EuroVA17

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2631436

Browse

Now showing 1 - 14 of 14

Visual Analysis of Optical Coherence Tomography Data in Ophthalmology
(The Eurographics Association, 2017) Röhlig, Martin; Rosenthal, Paul; Schmidt, Christoph; Schumann, Heidrun; Stachs, Oliver; Michael Sedlmair and Christian Tominski
Optical coherence tomography (OCT) enables noninvasive high-resolution 3D imaging of the human retina and thus, plays a fundamental role in detecting a wide range of ocular diseases. Despite OCT's diagnostic value, managing and analyzing resulting data is challenging. We apply two visual analytics strategies for supporting retinal assessment in practice. First, we provide an interface for unifying and structuring data from different sources into a common basis. Fusing that basis with medical records and augmenting it with analytically derived information facilitates thorough investigations. Second, we present a tailored visual analysis tool for presenting, selecting, and emphasizing different aspects of the attributed data. This enables free exploration, reducing the data to relevant subsets, and focusing on details. By applying both strategies, we effectively enhance the management and the analysis of OCT data for assisting medical diagnoses.
Visual Comparative Case Analytics
(The Eurographics Association, 2017) Sacha, Dominik; Jentner, Wolfgang; Zhang, Leishi; Stoffel, Florian; Ellis, Geoffrey; Michael Sedlmair and Christian Tominski
Criminal Intelligence Analysis (CIA) faces a challenging task in handling high-dimensional data that needs to be investigated with complex analytical processes. State-of-the-art crime analysis tools do not fully support interactive data exploration and fall short of computational transparency in terms of revealing alternative results. In this paper we report our ongoing research into providing the analysts with such a transparent and interactive system for exploring similarities between crime cases. The system implements a computational pipeline together with a visual platform that allows the analysts to interact with each stage of the analysis process and to validate the result. The proposed Visual Analytics (VA) workflow iteratively supports the interpretation of obtained clustering results, the development of alternative models, as well as cluster verification. The visualizations offer a usable way for the analyst to provide feedback to the system and to observe the impact of their interactions.
Visual Analysis of Geo-spatial Data in 3D Terrain Environments using Focus+Context
(The Eurographics Association, 2017) Richter, Christian; Dübel, Steve; Schumann, Heidrun; Michael Sedlmair and Christian Tominski
Visual analysis of geo-spatial data represented within a three-dimensional frame of reference is a challenging task. Focus+ Context is a common concept that aids this process. This paper addresses the question, how Focus+Context can be applied to a visualization of multivariate weather data along with 3D terrain data. For this purpose, the focus can be specified with regard to both, the terrain and the weather data, utilizing different strategies. Based on the specified focus, the associated context is derived automatically. Data within focus is emphasized, whereas context information is shown with less detail. To this end, various rendering strategies are proposed. We demonstrate our approach by several examples that were generated by the Focus+Context functionality of our visual analytics tool TedaVis.
A Unified Process for Visual-Interactive Labeling
(The Eurographics Association, 2017) Bernard, Jürgen; Zeppelzauer, Matthias; Sedlmair, Michael; Aigner, Wolfgang; Michael Sedlmair and Christian Tominski
Assigning labels to data instances is a prerequisite for many machine learning tasks. Similarly, labeling is applied in visualinteractive analysis approaches. However, the strategies for creating labels often differ in the two fields. In this paper, we study the process of labeling data instances with the user in the loop, from both the machine learning and visual-interactive perspective. Based on a review of differences and commonalities, we propose the 'Visual-Interactive Labeling' (VIAL) process, conflating the strengths of both. We describe the six major steps of the process and highlight their related challenges.
Guidance for Multi-Type Entity Graphs from Text Collections
(The Eurographics Association, 2017) Müller, Martin; Ballweg, Kathrin; Landesberger, Tatiana von; Yimam, Seid; Fahrer, Uli; Biemann, Chris; Rosenbach, Marcel; Regneri, Michaela; Ulrich, H.; Michael Sedlmair and Christian Tominski
