检索结果-内蒙古大学图书馆

19th International conference on Computer analysis of Images and Patterns (CAIP)

作者： Bigazzi, Roberto Landi, Federico Cornia, Marcella Cascianelli, Silvia Baraldi, Lorenzo Cucchiara, Rita Univ Modena & Reggio Emilia Modena Italy

ISBN: (纸本)9783030891275;9783030891282

The research field of Embodied AI has witnessed substantial progress in visual navigation and exploration thanks to powerful simulating platforms and the availability of 3D data of indoor and photorealistic environments. These two factors have opened the doors to a new generation of intelligent agents capable of achieving nearly perfect PointGoal Navigation. However, such architectures are commonly trained with millions, if not billions, of frames and tested in simulation. Together with great enthusiasm, these results yield a question: how many researchers will effectively benefit from these advances? In this work, we detail how to transfer the knowledge acquired in simulation into the real world. To that end, we describe the architectural discrepancies that damage the Sim2Real adaptation ability of models trained on the Habitat simulator and propose a novel solution tailored towards the deployment in real-world scenarios. We then deploy our models on a LoCoBot, a Low-Cost Robot equipped with a single Intel RealSense camera. Different from previous work, our testing scene is unavailable to the agent in simulation. The environment is also inaccessible to the agent beforehand, so it cannot count on scene-specific semantic priors. In this way, we reproduce a setting in which a research group (potentially from other fields) needs to employ the agent visual navigation capabilities as-a-Service. Our experiments indicate that it is possible to achieve satisfying results when deploying the obtained model in the real world. Our code and models are available at https://***/aimagelab/LoCoNav.

关键词： Embodied AI Sim2Real visual navigation

来源：评论

学校读者我要写书评

暂无评论

20th International conference on Computer-Aided Architectural Design Futures, CAAD Futures 2023

20th International Conference on Computer-Aided Architectura...

引用

20th International conference on Computer-Aided Architectural Design Futures, CAAD Futures 2023

ISBN: (纸本)9783031371882

The proceedings contain 43 papers. The special focus in this conference is on Computer-Aided Architectural Design Futures. The topics include: Social Signals: An Adaptive Installation for Mediating Space During COVID-19 and Beyond;enabling Flexible Architectural Design Re-representations Using a Phenotype-Based Strategy;Towards Human-AI Collaborative Architectural Concept Design via Semantic AI;the Impact of Spatial Layout on Orientation and Wayfinding in Public Housing Estates Using Isovist Polygons and Shape Matching Algorithms;architectural Sketch to 3D Model: An Experiment on Simple-Form Houses;a Physics-Based Constraint Solver for the Site Layout Optimization of Non-convex Buildings with Multiple Requirements;topological Operations: A New Method Toward Retrievable Design Operations;a visual Support Tool for Decision-Making over Federated Building Information;illustrating Algorithmic Design;biologically Informed Design - Towards Additive Biofabrication with Cyanobacteria;a Design-to-Fabrication Workflow for Free-Form Timber Structures Using Offcuts;urban Shaderade. Building Space analysis Method for Energy and Sunlight Consideration in Urban Environments;a Parametric Tool for Outdoor Shade Design: Harnessing Quantitative Indices and visual Feedback for Effective and Efficient Climatic Design of Streets;fine-Grained Long-Term analysis of Resurgent Urban Morphotypes;optimization Strategies of Architecture and Engineering Graduate Students: Responding to data During Design;a Design Ranking Method for Many-Objective Evolutionary Optimization;expanding Performance-Driven Parametric Design Spaces Through data Streams;the Marching Shape 3D: Extensions of the Ice Ray Shape Grammar;AI-Assisted exploration of the Spirit of Place in Chinese Gardens from the Perspective of Spatial Sequences;material-in-the-Loop Fabrication: A Vision-Based Adaptive Clay 3D Printing Workflow on Indeterminate Sand Surfaces;Cost-Effective 3D Urban Massing Reconstruction of Public Aerial LiDAR S

关键词：

来源：评论

学校读者我要写书评

暂无评论

exploration of Aural & visual Media About Birds Informs Lessons for Citizen Science Design 20

Exploration of Aural & Visual Media About Birds Informs Less...

引用

ACM Designing Interactive Systems conference (DIS)

作者： Oliver, Jessica L. Brereton, Margot Turkay, Selen Watson, David M. Roe, Paul Queensland Univ Technol Brisbane Qld Australia Charles Sturt Univ Albury NSW Australia

ISBN: (纸本)9781450369749

Acoustic sensing has been hailed as a game-changer for detecting furtive wildlife, but uptake has been constrained by the laborious process of reviewing resultant torrents of audio data. To inform the design of interactive interfaces for reviewing audio recordings, we explored how people interact with aural and visual media about birds. We observed how twelve participants with different levels of interest in birds engaged with vocalization recordings, visualizations of bird calls, photographs, and range maps of three species. By conducting thematic analysis, we identified a variety of Challenges of exploration and Benefits of a Media Assortment. We contribute lessons for designing to Bridge Knowledge & Context and to Facilitate Long-term Engagement with audio in ways that are fun, accessible, and informative. We provide explicit guidance for designers to diversify how citizen scientists interact with nature through audio as they move from engagement to conservation action.

