检索结果-内蒙古大学图书馆

1st IEEE VIS workshop on visualization Education, Literacy, and Activities (EduVis) part of the IEEE VIS Conference

作者： stoiber, Christina Pohl, Margit Aigner, Wolfgang St Polten Univ Appl Sci St Polten Austria Vienna Univ Technol Inst Design & Assessment Technol Vienna Austria

ISBN: (纸本)9798350330304

Integrating visualization onboarding methods into visual analytics tools presents challenges for designers and developers. These challenges include the varying complexity of visualization techniques, data types, and users' expertise levels. Selecting and integrating educational theories, ensuring the completeness and clarity of onboarding instructions, choosing the appropriate medium, and determining interaction techniques for exploration during onboarding are also problematic. However, there needs to be established design guidance specifically focused on visualization onboarding. Existing resources like VisGuides and design patterns offer some qualitative advice but lack scientific foundations. To address this gap, we propose nine design actions based on critical reflections of empirical studies, the development of a design space, and user studies. These design actions emphasize customizing onboarding experiences to address users' knowledge gaps, finding a balance between flexibility and structure, and incorporating concrete examples while considering potential limitations in knowledge transfer. Furthermore, we explore the connections, issues, and contradictions within the design actions. In conclusion, it is crucial to tailor onboarding experiences, balance flexibility and structure, and provide concrete examples while acknowledging knowledge transfer challenges.

关键词： visualization literacy visualization onboarding design guidelines educational theory

来源：评论

学校读者我要写书评

暂无评论

A data Model and Operations for Higher-Dimensional Moving Objects in databases 1

A Data Model and Operations for Higher-Dimensional Moving Ob...

引用

1st ACM SIGSPATIAL International workshop on Methods for Enriched Mobility data: Emerging issues and Ethical Perspectives, EMODE 2023

作者： Heinz, Florian Schildgen, Johannes Ostbayerische Technische Hochschule Regensburg Regensburg Germany

ISBN: (纸本)9798400703478

Moving Object databases are designed to store and process database objects with attributes that can change over time. Simple examples are moving points, that change position over time, a bit more complex are moving regions, that can also change shape. The spatial and spatiotemporal object types in current moving objects databases are limited to two dimensions. This work strives to extend the set of spatial moving object types into the third and even higher dimensions while preserving a consistent family of operations for it. A robust algorithm for the interpolation of two regions to a moving region of any dimensionality is developed, as well as the fundamental ideas for several other operations. © 2023 ACM.

关键词： data models moving objects moving regions spatiotemporal data

来源：评论

学校读者我要写书评

暂无评论

A static Analysis Platform for Investigating Security Trends in Repositories 1

A Static Analysis Platform for Investigating Security Trends...

引用

IEEE/ACM 1st International workshop on Software Vulnerability (SVM)

作者： Sonnekalb, Tim Knaust, Christopher-Tobias Gruner, Bernd Brust, Clemens-Alexander von Kurnatowski, Lynn Schreiber, Andreas Heinze, Thomas S. Maeder, Patrick German Aerosp Ctr DLR Inst Data Sci Jena Germany German Aerosp Ctr DLR Inst Software Technol Cologne Germany Cooperat Univ Gera Eisenach Gera Germany Tech Univ Ilmenau Data Intens Syst & Visualizat Grp Ilmenau Germany

ISBN: (纸本)9798350301908

static analysis tools come in many forms and configurations, allowing them to handle various tasks in a (secure) development process: code style linting, bug/vulnerability detection, verification, etc., and adapt to the specific requirements of a software project, thus reducing the number of false positives. The wide range of configuration options poses a hurdle in their use for software developers, as the tools cannot be deployed out-of-the-box. However, static analysis tools only develop their full benefit if they are integrated into the software development workflow and used on regular. Vulnerability management should be integrated via version history to identify hotspots, for example. We present an analysis platform that integrates several static analysis tools that enable Git-based repositories to continuously monitor warnings across their version history. The framework is easily extensible with other tools and programming languages. We provide a visualization component in the form of a dashboard to display security trends and hotspots. Our tool can also be used to create a database of security alerts at a scale well-suited for machine learning applications such as bug or vulnerability detection.