The visual exploration of graphs encoding relationships between entities of multiple types (e.g., persons, locations,...) supports journalists in finding newsworthy information in large text collections. Journalists may have interest in certain entity types or their relations such as locations or person-person relations. This interest may change during the exploration process. The exploration of such large graphs is often supported by guidance using a degree-of-interest (DOI) function. Although many DOIs exist, they do not differentiate entity types, rely on additional data, or require complex settings overburding the journalists. We present a novel DOI for graphs with multiple types of entities. We show the interesting subgraph around the focal node and offer information about possible further steps. The user can interactively set her interest in entity types and entity relations. We apply our approach to a graph extracted from WikiLeaks PlusD Cablegate documents and report on journalists' feedback.
Feature Alignment for the Analysis of Verbatim Text Transcripts
(The Eurographics Association, 2017) Jentner, Wolfgang; El-Assady, Mennatallah; Gipp, Bela; Keim, Daniel A.; Michael Sedlmair and Christian Tominski
In the research of deliberative democracy, political scientists are interested in analyzing the communication models of discussions, debates, and mediation processes with the goal of extracting reoccurring discourse patterns from the verbatim transcripts of these conversations. To enhance the time-exhaustive manual analysis of such patterns, we introduce a visual analytics approach that enables the exploration and analysis of repetitive feature patterns over parallel text corpora using feature alignment. Our approach is tailored to the requirements of our domain experts. In this paper, we discuss our visual design and workflow, and we showcase the applicability of our approach using an experimental parallel corpus of political debates.
Visual Analytics for Information Retrieval Evaluation Campaigns
(The Eurographics Association, 2017) Angelini, Marco; Ferro, Nicola; Santucci, Giuseppe; Silvello, Gianmaria; Michael Sedlmair and Christian Tominski
Information Retrieval (IR) has been deeply rooted in experimentation since its inception, allowing researchers and developers to understand the behavior and interactions within increasingly complex IR systems, such as web search engines, which have to address ever increasing user needs and support challenging tasks. This paper focuses on the innovative Visual Analytics (VA) approach realized by the Participative Research labOratory for Multimedia and Multilingual Information Systems Evaluation (PROMISE) environment, which simplifies and makes more effective the experimental evaluation process by allowing a formal and structured way to explore the complex data set of measures produced along an evaluation campaign. The system uses the result produced within the Conference and Labs of the Evaluation Forum (CLEF) [Cle].
Combining Cluster and Outlier Analysis with Visual Analytics
(The Eurographics Association, 2017) Bernard, Jürgen; Dobermann, Eduard; Sedlmair, Michael; Fellner, Dieter W.; Michael Sedlmair and Christian Tominski
Cluster and outlier analysis are two important tasks. Due to their nature these tasks seem to be opposed to each other, i.e., data objects either belong to a cluster structure or a sparsely populated outlier region. In this work, we present a visual analytics tool that allows the combined analysis of clusters and outliers. Users can add multiple clustering and outlier analysis algorithms, compare results visually, and combine the algorithms' results. The usefulness of the combined analysis is demonstrated using the example of labeling unknown data sets. The usage scenario also shows that identified clusters and outliers can share joint areas of the data space.
How Sensemaking Tools Influence Display Space Usage
(The Eurographics Association, 2017) Geymayer, Thomas; Waldner, Manuela; Lex, Alexander; Schmalstieg, Dieter; Michael Sedlmair and Christian Tominski
We explore how the availability of a sensemaking tool influences users' knowledge externalization strategies. On a large display, users were asked to solve an intelligence analysis task with or without a bidirectionally linked concept-graph (BLC) to organize insights into concepts (nodes) and relations (edges). In BLC, both nodes and edges maintain links to the exact source phrases and sections in associated documents. In our control condition, we were able to reproduce previously described spatial organization behaviors using document windows on the large display. When using BLC, however, we found that analysts apply spatial organization to BLC nodes instead, use significantly less display space and have significantly fewer open windows.
