EuroVA2022
Permanent URI for this collection
Browse
Browsing EuroVA2022 by Subject "Human centered computing"
Now showing 1 - 7 of 7
Results Per Page
Sort Options
Item A Comprehensive Workflow for Effective Imitation and Reinforcement Learning with Visual Analytics(The Eurographics Association, 2022) Metz, Yannick; Schlegel, Udo; Seebacher, Daniel; El-Assady, Mennatallah; Keim, Daniel; Bernard, Jürgen; Angelini, MarcoMultiple challenges hinder the application of reinforcement learning algorithms in experimental and real-world use cases even with recent successes in such areas. Such challenges occur at different stages of the development and deployment of such models. While reinforcement learning workflows share similarities with machine learning approaches, we argue that distinct challenges can be tackled and overcome using visual analytic concepts. Thus, we propose a comprehensive workflow for reinforcement learning and present an implementation of our workflow incorporating visual analytic concepts integrating tailored views and visualizations for different stages and tasks of the workflow.Item CryptoComparator: A Visual Analytics Environment for Cryptocurrencies Analysis(The Eurographics Association, 2022) Conforti, Pietro Manganelli; Emanuele, Matteo; Nardelli, Pietro; Santucci, Giuseppe; Angelini, Marco; Bernard, Jürgen; Angelini, MarcoCryptocurrencies are a novel phenomenon in the finance world that is gaining more attention from the general public, banks, investors, and lately also academic research. A characteristic of cryptocurrencies is to be the target of investments that, due to the volatility of most of the cryptocurrencies, tends to be at high risk and behave very differently from classic currencies. A way of reducing this risk is to look at the history of existing cryptocurrencies and compare them in order to spot promising trends for increased gain. This paper introduces CryptoComparator, a Visual Analytics tool designed for allowing analysis of correlations and trends of cryptocurrencies. The system exploits an initial proposal for a double elliptic graph layout, reconfigurable with three different ordering functions, in order to support fast visual search of cryptocurrencies by correlation strength. One usecase developed with a domain expert in cryptocurrency financial activities demonstrates qualitatively the usage of the system.Item A Pipeline for Tailored Sampling for Progressive Visual Analytics(The Eurographics Association, 2022) Hogräfer, Marius; Burkhardt, Jakob; Schulz, Hans-Jörg; Bernard, Jürgen; Angelini, MarcoProgressive Visual Analytics enables analysts to interactively work with partial results from long-running computations early on instead of forcing them to wait. For very large datasets, the first step is to divide that input data into smaller chunks using sampling, which are then passed down the progressive analysis pipeline all the way to their progressive visualization in the end. The quality of the partial results produced by the progression heavily depends on the quality of these chunks, that is, chunks need to be representative of the dataset. Whether or not a sampling approach produces representative chunks does however depend on the particular analysis scenario. This stands in contrast to the common use of random sampling as a ''one-size-fits-most'' approach in PVA. In this paper, we propose a sampling pipeline and its open source implementation which can be used to tailor the used sampling method for an analysis scenario at hand. This pipeline consists of three configurable steps - linearization, subdivision, and selection - and for each, we propose exemplar operators. We then demonstrate its utility by providing tailored samplings for three distinct scenarios.Item ScrutinAI: A Visual Analytics Approach for the Semantic Analysis of Deep Neural Network Predictions(The Eurographics Association, 2022) Haedecke, Elena; Mock, Michael; Akila, Maram; Bernard, Jürgen; Angelini, MarcoWe present ScrutinAI, a Visual Analytics approach to exploit semantic understanding for deep neural network (DNN) predictions analysis, focusing on models for object detection and semantic segmentation. Typical fields of application for such models, e.g. autonomous driving or healthcare, have a high demand for detecting and mitigating data- and model-inherent shortcomings. Our approach aims to help analysts use their semantic understanding to identify and investigate potential weaknesses in DNN models. ScrutinAI therefore includes interactive visualizations of the model's inputs and outputs, interactive plots with linked brushing, and data filtering with textual queries on descriptive meta data. The tool fosters hypothesis driven knowledge generation which aids in understanding the model's inner reasoning. Insights gained during the analysis process mitigate the ''black-box character'' of the DNN and thus support model improvement and generation of a safety argumentation for AI applications. We present a case study on the investigation of DNN models for pedestrian detection from the automotive domain.Item Toward Disease Diagnosis Visual Support Bridging Classic and Precision Medicine(The Eurographics Association, 2022) Palleschi, Alessia; Petti, Manuela; Tieri, Paolo; Angelini, Marco; Bernard, Jürgen; Angelini, MarcoThe traditional approach in medicine starts with investigating patients' symptoms to make a diagnosis. While with the advent of precision medicine, a diagnosis results from several factors that interact and need to be analyzed together. This added complexity asks for increased support for medical personnel in analyzing these data altogether. Our objective is to merge the traditional approach with network medicine to offer a tool to investigate together symptoms, anatomies, diseases, and genes to establish a diagnosis from different points of view. This paper aims to help the clinician with the typical workflow of disease analysis, proposing a Visual Analytics tool to ease this task. A use case demonstrates the benefits of the proposed solution.Item Towards Understanding Edit Histories of Multivariate Graphs(The Eurographics Association, 2022) Berger, Philip; Schumann, Heidrun; Tominski, Christian; Bernard, Jürgen; Angelini, MarcoThe visual analysis of multivariate graphs increasingly involves not only exploring the data, but also editing them. Existing editing approaches for multivariate graphs support visual analytics workflows by facilitating a seamless switch between data exploration and editing. However, it remains difficult to comprehend performed editing operations in retrospect and to compare different editing results. Addressing these challenges, we propose a model describing what graph aspects can be edited and how. Based on this model, we develop a novel approach to visually track and understand data changes due to edit operations. To visualize the different graph states resulting from edits, we extend an existing graph visualization approach so that graph structure and the associated multivariate attributes can be represented together. Branching sequences of edits are visualized as a node-link tree layout where nodes represent graph states and edges visually encode the performed edit operations and the graph aspects they affect. Individual editing operations can be inspected by dynamically expanding edges to detail views on demand. In addition, we support the comparison of graph states through an interactive creation of attribute filters that can be applied to other states to highlight similarities.Item Voyage Viewer: Empowering Human Mobility at a Global Scale(The Eurographics Association, 2022) Loaiza, Isabella; South, Tobin; Sánchez, Germán; Chan, Serena; Yu, Alice; Montes, Felipe; Bahrami, Mohsen; Pentland, Alex; Bernard, Jürgen; Angelini, MarcoThe challenge of refugee relocation is fertile ground to pose a new direction in the quest for extended human intelligence: developing systems that leverage big data, and the power of social learning to provide personalized visual analytics for big life decisions. To probe into this new avenue, this paper presents Voyage Viewer, a novel open-access multi-stream data dashboard called Voyage Viewer. It helps individuals make their own relocation and migration decisions given personalized queries and visualizations, which stands in contrast to previous top-down approaches that use algorithms to match individuals and places, as is the case for some refugee relocation programs. Voyage Viewer hopes to foster social learning between community members to improve the match between migrants and their potential new communities so that both can reap the benefits of the move.