EuroVA2023

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2633347

Browse

Now showing 1 - 10 of 10

ChatKG: Visualizing Temporal Patterns as Knowledge Graph
(The Eurographics Association, 2023) Christino, Leonardo; Paulovich, Fernando V.; Angelini, Marco; El-Assady, Mennatallah
Line-chart visualizations of temporal data enable users to identify interesting patterns for the user to inquire about. Using oracles, such as chat AIs, Visual Analytic tools can automatically uncover explicit knowledge related information to said patterns. Yet, visualizing the association of data, patterns, and knowledge is not straightforward. In this paper, we present ChatKG, a novel visualization strategy that allows exploratory data analysis of a Knowledge Graph which associates a dataset of temporal sequences, the patterns found in each sequence, the temporal overlap between patterns, and related explicit knowledge to each given pattern. We exemplify and informally evaluate ChatKG by analyzing the world's life expectancy. For this, we implement an oracle that automatically extracts relevant or interesting patterns, inquires chatGPT for related information, and populates the Knowledge Graph which is visualized. Our tests and an interview conducted showed that ChatKG is well suited for temporal analysis of temporal patterns and their related knowledge when applied to history studies.
Extracting Movement-based Topics for Analysis of Space Use
(The Eurographics Association, 2023) Andrienko, Gennady; Andrienko, Natalia; Hecker, Dirk; Angelini, Marco; El-Assady, Mennatallah
We present a novel approach to analyze spatio-temporal movement patterns using topic modeling. Our approach represents trajectories as sequences of place visits and moves, applies topic modeling separately to each collection of sequences, and synthesizes results. This supports the identification of dominant topics for both place visits and moves, the exploration of spatial and temporal patterns of movement, enabling understanding of space use. The approach is applied to two real-world data sets of car movements in Milan and UK road traffic, demonstrating the ability to uncover meaningful patterns and insights.
KidCAD: An Interactive Cohort Analysis Dashboard of Patients with Chronic Kidney Diseases
(The Eurographics Association, 2023) Höhn, Markus; Schwindt, Sarah; Hahn, Sara; Patyna, Sammy; Büttner, Stefan; Kohlhammer, Jörn; Angelini, Marco; El-Assady, Mennatallah
Chronic Kidney Diseases (CKD) are a prominent health problem. With an ongoing process, CKD leads to impaired kindey function with decreased ability to filter the patients' blood, concluding in multiple complications, like heart disease and finally death. We developed a prototype to support nephrologists to gain an overview of their CKD patients. The prototype visualizes the patients in cohorts according to their pairwise similarity. The user can interactively modify the similarity by changing the underlying weights of the included features. The prototype was developed in response to the needs of physicians due to a context of use analysis. A qualitative user study shows the need and suitability of our new approach.
A Methodology for Task-Driven Guidance Design
(The Eurographics Association, 2023) Pérez-Messina, Ignacio; Ceneda, Davide; Miksch, Silvia; Angelini, Marco; El-Assady, Mennatallah
Mixed-initiative Visual Analytics (VA) systems are becoming increasingly important; however, the design of such systems still needs to be formulated. We present a methodology to aid and structure the design of guidance for mixed-initiative VA systems consisting of four steps: (1) defining the target of analysis, (2) identifying the user search tasks, (3) describing the system guidance tasks, and (4) specifying which and when guidance is provided. In summary, it specifies a space of possible user tasks and then maps it to the corresponding space of guidance tasks, using recent VA task typologies for guidance and visualizations. We illustrate these steps through a case study in a real-world model-building task involving decision-making with unevenlyspaced time-oriented data. Our methodology's goal is to enrich existing VA systems with guidance, being its output a structured description of a complex guidance task schema.
Multi-Ensemble Visual Analytics via Fuzzy Sets
(The Eurographics Association, 2023) Piccolotto, Nikolaus; Bögl, Markus; Miksch, Silvia; Angelini, Marco; El-Assady, Mennatallah
Analysis of ensemble datasets, i.e., collections of complex elements such as geochemical maps, is widespread in science and industry. The elements' complexity arises from the data they capture, which are often multivariate or spatio-temporal. We speak of multi-ensemble datasets when the analysis pertains to multiple ensembles. While many visualization approaches were suggested for ensemble datasets, multi-ensemble datasets remain comparatively underexplored. Our years-long collaboration with statisticians and geochemists taught us that they frame many questions about multi-ensemble data as set operations. E.g., what are the most common members (intersection of ensembles), or what features exist in one member but not another (difference of members)? As classical crisp set relations cannot account for the elements' complexity, we propose to model multi-ensembles as fuzzy relations. We provide examples of fuzzy set-based queries on a multi-ensemble of geochemical maps and integrate this approach into an existing ensemble visualization pipeline. We evaluated two visualizations obtained by applying this pipeline with experts in geochemistry and statistics. The experts confirmed known information and got directions for further research, which is one Visual Analytics (VA) goal. Hence, our proposal is highly promising for an interactive VA approach.
Nonparametric Dimensionality Reduction Quality Assessment based on Sortedness of Unrestricted Neighborhood
