• Publikationen
Show publication details

Ruppert, Tobias; Bannach, Andreas; Bernard, Jürgen; Lokanc, Martin; Kohlhammer, Jörn

Visual Access to Performance Indicators in the Mining Sector

2017

Kozlíková, Barbora (Ed.) et al.: Eurographics / IEEE VGTC Conference on Visualization (EuroVis) - Short Papers. Goslar: Eurographics Association, 2017, pp. 157-161

Eurographics / IEEE VGTC Conference on Visualization (EuroVis) <19, 2017, Barcelona, Spain>

We introduce a visualization system that provides visual interactive access to information relevant for decision making in the mining sector. The mining sector is one of the most important industries in developing countries, especially in Africa. Stakeholders like governments, investors, and the civil society play an important role in the growth of the mining sector. They are interested in information reviewing individual country performances towards mining. The Mining Investment and Governance Review (MInGov) dataset explicitly addresses this issue. However, the complex data structure introduces challenges for the intuitive and easy understanding of the information. Together with mining sector experts, we conducted a design study with the goal to provide visual interactive access to investment- and policy-related information. We report on a domain characterization of the MInGov dataset, its potential users, and their tasks. Based on this analysis, we design a visualization system that supports mining-related decision making. Finally, we evaluate the visualization system in a user workshop with domain experts.

Show publication details

Ruppert, Tobias; Staab, Michael; Bannach, Andreas; Lücke-Tieke, Hendrik; Bernard, Jürgen; Kuijper, Arjan; Kohlhammer, Jörn

Visual Interactive Creation and Validation of Text Clustering Workflows to Explore Document Collections

2017

Wischgoll, Thomas (Ed.) et al.: Visualization and Data Analysis 2017. Springfield: IS&T, 2017. (Electronic Imaging), pp. 46-57

Visualization and Data Analysis (VDA) <2017, Burlingame, CA, USA>

The exploration of text document collections is a complex and cumbersome task. Clustering techniques can help to group documents based on their content for the generation of overviews. However, the underlying clustering workflows comprising preprocessing, feature selection, clustering algorithm selection and parameterization offer several degrees of freedom. Since no "best" clustering workflow exists, users have to evaluate clustering results based on the data and analysis tasks at hand. In our approach, we present an interactive system for the creation and validation of text clustering workflows with the goal to explore document collections. The system allows users to control every step of the text clustering workflow. First, users are supported in the feature selection process via feature selection metrics-based feature ranking and linguistic filtering (e.g., part-of-speech filtering). Second, users can choose between different clustering methods and their parameterizations. Third, the clustering results can be explored based on the cluster content (documents and relevant feature terms), and cluster quality measures. Fourth, the results of different clusterings can be compared, and frequent document subsets in clusters can be identified. We validate the usefulness of the system with a usage scenario describing how users can explore document collections in a visual and interactive way.

Show publication details

Ruppert, Tobias; Bannach, Andreas; Bernard, Jürgen; Lücke-Tieke, Hendrik; Ulmer, Alex; Kohlhammer, Jörn

Supporting Collaborative Political Decision Making - An Interactive Policy Process Visualization System

2016

Kerren, Andreas (Ed.) et al.: Proceedings of the 9th International Symposium on Visual Information Communication and Interaction : INCI 2016 [online]. ACM, 2016, 8 p.

International Symposium on Visual Information Communication and Interaction (VINCI 2016) < 9, 2016, Dallas, Texas>

The process of political decision making is often complex and tedious. The policy process consists of multiple steps, most of them are highly iterative. In addition, different stakeholder groups are involved in political decision making and contribute to the process. A series of textual documents accompanies the process. Examples are official documents, discussions, scientific reports, external reviews, newspaper articles, or economic white papers. Experts from the politi- cal domain report that this plethora of textual documents often exceeds their ability to keep track of the entire policy process. We present PolicyLine, a visualization system that supports different stakeholder groups in overview-and-detail tasks for large sets of textual documents in the political decision making process. In a longitudinal design study conducted together with domain experts in political decision making, we identfied missing analytical functionality on the basis of a problem and domain characterization. In an iterative design phase, we created PolicyLine in close collaboration with the domain experts. Finally, we present the results of three evaluation rounds, and reect on our collaborative visualization system.

Show publication details

Bernard, Jürgen; Sessler, David; Bannach, Andreas; May, Thorsten; Kohlhammer, Jörn

A Visual Active Learning System for the Assessment of Patient Well-Being in Prostate Cancer Research

2015

Gschwandtner, Theresia (Conference Chair) et al.: Proceedings of the 2015 Workshop on Visual Analytics in Healthcare. New York: ACM, 2015, Art. 1, 8 p.

Workshop in Visual Analytics in Healthcare (VAHC) <2015, Chicago, IL, USA>

The assessment of patient well-being is highly relevant for the early detection of diseases, for assessing the risks of therapies, or for evaluating therapy outcomes. The knowledge to assess a patient's well-being is actually tacit knowledge and thus, can only be used by the physicians themselves. The rationale of this research approach is to use visual interfaces to capture the mental models of experts and make them available more explicitly. We present a visual active learning system that enables physicians to label the well-being state of patient histories su ering prostate cancer. The labeled instances are iteratively learned in an active learning approach. In addition, the system provides models and visual interfaces for a) estimating the number of patients needed for learning, b) suggesting meaningful learning candidates and c) visual feedback on test candidates. We present the results of two evaluation strategies that prove the validity of the applied model. In a representative real-world use case, we learned the feedback of physicians on a data collection of more than 16.000 prostate cancer histories.

Show publication details

May, Thorsten; Bannach, Andreas; Davey, James; Ruppert, Tobias; Kohlhammer, Jörn

Guiding Feature Subset Selection with an Interactive Visualization

2011

Miksch, Silvia (Ed.) et al.: IEEE Conference on Visual Analytics Science and Technology 2011. Proceedings : VAST 2011. New York: IEEE Press, 2011, pp. 111-120

IEEE Symposium on Visual Analytics Science and Technology (VAST) <6, 2011, Providence, RI, USA>

We propose a method for the semi-automated refinement of the results of feature subset selection algorithms. Feature subset selection is a preliminary step in data analysis which identifies the most useful subset of features (columns) in a data table. So-called filter techniques use statistical ranking measures for the correlation of features. Usually a measure is applied to all entities (rows) of a data table. However, the differing contributions of subsets of data entities are masked by statistical aggregation. Feature and entity subset selection are, thus, highly interdependent. Due to the difficulty in visualizing a high-dimensional data table, most feature subset selection algorithms are applied as a black box at the outset of an analysis. Our visualization technique, SmartStripes, allows users to step into the feature subset selection process. It enables the investigation of dependencies and interdependencies between different feature and entity subsets. A user may even choose to control the iterations manually, taking into account the ranking measures, the contributions of different entity subsets, as well as the semantics of the features.