EuroVA 2017: Frontmatter
(Eurographics Association, 2017) Sedlmair, Michael; Tominski, Christian;
A Visual Analytics Approach for User Behaviour Understanding through Action Sequence Analysis
(The Eurographics Association, 2017) Nguyen, Phong H.; Turkay, Cagatay; Andrienko, Gennady; Andrienko, Natalia; Thonnard, Olivier; Michael Sedlmair and Christian Tominski
Analysis of action sequence data provides new opportunities to understand and model user behaviour. Such data are often in the form of timestamped and labelled series of atomic user actions. Cyber security is one of the domains that show the value of the analysis of these data. Elaborate and specialised models of user-behaviour are desired for effective decision making during investigation of cyber threats. However, due to their complex nature, activity sequences are not yet well-exploited within cyber security systems. In this paper, we describe the initial phases of a visual analytics approach that aims to enable a rich understanding of user behaviour through the analysis of user activity sequences. First, we discuss a motivating case study and discuss a number of high level requirements as derived from a series of workshops within an ongoing research project. We then present the components of a visual analytics approach that constitutes a novel combination of ''action space'' analysis, pattern mining, and the interactive visual analysis of multiple sequences to take the initial steps towards a comprehensive understanding of user behaviour.
PipeVis: Interactive Visual Exploration of Pipeline Incident Data
(The Eurographics Association, 2017) Sahaf, Zahra; Marbouti, Mahshid; Mota, Roberta Cabral; Alemasoom, Haleh; Maurer, Frank; Sousa, Mario Costa; Michael Sedlmair and Christian Tominski
The fatal hazards associated with pipeline incidents as well as their frequent occurrence motivate pipeline analysts to learn from historical events and to use that information to prevent future ones by taking proper action. However, the incredible wealth of information contained in pipeline incidents data sets makes it considerably challenging to explore such data. Our solution comprises a visual exploration prototype that aims to help pipeline analysts overcome these difficulties. In this sense, it applies different visual analytical and exploration techniques over the raw pipeline incident data to uncover hidden patterns, unknown correlations, tendencies, and other meaningful information. In that regard, we implemented a prototype which consists of four different views that user can with: a map view that provides spatial information, a chart view that highlights tendencies, a Parallel Coordinates view that discloses hidden patterns and a decision tree view that extracts crucial rules and relations in data.
Visual Analytics for Multitemporal Aerial Image Georeferencing
(The Eurographics Association, 2017) Amor-Amorós, Albert; Federico, Paolo; Miksch, Silvia; Zambanini, Sebastian; Brenner, Simon; Sablatnig, Robert; Michael Sedlmair and Christian Tominski
Georeferencing of multitemporal aerial imagery is a time-consuming and challenging task that typically requires a high degree of human intervention, and which appears in application domains of critical importance, like unexploded ordnance detection. In order to make a semi-automatic scenario possible, we introduce a Visual Analytics approach for multitemporal aerial image georeferencing designed in close collaboration with real-world analysts that face the problem on a daily basis, and implemented by combining computer vision and interactive visual exploration methods. We report on informal validation findings resulting from the integration of our solution into our users' GIS platform of choice, which positively illustrate its effectiveness and time-saving potential.
Subpopulation Discovery and Validation in Epidemiological Data
(The Eurographics Association, 2017) Alemzadeh, Shiva; Hielscher, Tommy; Niemann, Uli; Cibulski, Lena; Ittermann, Till; Völzke, Henry; Spiliopoulou, Myra; Preim, Bernhard; Michael Sedlmair and Christian Tominski
Motivated by identifying subpopulations that share common characteristics (e.g. alcohol consumption) to explain risk factors of diseases in cohort study data, we used subspace clustering to discover such subpopulations. In this paper, we describe our interactive coordinated multiple view system Visual Analytics framework S-ADVIsED for SubpopulAtion Discovery and Validation In Epidemiological Data. S-ADVIsED enables epidemiologists to explore and validate findings derived from subspace clustering. We investigated the replication of a selected subpopulation in an independent population.

Browse

Browsing EuroVA17 by Issue Date

Results Per Page

Sort Options