检索结果-内蒙古大学图书馆

50th International conference on Very Large data Bases, VLDB 2024

作者： Ji, Daomin Luo, Hui Bao, Zhifeng Culpepper, Shane RMIT University Australia University of Wollongong Australia The University of Queensland Australia

Line charts are fundamental to data analysis and exploration, offering concise visual representations of trends. However, gaining access to the underlying data used to construct these charts is often challenging. In this paper, we describe DDLC (short for dataset discovery via line charts), an automatic dataset discovery tool that is able to not only identify datasets (from a dataset repository) that are "relevant" to the information depicted from a line chart provided by the users, but also empower users to refine search results based on specific visual elements extracted from the line chart. Moreover, DDLC offers multiple avenues for users to validate search outcomes: 1) Providing explanations on how a similar line chart could be generated from the identified dataset;2) enabling comparison of line charts generated from different datasets via different ways (e.g., the aggregation vs. non-aggregation operator);3) facilitating fine-grained examination of the correspondence between the line chart and the identified dataset. By seamlessly combining dataset retrieval with visual refinement and validation mechanisms, DDLC offers a comprehensive solution for the data-driven exploration and analysis. © 2024, VLDB Endowment. All rights reserved.

关键词： data aggregation

来源：评论

学校读者我要写书评

暂无评论

Interaction visualization for Analysing and Improving User Models 32

Interaction Visualization for Analysing and Improving User M...

引用

32nd ACM conference on User Modeling, Adaptation and Personalization (ACM UMAP)

作者： Lengauer, Stefan Shao, Lin Tytarenko, Mariia Klaffenboeck, Manfred Schreck, Tobias Graz Univ Technol Graz Austria TU Wien Vienna Austria

ISBN: (纸本)9798400704666

Many web-based systems such as online retail, information systems or search engines track the interactions users have with them. Tracked data can comprise high-level information like dwelling time, reviewed items, and clicked elements, but also fine-grained information in the form of mouse trajectories and keystrokes. While these data are often fed into user- or behavior models in recommender systems, there are few approaches for interactive visual exploration of multi-modal and complex interaction patterns. Yet, the thorough analysis could reveal important insights for the design and evaluation of said models. We propose a suitable visual analysis approach that allows to validate and correct models in an intuitive and interactive manner. Our tool provides insights into concrete user (inter)actions and also estimates more complex behavioral patterns. Level of detail views in our system outlines the certainty of detected behaviors and serve the explainability. Our approach can help engineers to understand user interactions and improve behavioral models.

关键词： User Modelling Model Validation and analysis Interaction visualization

来源：评论

学校读者我要写书评

暂无评论

A Computational Design Pipeline to Fabricate Sensing Network Physicalizations

引用

IEEE TRANSACTIONS ON visualIZATION AND COMPUTER GRAPHICS 2024年第1期30卷 913-923页

作者： Bae, S. Sandra Fujiwara, Takanori Ynnerman, Anders Do, Ellen Yi-Luen Rivera, Michael L. Szafir, Danielle Albers Univ Colorado Boulder CO 80309 USA Linkoping Univ Linkoping Sweden Univ North Carolina Chapel Hill Chapel Hill NC USA

Interaction is critical for data analysis and sensemaking. However, designing interactive physicalizations is challenging as it requires cross-disciplinary knowledge in visualization, fabrication, and electronics. Interactive physicalizations are typically produced in an unstructured manner, resulting in unique solutions for a specific dataset, problem, or interaction that cannot be easily extended or adapted to new scenarios or future physicalizations. To mitigate these challenges, we introduce a computational design pipeline to 3D print network physicalizations with integrated sensing capabilities. Networks are ubiquitous, yet their complex geometry also requires significant engineering considerations to provide intuitive, effective interactions for exploration. Using our pipeline, designers can readily produce network physicalizations supporting selection-the most critical atomic operation for interaction-by touch through capacitive sensing and computational inference. Our computational design pipeline introduces a new design paradigm by concurrently considering the form and interactivity of a physicalization into one cohesive fabrication workflow. We evaluate our approach using (i) computational evaluations, (ii) three usage scenarios focusing on general visualization tasks, and (iii) expert interviews. The design paradigm introduced by our pipeline can lower barriers to physicalization research, creation, and adoption.

关键词： Physicalization tangible interfaces 3D printing computational fabrication design automation network data

来源：评论

学校读者我要写书评

暂无评论

EmoVIT: Revolutionizing Emotion Insights with visual Instruction Tuning

EmoVIT: Revolutionizing Emotion Insights with Visual Instruc...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xie, Hongxia Peng, Chu-Jun Tseng, Yu-Wen Chen, Hung-Jen Hsu, Chan-Feng Shuai, Hong-Han Cheng, Wen-Huang Jilin Univ Changchun Peoples R China Natl Taiwan Univ Taipei Taiwan Natl Yang Ming Chiao Tung Univ Hsinchu Taiwan

ISBN: (纸本)9798350353006

visual Instruction Tuning represents a novel learning paradigm involving the fine-tuning of pre-trained language models using task-specific instructions. This paradigm shows promising zero-shot results in various natural language processing tasks but is still unexplored in vision emotion understanding. In this work, we focus on enhancing the model's proficiency in understanding and adhering to instructions related to emotional contexts. Initially, we identify key visual clues critical to visual emotion recognition. Subsequently, we introduce a novel GPT-assisted pipeline for generating emotion visual instruction data, effectively addressing the scarcity of annotated instruction data in this domain. Expanding on the groundwork established by InstructBLIP, our proposed EmoVIT architecture incorporates emotion-specific instruction data, leveraging the powerful capabilities of Large Language Models to enhance performance. Through extensive experiments, our model showcases its proficiency in emotion classification, adeptness in affective reasoning, and competence in comprehending humor. The comparative analysis provides a robust benchmark for Emotion visual Instruction Tuning in the era of LLMs, providing valuable insights and opening avenues for future exploration in this domain. Our code is available at https://***/aimmemotion/EmoVIT.

关键词： Emotion Recognition Large Language Model visual Instruction Tuning

来源：评论

学校读者我要写书评

暂无评论

Applying visual analytics to firearms trafficking trails for the extraction of strategic intelligence

Applying visual analytics to firearms trafficking trails for...

引用

2024 IEEE International conference on Big data, Bigdata 2024

作者： Adamakis, E. Sykianaki, E. Margetis, G. Ntoa, S. Stephanidis, C. Foundation for Research and Technology Hellas Institute of Computer Science Heraklion Greece University of Crete Department of Computer Science Heraklion Greece

ISBN: (纸本)9798350362480

Big data analysis and insight extraction are critical in contemporary large-scale criminal investigations. Analyzing large sets of information related to criminal activities can assist in the identification of correlations between records which can be utilized as strategic intelligence information for the coordination of law enforcement efforts. A Law Enforcement Agency (LEA) officer tasked with this analysis requires tools that can enable Big data exploration while being intuitive and without requiring the need for prior knowledge. A common practice of data analysis software is the ability to create dashboards that can provide all the necessary visualizations and filters to support such an analysis. However, when it comes to dashboard-wide data exploration through drill-down or roll-up analysis;review and evaluation of correlations between data records;and creation of collections with information important to an investigation, current solutions fall short. In this paper, we present a system that addresses these limitations by facilitating the visualization and exploration of diverse data sources, allowing for individual or concurrent analysis via user-configured dashboards. Individual data records of interest to the analysis can be reviewed and their correlations evaluated by the user, allowing for the creation of collections of records and their relationships based on formalized types of correlations. © 2024 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Understanding visual Artists' Values and Attitudes towards Collaboration, Technology, and AI 24

Understanding Visual Artists' Values and Attitudes towards C...

引用

50th Graphics Interface conference (GI)

作者： Johnston, Hannah Thue, David Carleton Univ Ottawa ON Canada

ISBN: (纸本)9798400718281

Artificial Intelligence (AI) tools have recently gained widespread interest for image creation, but tool developers have largely focused on technical capabilities or specialized domain uses, rather than visual artists as users. We collected survey data from 89 practising visual artists and conducted follow-up interviews with 30 of them, to better understand their diverse needs and values. Through reflexive thematic analysis, we explored visual artists' attitudes towards collaboration in art creation both with human artists and with AI- and other technology-based support systems. Our results suggest that the focus of popular AI tools on high-quality, finished images does not meet the needs of visual artists. Instead, they wanted reference images, ideation support, and variant exploration. We identified similarities and differences between how visual artists view collaboration with other artists or with machine support, enabling designers of new tools to adopt a more user-centered approach.

关键词： visual Art Collaboration Artificial Intelligence Creativity Support Tools User Experience Generative Research

来源：评论

学校读者我要写书评

暂无评论

Advances in the Security of SDNs: exploration of Recent ML-Based Approaches 5th

Advances in the Security of SDNs: Exploration of Recent ML-B...

引用

5th International conference on Smart Applications and data analysis for Smart Cyber Physical Systems

作者： Mellal, Ilyasse Wakrime, Abderrahime Ait Boukir, Khaoula Mohammed V Univ Rabat Dept Comp Sci Fac Sci Rabat Morocco Ibn Tofail Univ Kenitra Morocco

ISBN: (纸本)9783031770425;9783031770432

In contrast to conventional networks, Software-Defined Networking has revolutionized network control by separating data and control layers, introducing a dynamic and programmable infrastructure. Despite its benefits, SDN faces various security challenges. This study investigates specific attack vectors, such as DDoS/DoS attacks, topology poisoning, and malicious applications, along with machine learning applications that exhibit several benefits in addressing SDN-specific vulnerabilities and attacks. The study emphasizes the need for investigations and contributions directly addressing unique security challenges across SDN planes, interfaces, and attack categories with the help of ML techniques.