关键词： static analysis software security automatic analysis SAst tool database security dashboard

来源：评论

学校读者我要写书评

暂无评论

How You Split Matters: data Leakage and Subject Characteristics studies in Longitudinal Brain MRI Analysis 12th

How You Split Matters: Data Leakage and Subject Characterist...

引用

12th Int workshop on Clin Image-Based Procedures - Towards Holist Patient Models for Personalised Healthcare / 1st Int workshop on Fairness of AI in Med Imaging / 2nd Int workshop on Ethical and Philosoph issues in Med Imaging

作者： Rumala, Dewinda J. Inst Teknol Sepuluh Nopember Surabaya Indonesia

ISBN: (纸本)9783031452482;9783031452499

Deep learning models have revolutionized the field of medical image analysis, offering significant promise for improved diagnostics and patient care. However, their performance can be misleadingly optimistic due to a hidden pitfall called 'data leakage'. In this study, we investigate data leakage in 3D medical imaging, specifically using 3D Convolutional Neural Networks (CNNs) for brain MRI analysis. While 3D CNNs appear less prone to leakage than 2D counterparts, improper data splitting during cross-validation (CV) can still pose issues, especially with longitudinal imaging data containing repeated scans from the same subject. We explore the impact of different data splitting strategies on model performance for longitudinal brain MRI analysis and identify potential data leakage concerns. GradCAM visualization helps reveal shortcuts in CNN models caused by identity confounding, where the model learns to identify subjects along with diagnostic features. Our findings, consistent with prior research, underscore the importance of subject-wise splitting and evaluating our model further on hold-out data from different subjects to ensure the integrity and reliability of deep learning models in medical image analysis.

关键词： data Leakage Deep Learning MRI Alzheimer's Disease

来源：评论

学校读者我要写书评

暂无评论

A static Analysis Platform for Investigating Security Trends in Repositories

A Static Analysis Platform for Investigating Security Trends...

引用

Software Vulnerability (SVM), IEEE/ACM International workshop on

作者： Tim Sonnekalb Christopher-Tobias Knaust Bernd Gruner Clemens-Alexander Brust Thomas S. Heinze Lynn von Kurnatowski Andreas Schreiber Patrick Mäder German Aerospace Center (DLR) Institute of Data Science Jena Germany Cooperative University Gera-Eisenach Gera Germany Institute for Software Technology German Aerospace Center (DLR) Cologne Germany Institute for Software Technology German Aerospace Center (DLR) Cologne Germany

static analysis tools come in many forms and configurations, allowing them to handle various tasks in a (secure) development process: code style linting, bug/vulnerability detection, verification, etc., and adapt to the specific requirements of a software project, thus reducing the number of false *** wide range of configuration options poses a hurdle in their use for software developers, as the tools cannot be deployed out-of-the-box. However, static analysis tools only develop their full benefit if they are integrated into the software development workflow and used on regular. Vulnerability management should be integrated via version history to identify hotspots, for *** present an analysis platform that integrates several static analysis tools that enable Git-based repositories to continuously monitor warnings across their version history. The framework is easily extensible with other tools and programming languages. We provide a visualization component in the form of a dashboard to display security trends and hotspots. Our tool can also be used to create a database of security alerts at a scale well-suited for machine learning applications such as bug or vulnerability detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interactive statistical monitoring to optimize review of potential clinical trial issues during study conduct

引用

CONTEMPORARY CLINICAL TRIALS COMMUNICATIONS 2023年 33卷 101101-101101页

作者： Pau, David Lotz, Marie Grandclaude, Gaelle Jegou, Romain Civet, Alexandre Roche SAS Boulogne Billancourt France Keyrus Life Sci Nantes France