关键词： Audio interactions aural birds citizen science multisensory nature connection visual wildlife

来源：评论

学校读者我要写书评

暂无评论

Immersive Process Model exploration in Virtual Reality

引用

IEEE TRANSACTIONS ON visualIZATION AND COMPUTER GRAPHICS 2020年第5期26卷 2104-2114页

作者： Zenner, Andre Makhsadov, Akhmajon Klingner, Soren Liebemann, David Kruger, Antonio German Res Ctr Artificial Intelligence DFKI Saarland Informat Campus Saarbrucken Germany

In many professional domains, relevant processes are documented as abstract process models, such as event-driven process chains (EPCs). EPCs are traditionally visualized as 2D graphs and their size varies with the complexity of the process. While process modeling experts are used to interpreting complex 2D EPCs, in certain scenarios such as, for example, professional training or education, also novice users inexperienced in interpreting 2D EPC data are facing the challenge of learning and understanding complex process models. To communicate process knowledge in an effective yet motivating and interesting way, we propose a novel virtual reality (VR) interface for non-expert users. Our proposed system turns the exploration of arbitrarily complex EPCs into an interactive and multi-sensory VR experience. It automatically generates a virtual 3D environment from a process model and lets users explore processes through a combination of natural walking and teleportation. Our immersive interface leverages basic gamification in the form of a logical walkthrough mode to motivate users to interact with the virtual process. The generated user experience is entirely novel in the field of immersive data exploration and supported by a combination of visual, auditory, vibrotactile and passive haptic feedback. In a user study with $\mathrm{N}=27$ novice users, we evaluate the effect of our proposed system on process model understandability and user experience, while comparing it to a traditional 2D interface on a tablet device. The results indicate a tradeoff between efficiency and user interest as assessed by the UEQ novelty subscale, while no significant decrease in model understanding performance was found using the proposed VR interface. Our investigation highlights the potential of multi-sensory VR for less time-critical professional application domains, such as employee training, communication, education, and related scenarios focusing on user interest.

关键词： Virtual reality Business Virtual reality multi-sensory feedback passive haptics immersion business process models immersive data analysis

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Task-Specific Limitations of the Overview+Detail Technique for Interactive Time Series analysis 2

An Empirical Study of Task-Specific Limitations of the Overv...

引用

2nd International conference on Industry 4.0 and Smart Manufacturing, ISM 2020

作者： Friedl, Judith Zimmer, Björn Perkhofer, Lisa Zenisek, Jan Hofer, Peter Jetter, Hans-Christian University of Applied Sciences Upper Austria Hagenberg Campus Softwarepark 11 HagenbergA-4232 Austria University of Applied Sciences Upper Austria Steyr Campus Wehrgrabengasse 1 SteyrA-4400 Austria University of Lübeck Ratzeburger Allee 160 LübeckD-23562 Germany

Interactive visualisation and analysis of time series data is a critical part of many data-driven optimisation processes, particularly in Industry 4.0 and Smart Manufacturing. Time series visualisation enables data analysts or domain experts to visually identify problems such as missing values, sensor drift, precision degradation, or faulty data, before or after algorithmic analysis. A common technique to support the visual exploration of large time series is the overview+detail (O+D) technique. O+D provides both detail and context information by displaying a detailed view showing the actual data and a thumbnail overview for showing its context. User studies have shown that users analyse and navigate data sets more efficently and effectively with than without O+D, but that this strongly depends on the task and the nature and amount of the data to be displayed. We present results of a quantitative user study that was performed on Amazon Mechanical Turk with 95 participants to identify scenarios in which O+D could not effectively solve the challenge of visualising large time series. By this, we identify potential usability issues of O+D for typical time series analysis tasks and discuss their origins. For each of these usability issues, we also propose alternative interaction and visualisation designs or other strategies to maintain good usability, even for challenging task types and data densities. © 2021 Elsevier B.V.. All rights reserved.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

exploration and Research on the Mixed Teaching Mode of Basic Japanese Course under the Background of Information Technology

Exploration and Research on the Mixed Teaching Mode of Basic...

引用

2020 International conference on Artificial Intelligence, Computer Networks and Communications, AICNC 2020

作者： Wei, Yarong Fuzhou University of International Studies and Trade Fuzhou China

At present, the general trend of information technology development is changing from the typical technology-driven development mode to the combination of application-driven and technology-driven mode. The development of information technology brings both opportunities and challenges to the reform and innovation of foreign language teaching. This paper starts with features and types of information-based foreign language teaching, to explore the mixed teaching mode of basic Japanese course under the background of information technology. Choose a reasonable teaching platform and teaching resources according to the teaching objectives;make a good teaching design for online autonomous learning for each chapter before class;to do well in offline classroom teaching development and classroom network-assisted teaching;and supplement online learning materials effectively for students after-class learning. Pay more attention to process evaluation, multi-subject evaluation and visual data analysis and evaluation based on big data. Pay attention to the role of games in basic Japanese learning, applying information technology to the teaching of basic Japanese courses and exploring the mixed teaching mode of basic Japanese courses can improve teaching effectiveness in all directions and contribute to the overall improvement of teaching quality. © Published under licence by IOP Publishing Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Knowledge Map of Chinese Geriatric Medical Care Research Field: Research Status and Trend—data visualization analysis Based on Cooc Software

Knowledge Map of Chinese Geriatric Medical Care Research Fie...

引用

HBDSS 2022;2nd International conference on Health Big data and Smart Sports

作者： Hongrui Bao Yanyin Cui Hui Yue

In the long-term context of an ageing population, geriatric medical care is an important safeguard for the Chinese response to the problem of aging. The study aimed to explore the research hotspots and process of geriatric medical care. We conducted a visual analysis of the literatures from 1986 to 2021 in CNKI, Wanfang and VIP database by Louvain algorithm and bibliometric method. We found that the research of geriatric medical care in China lags behind that in developed countries, and the development mainly presents three stages: germination, development and adjustment. The number of publications presents a steady growth trend; