检索结果-内蒙古大学图书馆

Information That Matters: Exploring Information Needs of People Affected by Algorithmic Decisions

学校读者我要写书评

暂无评论

arXiv 2024年

Every AI system that makes decisions about people has a group of stakeholders that are personally affected by these decisions. However, explanations of AI systems rarely address the information needs of this stakeholder group, who often are AI novices. This creates a gap between conveyed information and information that matters to those who are impacted by the system’s decisions, such as domain experts and decision subjects. To address this, we present the "XAI Novice Question Bank," an extension of the XAI Question Bank [60] containing a catalog of information needs from AI novices in two use cases: employment prediction and health monitoring. The catalog covers the categories of data, system context, system usage, and system specifications. We gathered information needs through task-based interviews where participants asked questions about two AI systems to decide on their adoption and received verbal explanations in response. Our analysis showed that participants’ confidence increased after receiving explanations but that their understanding faced challenges. These included difficulties in locating information and in assessing their own understanding, as well as attempts to outsource understanding. Additionally, participants’ prior perceptions of the systems’ risks and benefits influenced their information needs. Participants who perceived high risks sought explanations about the intentions behind a system’s deployment, while those who perceived low risks rather asked about the system’s operation. Our work aims to support the inclusion of AI novices in explainability efforts by highlighting their information needs, aims, and challenges. We summarize our findings as five key implications that can inform the design of future explanations for lay stakeholder audiences. Copyright © 2024, The Authors. All rights reserved.

关键词：

PraK Tool V3: Enhancing Video Item Search Using Localized Text and Texture Queries 31st

学校读者我要写书评

暂无评论

PraK Tool V3: Enhancing Video Item Search Using Localized Te...

31st International Conference on Multimedia Modeling, MMM 2025

作者： Stroh, Michael Kloda, Vojtěch Verner, Benjamin Vopálková, Zuzana Buchmüller, Raphael Jäckl, Bastian Hajko, Jakub Lokoč, Jakub Visual Computing Department of Computer Science Faculty of Natural Sciences Konstanz University Konstanz Germany SIRET Research Group Department of Software Engineering Faculty of Mathematics and Physics Charles University Prague Czech Republic Data Analysis and Visualization Department of Computer Science Faculty of Natural Sciences Konstanz University Konstanz Germany

ISBN: (纸本)9789819620739

We present a third version of the PraK system designed around an effective text-image and image-image search model. The system integrates sub-image search options for localized context search for CLIP and image color/texture and interfaces tailored to specific task types. A user study shows the benefits of sub-image search in homogeneous video collections. We further enhance the user experience of the PraK framework by re-designing the frontend and introducing task-specific views. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Video analysis

PraK Tool: An Interactive Search Tool Based on Video data Services 30th

学校读者我要写书评

暂无评论

PraK Tool: An Interactive Search Tool Based on Video Data S...

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Lokoč, Jakub Vopálková, Zuzana Stroh, Michael Buchmueller, Raphael Schlegel, Udo SIRET Research Group Department of Software Engineering Faculty of Mathematics and Physics Charles University Prague Czech Republic Visual Computing Department of Computer Science Faculty of Natural Sciences Konstanz University Konstanz Germany Data Analysis and Visualization Department of Computer Science Faculty of Natural Sciences Konstanz University Konstanz Germany

ISBN: (纸本)9783031533013

This paper presents a tool relying on data service architecture, where technical details of all VBS datasets are completely hidden behind an abstract stateless data layer. The data services allow independent development of interactive search interfaces and refinement techniques, which is demonstrated by a smart front-end component. The component supports common search features and allows users to exploit content-based statistics for effective filtering. We believe that video data services might be a valuable addition to the open-source VBS toolkit, especially when available for the competition on a shared server with all VBS datasets, extracted features, and meta-data behind. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Video recording

Applying Interdisciplinary Frameworks to Understand Algorithmic Decision-Making

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Schmude, Timothée Koesten, Laura Möller, Torsten Tschiatschek, Sebastian University of Vienna Faculty of Computer Science Research Network Data Science UniVie Doctoral School Computer Science DoCS Austria University of Vienna Faculty of Computer Science Research Group Visualization and Data Analysis Austria University of Vienna Faculty of Computer Science Research Network Data Science Research Group Visualization and Data Analysis Austria University of Vienna Faculty of Computer Science Research Network Data Science Research Group Data Mining and Machine Learning Austria

We argue that explanations for "algorithmic decision-making" (ADM) systems can profit by adopting practices that are already used in the learning sciences. We shortly introduce the importance of explaining ADM systems, give a brief overview of approaches drawing from other disciplines to improve explanations, and present the results of our qualitative task-based study incorporating the "six facets of understanding" [24] framework. We close with questions guiding the discussion of how future studies can leverage an interdisciplinary approach. © 2023, CC BY.

