Buchmüller, Juri F.
E-Mail-Adresse
ORCID
Geburtsdatum
Berufsbeschreibung
Nachname
Vorname
Name
Suchergebnisse Publikationen
Stable Visual Summaries for Trajectory Collections
The availability of devices that track moving objects has led to an explosive growth in trajectory data. When exploring the resulting large trajectory collections, visual summaries are a useful tool to identify time intervals of interest. A typical approach is to represent the spatial positions of the tracked objects at each time step via a one-dimensional ordering; visualizations of such orderings can then be placed in temporal order along a time line. There are two main criteria to assess the quality of the resulting visual summary: spatial quality - how well does the ordering capture the structure of the data at each time step, and stability - how coherent are the orderings over consecutive time steps or temporal ranges?In this paper we introduce a new Stable Principal Component (SPC) method to compute such orderings, which is explicitly parameterized for stability, allowing a trade-off between the spatial quality and stability. We conduct extensive computational experiments that quantitatively compare the orderings produced by ours and other stable dimensionality-reduction methods to various state-of-the-art approaches using a set of well-established quality metrics that capture spatial quality and stability. We conclude that stable dimensionality reduction outperforms existing methods on stability, without sacrificing spatial quality or efficiency; in particular, our new SPC method does so at a fraction of the computational costs.
Visual Analytics for Supporting Conflict Resolution in Large Railway Networks
Train operators are responsible for maintaining and following the schedule of large-scale railway transport systems. Disruptions to this schedule imply conflicts that occur when two trains are bound to use the same railway segment. It is upon the train operator to decide which train must go first to resolve the conflict. As the railway transport system is a large and complex network, the decision may have a high impact on the future schedule, further train delay, costs, and other performance indicators. Due to this complexity and the enormous amount of underlying data, machine learning models have proven to be useful. However, the automated models are not accessible to the train operators which results in a low trust in following their predictions. We propose a Visual Analytics solution for a decision support system to support the train operators in making an informed decision while providing access to the complex machine learning models. Different integrated, interactive views allow the train operator to explore the various impacts that a decision may have. Additionally, the user can compare various data-driven models which are structured by an experience-based model. We demonstrate a decision-making process in a use case highlighting how the different views are made use of by the train operator.
Moving Together : Towards a Formalization of Collective Movement
While conventional applications for spatiotemporal datasets mostly focus on the relation between movers and environment, research questions in the analysis of collective movement typically focus more on relationships and dynamics between the moving entities themselves. Instead of concentrating on origin, destination and the way in between, this inter-mover perspective on spatiotemporal data allows to explain how moving groups are coordinating. Yet, only few visualization and Visual Analytics approaches focus on the relationships between movers. To illuminate this research gap, we propose initial steps towards a comprehensive formalization of coordination in collective movement based on temporal autocorrelation of distance matrices derived from basic movement characteristics. We exemplify how patterns can be encoded using autocorrelation cubes and outline the next steps towards an exhaustive formalization of coordination patterns.
RescueMark : Visual Analytics of Social Media Data for Guiding Emergency Response in Disaster Situations Award for Skillful Integration of Language Model
This paper presents RescueMark, a web-based visual analytics tool for analyzing disaster situations and guiding emergency response. In disaster situations operators must take quick and effective decisions to solve critical problems. RescueMark provides spatial, topic and temporal event exploration supporting decision making for resource allocation and determine damaged areas of the city. We describe the data analysis and visualization process of the social media data applied to extract the relevant information.
Assessing 2D and 3D Heatmaps for Comparative Analysis : An Empirical Study
Heatmaps are a popular visualization technique that encode 2D density distributions using color or brightness. Experimental studies have shown though that both of these visual variables are inaccurate when reading and comparing numeric data values. A potential remedy might be to use 3D heatmaps by introducing height as a third dimension to encode the data. Encoding abstract data in 3D, however, poses many problems, too. To better understand this tradeoff, we conducted an empirical study (N=48) to evaluate the user performance of 2D and 3D heatmaps for comparative analysis tasks. We test our conditions on a conventional 2D screen, but also in a virtual reality environment to allow for real stereoscopic vision. Our main results show that 3D heatmaps are superior in terms of error rate when reading and comparing single data items. However, for overview tasks, the well-established 2D heatmap performs better.