Background: statistical monitoring involves the review of prospective study data collected in participating sites to detect intra/inter patients and sites inconsistencies. We report methods and results of statistical monitoring in a phase IV clinical ***: PRO-MSACTIVE is a study evaluating ocrelizumab in active relapsing multiple sclerosis (RMS) patients in France. Specific statistical methods (volcano plots, mahalanobis distance, funnel plot ...) have been applied to a SDTM database to detect potential issues. R-Shiny application was developed to generate an interactive web application in order to ease site and/or patients identification during statistical data review ***: The PRO-MSACTIVE study enrolled 422 patients in 46 centers between July 2018 and August 2019. Three data review meetings were held between April and October 2019 and 14 standard and planned tests were run on study data, with a total of 15 (32.6%) sites identified as needing review or investigation. Overall 36 findings were identified during the meetings: duplicate records, outliers, inconsistent delays between ***: statistical monitoring is useful to identify unusual or clustered data patterns that might be revealing issues that could impact the data integrity and/or may potentially impact patients' safety. With anticipated and appropriate interactive data visualization, early signals can easily be identified or reviewed by the study team and appropriate actions be set up and assigned to the most appropriate function for a close follow-up and resolution. Interactive statistical monitoring is time consuming to initiate using R-Shiny, but is time saving after the 1st data review meeting (DRV).(*** identifier: NCT03589105;EudraCT identifier: 2018-000780-91)

关键词： statistical monitoring R shiny Clinical trial Interactive data visualization

来源：评论

学校读者我要写书评

暂无评论

Selecting and Sharing Multidimensional Projection Algorithms: A Practical View 1

Selecting and Sharing Multidimensional Projection Algorithms...

引用

1st workshop on the Gap between visualization Research and visualization Software, VisGap 2020

作者： Espadoto, M. Vernier, E.F. Telea, A.C. Institute of Mathematics and Statistics University of São Paulo Brazil Institute of Informatics Federal University of Rio Grande Do sul Brazil Department of Information and Computing Sciences Utrecht University Netherlands Johann Bernoulli Institute University of Groningen Netherlands

ISBN: (纸本)9783038681250

Multidimensional Projection techniques are often used by data analysts for exploring multivariate datasets, but the task of selecting the best technique for the job is not trivial, as there are many candidates and the reasons for picking one over another are usually unclear. On the other hand, researchers developing new techniques can have a hard time comparing their new technique to existing ones and sharing their code in a way that makes it readily available for the public. In this paper, we try to address those issues systematically by analyzing recent surveys in the area, identifying the methods and tools used, and discussing challenges, limitations, and ideas for further work. © 2020 The Author(s).

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

Acquisition of Typical Occupancy Schedules for Commercial Buildings from Social Networks 1

Acquisition of Typical Occupancy Schedules for Commercial Bu...

引用

1st ACM International workshop on Urban Building Energy Sensing, Controls, Big data Analysis, And visualization (UrbSys)

作者： Lu, Xing Feng, Fan O'Neill, Zheng Univ Alabama Dept Mech Engn Tuscaloosa AL 35487 USA

ISBN: (纸本)9781450370141

Occupancy behavior in buildings has been a hotspot of research as building systems become more sophisticated. Traditional sensing technologies suffer from high costs, inevitable sensor errors, and scalability issues and thus are not widely implemented in buildings. In this notes paper, two different approaches for extracting the typical occupancy schedules for the input to the building energy simulation are explored based on the data from social networks. The first approach is to use text classification algorithms to identify whether people are present in space where they are making posts on social networks. To achieve this, word embedding and machine learning algorithms for the classification are used. On top of that, we could extract the typical occupancy schedules by assuming certain people counting rules. The second approach is to utilize the processed GPS location tracking data provided by social network giants such as Facebook and Google Map. Web scraping techniques are used to obtain the data and extract the building typical occupancy schedules. Two preliminary case studies demonstrate these two approaches as a proof of concept using a museum building, the Art Institute of Chicago. The results show that the extracted building occupancy schedules from different social network data sources (Twitter, Facebook, and Google Map) share a similar trend but slightly distinct with each other, which requires more explorations and further validations and corrections. However, the methodology and promising results from this preliminary study will lay the foundation of the occupancy sensing through the social network data mining, which aims to provide another data source for occupancy sensing in buildings at the building level. This will provide another alternative to estimate the occupancy at the community- and urban-scale.