关键词： Decision making

On the Impact of Explanations on Understanding of Algorithmic Decision-Making

学校读者我要写书评

暂无评论

arXiv 2023年

Ethical principles for algorithms are gaining importance as more and more stakeholders are affected by "high-risk" algorithmic decision-making (ADM) systems. Understanding how these systems work enables stakeholders to make informed decisions and to assess the systems’ adherence to ethical values. Explanations are a promising way to create understanding, but current explainable artificial intelligence (XAI) research does not always consider existent theories on how understanding is formed and evaluated. In this work, we aim to contribute to a better understanding of understanding by conducting a qualitative task-based study with 30 participants, including users and affected stakeholders. We use three explanation modalities (textual, dialogue, and interactive) to explain a "high-risk" ADM system to participants and analyse their responses both inductively and deductively, using the "six facets of understanding" framework by Wiggins & McTighe [63]. Our findings indicate that the "six facets" framework is a promising approach to analyse participants’ thought processes in understanding, providing categories for both rational and emotional understanding. We further introduce the "dialogue" modality as a valid explanation approach to increase participant engagement and interaction with the "explainer", allowing for more insight into their understanding in the process. Our analysis further suggests that individuality in understanding affects participants’ perceptions of algorithmic fairness, demonstrating the interdependence between understanding and ADM assessment that previous studies have outlined. We posit that drawing from theories on learning and understanding like the "six facets" and leveraging explanation modalities can guide XAI research to better suit explanations to learning processes of individuals and consequently enable their assessment of ethical values of ADM systems. © 2023, CC BY.

关键词： Decision making

SpatialRugs: Enhancing spatial awareness of movement in dense pixel visualizations

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Buchmüller, Juri F. Schlegel, Udo Cakmak, Eren Dimara, Evanthia Keim, Daniel A. University of Konstanz Data Analysis and Visualization Group Germany

Compact visual summaries of spatio-temporal movement data often strive to express accurate positions of movers. We present SpatialRugs, a technique to enhance the spatial awareness of movements in dense pixel visualizations. SpatialRugs apply 2D colormaps to visualize location mapped to a juxtaposed display. We explore the effect of various colormaps discussing perceptual limitations and introduce a custom color-smoothing method to mitigate distorted patterns of collective movement behavior. Copyright © 2020, The Authors. All rights reserved.

关键词： visualization

cpmViz: A Web-Based visualization Tool for Uncertain Spatiotemporal data

学校读者我要写书评

暂无评论

cpmViz: A Web-Based Visualization Tool for Uncertain Spatiot...

IEEE Symposium on Visual Analytics Science and Technology (VAST)

作者： Fabian Nagel Giuliano Castiglia Gemza Ademaj Juri Buchmller Udo Schlegel Daniel A. Keim Data Analysis and Visualization Group University of Konstanz Germany

The goal of the VAST challenge 2019 Mini Challenge 2 was to visualize radioactive contaminations measured by mobile and static sensors and their changes over time, allowing city officials to determine the severity of the leakage at the city's nuclear power plant. We propose cpmViz, a web-based tool that allows for interactive data exploration of the sensor readings in both of the spatial and temporal dimensions. The tool consists out of three views that are connected via linking and scrolling. We visualize static sensor uncertainty by introducing Voronoi cells to illustrate how much space is covered by an individual measurement unit. For mobile sensors, we showcase their activity periods and introduce the concept of sensor streaks as periods of uninterrupted recordings as a temporal uncertainty measure. As for spatial uncertainty, we color individual districts based on the amount of data that was recorded inside the user's selected time window. Using our system, we were able to easily spot major events like the city's initial earthquake in the sensor readings. Certain southern districts are clearly visible as areas of concern that we consider in need of more static sensors. Furthermore, we were also able to identify static as well as moving contaminations.

关键词： Sensors Pollution measurement Contamination Uncertainty Urban areas data visualization Measurement uncertainty

G-Rap: Interactive text synthesis using recurrent neural network suggestions 26

学校读者我要写书评

暂无评论

G-Rap: Interactive text synthesis using recurrent neural net...

26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2018

作者： Schlegel, Udo Cakmak, Eren Buchmüller, Juri Keim, Daniel A. University of Konstanz Data Analysis and Visualization Group Konstanz Germany

ISBN: (纸本)9782875870476

Finding the best neural network configuration for a given goal can be challenging, especially when it is not possible to assess the output quality of a network automatically. We present G-Rap, an interactive interface based on Visual Analytics principles for comparing outputs of multiple RNNs for the same training data. G-Rap enables an iterative result generation process that allows a user to evaluate the outputs with contextual statistics. © ESANN 2018 - Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.

关键词： Recurrent neural networks

Exploring Uncertainty in Image Segmentation Ensembles

学校读者我要写书评

暂无评论

Exploring Uncertainty in Image Segmentation Ensembles

20th Eurographics/IEEE VGTC Conference on visualization, EuroVis 2018

作者： Fröhler, B. Möller, T. Weissenböck, J. Hege, H.-C. Kastner, J. Heinzl, C. Research Group Computed Tomography University of Applied Sciences Upper Austria Austria Visualization and Data Analysis Research Group Faculty of Computer Science University of Vienna Austria Visual Data Analysis Department Zuse Institute Berlin Germany

ISBN: (纸本)9783038680659

Finding the most accurate image segmentation involves analyzing results from different algorithms or parameterizations. In this work, we identify different types of uncertainty in this analysis that are represented by the results of probabilistic algorithms, by the local variability in the segmentation, and by the variability across the segmentation ensemble. We propose visualization techniques for the analysis of such types of uncertainties in segmentation ensembles. For a global analysis we provide overview visualizations in the image domain as well as in the label space. Our probability probing and scatter plot based techniques facilitate a local analysis. We evaluate our techniques using a case study on industrial computed tomography data. © 2018 The Author(s)

关键词：