(The Eurographics Association, 2023) Pereira-Santos, Davi; Neves, Tácito Trindade Araújo Tiburtino; Carvalho, André C. P. L. F. de; Paulovich, Fernando V.; Angelini, Marco; El-Assady, Mennatallah
High-dimensional data are known to be challenging to explore visually. Dimensionality Reduction (DR) techniques are good options for making high-dimensional data sets more interpretable and computationally tractable. An inherent question regarding their use is how much relevant information is lost during the layout generation process. In this study, we aim to provide means to quantify the quality of a DR layout according to the intuitive notion of sortedness of the data points. For such, we propose a straightforward measure with Kendall t at its core to provide values in a standard and meaningful interval. We present sortedness and pairwise sortedness as suitable replacements over, respectively, trustworthiness and stress when assessing projection quality. The formulation, its rationale and scope, and experimental results show their strength compared to the state-of-the-art.
A Practical Approach to Provenance Capturing for Reproducible Visual Analytics at an Ocean Research Institute
(The Eurographics Association, 2023) Bernstetter, Armin; Kwasnitschka, Tom; Peters, Isabella; Angelini, Marco; El-Assady, Mennatallah
Reproducibility - and the lack thereof - has been an important topic for some time in the field of Human-Computer Interaction. Visual analytics workflows and in extension immersive analytics workflows are no exception there and benefit from being more transparent and reproducible. At our research institute, domain scientists in ocean research are using interactive visualization workflows for sensemaking processes. We are building a framework that supports these workflows by shifting the focus from solely lying on the end-product (i.e. published insights and visualizations) towards the generation process. We do this by capturing, organizing, and visualizing provenance artifacts using a modular and extensible web-based application. We not only apply this framework to conventional 2D display-based work but also workflows inside a unique and spatially immersive projection dome.
Scaling Up the Explanation of Multidimensional Projections
(The Eurographics Association, 2023) Thijssen, Julian; Tian, Zonglin; Telea, Alexandru; Angelini, Marco; El-Assady, Mennatallah
We present a set of interactive visual analysis techniques aiming at explaining data patterns in multidimensional projections. Our novel techniques include a global value-based encoding that highlights point groups having outlier values in any dimension as well as several local tools that provide details on the statistics of all dimensions for a user-selected projection area. Our techniques generically apply to any projection algorithm and scale computationally well to hundreds of thousands of points and hundreds of dimensions. We describe a user study that shows that our visual tools can be quickly learned and applied by users to obtain non-trivial insights in real-world multidimensional datasets.
ShaRP: Shape-Regularized Multidimensional Projections
(The Eurographics Association, 2023) Machado, Alister; Telea, Alexandru; Behrisch, Michael; Angelini, Marco; El-Assady, Mennatallah
Projections, or dimensionality reduction methods, are techniques of choice for the visual exploration of high-dimensional data. Many such techniques exist, each one of them having a distinct visual signature - i.e., a recognizable way to arrange points in the resulting scatterplot. Such signatures are implicit consequences of algorithm design, such as whether the method focuses on local vs global data pattern preservation; optimization techniques; and hyperparameter settings. We present a novel projection technique - ShaRP - that provides users explicit control over the visual signature of the created scatterplot, which can cater better to interactive visualization scenarios. ShaRP scales well with dimensionality and dataset size, generically handles any quantitative dataset, and provides this extended functionality of controlling projection shapes at a small, user-controllable cost in terms of quality metrics.
A Visual Analytics Framework for Renewable Energy Profiling and Resource Planning
(The Eurographics Association, 2023) Pammi, Ramakrishna P.; Afzal, Shehzad; Dasari, Hari Prasad; Yousaf, Muhammad; Ghani, Sohaib; Venkatraman, Murali Sankar; Hoteit, Ibrahim; Angelini, Marco; El-Assady, Mennatallah
Renewable energy growth is one of the focus areas globally against the backdrop of the global energy crisis and climate change. Energy planners are looking into clean, safe, affordable, and reliable energy generation sources for a net zero future. Countries are setting energy targets and policies prioritizing renewable energy, shifting the dependence on fossil fuels. The selection of renewable energy sources depends on the suitability of the region under consideration and requires analyzing relevant environmental datasets. In this work, we present a visual analytics framework that facilitates users to explore solar and wind energy datasets consisting of Global Horizontal Irradiance (GHI), Direct Normal Irradiance (DNI), Diffusive Horizontal Irradiance (DHI), and Wind Power (WP) spanning across a 40 year period. This framework provides a suite of interactive decision support tools to analyze spatiotemporal patterns, variability in the variables across space and time at different temporal resolutions, Typical Meteorological Year (TMY) data with varying percentiles, and provides the capability to interactively explore and evaluate potential solar and wind energy equipment installation locations and study different energy acquisition scenarios. This work is conducted in collaboration with domain experts involved in sustainable energy planning. Different use case scenarios are also explained in detail, along with domain experts feedback and future directions.

Browse

Browsing EuroVA2023 by Subject "Human centered computing"

Results Per Page

Sort Options