Breaking the Curse of Visual Analytics : Accommodating Virtual Reality in the Visualization Pipeline
Previous research has exposed the discrepancy between the subject of analysis (real world) and the actual data on which the analysis is performed (data world) as a critical weak spot in visual analysis pipelines. In this paper, we demonstrate how Virtual Reality (VR) can help to verify the correspondence of both worlds in the context of Information Visualization (InfoVis) and Visual Analytics (VA). Immersion allows the analyst to dive into the data world and collate it to familiar real-world scenarios. If the data world lacks crucial dimensions, then these are also missing in created virtual environments, which may draw the analyst’s attention to inconsistencies between the database and the subject of analysis. When situating VR in a generic visualization pipeline, we can confirm its basic equality compared to other mediums as well as possible benefits. To overcome the guarded stance of VR in InfoVis and VA, we present a structured analysis of arguments, exhibiting the circumstances that make VR a viable medium for visualizations. As a further contribution, we discuss how VR can aid in minimizing the gap between the data world and the real world and present a use case that demonstrates two solution approaches. Finally, we report on initial expert feedback attesting the applicability of our approach in a real-world scenario for crime scene investigation.
Earthquake Investigation and Visual Cognizance of Multivariate Temporal Tabular Data Using Machine Learning
This paper presents our tool for the Vast Challenge 2019 Mini Challenge 1 (MC1). It will give an overview of the approach of data preprocessing techniques used for the given dataset and it will introduce our application which is built considering the requirements and questions to be answered for the MC1. This application consists of Machine Learning techniques and Information Visualization techniques such as Integrated Spatial Uncertainty Visualization as shown in this paper [1] to convey the needed information to the end users. To show the usefulness of this application we give examples of analysis.
MultiSegVA : Using Visual Analytics to Segment Biologging Time Series on Multiple Scales
Segmenting biologging time series of animals on multiple temporal scales is an essential step that requires complex techniques with careful parameterization and possibly cross-domain expertise. Yet, there is a lack of visual-interactive tools that strongly support such multi-scale segmentation. To close this gap, we present our MultiSegVA platform for interactively defining segmentation techniques and parameters on multiple temporal scales. MultiSegVA primarily contributes tailored, visual-interactive means and visual analytics paradigms for segmenting unlabeled time series on multiple scales. Further, to flexibly compose the multi-scale segmentation, the platform contributes a new visual query language that links a variety of segmentation techniques. To illustrate our approach, we present a domain-oriented set of segmentation techniques derived in collaboration with movement ecologists. We demonstrate the applicability and usefulness of MultiSegVA in two real-world use cases from movement ecology, related to behavior analysis after environment-aware segmentation, and after progressive clustering. Expert feedback from movement ecologists shows the effectiveness of tailored visual-interactive means and visual analytics paradigms at segmenting multi-scale data, enabling them to perform semantically meaningful analyses. A third use case demonstrates that MultiSegVA is generalizable to other domains.
Comparative Analysis with Heightmaps in Virtual Reality Environments
3D heightmaps can be considered as an extension of heatmaps using the third dimension to encode the respective value by height, often in addition to encoding it by color. In contrast to 2D heatmaps, 3D heightmaps allow a superposition without aggregation. However, they also have the general disadvantages of 3D visualizations, such as occlusion and perceptual distortion. Previous research has revealed various advantages of stereoscopic displays and virtual reality (VR) in the context of 3D visualizations, for example, concerning memorization, depth perception, and collaboration. In this paper, we present a novel technique to compare heightmaps in VR by introducing a multi-layer approach of stacked heightmaps. We demonstrate the applicability and usefulness of our method by means of a use case on comparative crime data analysis.
N.E.A.T. : Novel Emergency Analysis Tool
We present N.E.A.T. - a Visual Analytics approach to the collaborative management of large-scale emergencies. N.E.A.T. unifies the analysis and annotation of heterogeneous, uncertainty-afflicted data sources in a single, adjustable screen. Stakeholders can create individual or shared workspaces providing configurable views tailored to the needs of different emergency responders. Within each workspace, annotated findings are automatically shared in real-time for effective collaboration. We illustrate the functionality of the tool and showcase exemplary findings on the St. Himark incident.