关键词： SDN Security Machine learning

来源：评论

学校读者我要写书评

暂无评论

Development and Application of data analysis and visualization Software in Oil Testing Process

Development and Application of Data Analysis and Visualizati...

引用

2024 International conference on Telecommunications and Power Electronics, TELEPE 2024

作者： Wu, Liqiang Jiang, Wanxue Chen, Zhi Downhole Services Company Cnpc Bohai Drilling Engineering Company Limited Hebei Renqiu062550 China

ISBN: (纸本)9798350369212

This study is devoted to the development and application of data analysis and visualization software in the process of oil testing, aiming at improving the understanding of underground reservoirs and the accuracy of reservoir development decisions. Through in-depth investigation and analysis of the requirements of geological data analysis and visualization, a powerful Oilanalysis software platform is designed and implemented, which can effectively process and analyze various types of geological data and provide intuitive and interactive visual display. The software developed in this study has flexible data import and processing functions, and can handle various geological data types including logging data, seismic data and core analysis data. At the same time, the software also integrates various data analysis and visualization algorithms, including stratigraphic modeling, porosity analysis, seismic exploration profile display and other functions, providing users with comprehensive data analysis and display tools. Through the analysis of practical application cases, the practical utility of the software in the process of oil testing is verified, which proves that it has important application value and popularization prospect. © 2024 IEEE.

关键词： data accuracy

来源：评论

学校读者我要写书评

暂无评论

The Role of visualization in Genomics data analysis Workflows: The Interviews

The Role of Visualization in Genomics Data Analysis Workflow...

引用

IEEE conference on visualization and visual Analytics (IEEE VIS)

作者： L'Yi, Sehi Wang, Qianwen Gehlenborg, Nils Harvard Med Sch Boston MA 02115 USA

ISBN: (纸本)9798350325577

The diversity of genome-mapped data and analysis tasks makes it challenging for a single visualization tool to fulfill all visualization needs. To design a visualization tool that supports various genomics workflows of users, it is critical to first gain insights into the diverse workflows and the limitations of existing genomics tools for supporting them. In this paper, we conducted semi-structured interviews (N=9) to understand the role of visualization in genomics data analysis workflows. Our main goals were to identify various genomics workflows, from data analysis to visual exploration and presentation, and to observe challenges that genomics analysts encounter in these workflows when using existing tools. Through the interviews, we found several unique characteristics of genomics workflows, such as the use of multiple visualization tools and many repetitive tasks, which can significantly affect the overall performance. Based on our findings, we discuss implications for designing effective visualization authoring tools that tightly support genomics workflows, such as supporting automation and reproducibility.

关键词： H.5.2 [Information Systems]: Information Interfaces and Presentation (e.g. HCI) User Interfaces

来源：评论

学校读者我要写书评

暂无评论

EVRACE: Enhanced visual Retrieval and analysis for Large-Scale E-Bike Charging Curve exploration

EVRACE: Enhanced Visual Retrieval and Analysis for Large-Sca...

引用

2024 IEEE International conference on Big data, Bigdata 2024

作者： Hu, Saisai Zhang, Ji Li, Zhao Ding, Donghui Liu, Dong Pan, Zhijun Dong, Jiale Nanjing University of Aeronautics and Astronautics School of Computer Science and Technology Nanjing China University of Southern Queensland Towoomba Australia Hangzhou Yugu Technology Co. Ltd. Hangzhou China

ISBN: (纸本)9798350362480

This Paper introduces a novel Enhanced visual Retrieval and analysis for Charging Efficiency (EVRACE) system, which presents a novel two-stage framework for visual retrieval and advanced analytics for massive charging curves of electric vehicles. The EVRACE is becoming an important system for enhancing battery performance management, detecting and mitigating charging anomalies, and informing strategic decision-making for stakeholders in the EV ecosystem. EVRACE utilizes deep time-series clustering to categorize charging curves with distinct characteristics and retrieves the most relevant cluster and the top k curves for comprehensive data analysis and risk assessment. This innovative framework substantially enhances retrieval efficiency, mitigates computational complexity, and offers a robust solution for real-time processing of large-scale charging data. Validation using real-world datasets demonstrates that the EVRACE system significantly improves retrieval efficiency and achieves high accuracy in anomaly detection compared to traditional methods. © 2024 IEEE.

关键词： Charging stations

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：