routes between start and destination locations. Most of the tools lack the flexibility of comparing journeys(More)
  • 1