关键词： Building Occupancy data Acquisition Machine Learning Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Challenges for air pollution monitoring: A cyber-physical social systems approach 1

Challenges for air pollution monitoring: A cyber-physical so...

引用

1st workshop on Cyber-Physical Social Systems, CPSS 2019

作者： Zappatore, Marco Refolo, Sergio Longo, Antonella Hesplora s.r.l. and University of Salento Lecce Italy Dept. of Innovation Engineering University of Salento Lecce Italy

Air pollution control plays a pivotal role today in urban contexts, as both citizens and public administrators are increasingly sensitive about it. Traditional air pollution sensing is performed and managed by public institutions with professional and expensive equipment, thus exhibiting a series of inherent limitations such as isolated monitoring campaigns, data heterogeneity, inconsistency and incompleteness, limited access to sensed data. Cyber-Physical-Social Systems (CPSS) promise to be a considerable step forward, as they promote the systematic involvement of citizens in monitoring processes and the provisioning of proactive services to end users. However, several elements hinders such a model. In this paper, we will discuss the challenges of applying cyber-physical paradigm to air pollution monitoring in smart cities, exemplifying the issues on the Italian case study and then we will show how CPSS will go over them and outline novel research directions. Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning to Improve Heart Disease Risk Prediction 1st

Deep Learning to Improve Heart Disease Risk Prediction

引用

1st International workshop on Machine Learning and Medical Engineering for Cardiovasvular Healthcare, MLMECH 2019, and the 8th International Joint workshops on Computing and visualization for Intravascular Imaging and Computer Assisted stenting, CVII-stENT 2019, held in conjunction with 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2019

作者： Sajeev, Shelda Maeder, Anthony Champion, stephanie Beleigoli, Alline Ton, Cheng Kong, Xianglong Shu, Minglei Flinders Digital Health Research Centre School of Nursing and Health Sciences Flinders University Adelaide Australia Department of Big Data Engineering Technology Research Center of E-Government JinanShandong China Shandong Computer Science Center Shandong Provincial Key Laboratory of Computer Networks Qilu University of Technology Jinan China

ISBN: (纸本)9783030333263

Disease prediction based on modeling the correlations between compounded indicator factors is a widely used technique in high incidence chronic disease prevention diagnosis. Predictive models based on personal health information have been developed historically by using simple regression fitting over relatively few factors. Regression approaches have been favored in previous prediction modeling approaches because they are simplest and do not assume any non-linearity in the model for contributions of the chosen factors. In practice, many factors are correlated and have underlying non-linear relationships to the predicted outcome. Deep learning offers a means to construct a more complex modeling approach, along with automation and adaptation. The aim of this paper is to assess the ability of a deep learning model to predict the heart disease incidence using a common benchmark dataset (University of California, Irvine (UCI) dataset). The performance of deep learning model has been compared with four popular machine learning models (two linear and two nonlinear) in predicting the incidence of heart disease using data from 567 participants from two cohorts taken from UCI database. The deep learning model was able to achieve the best accuracy of 94% and an AUC score of 0.964 when compared to other models. The performance of deep learning and nonlinear machine learning models was significantly better compared to the linear machine learning models with increase in the dataset size. © 2019, Springer Nature Switzerland AG.

关键词： Diseases

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：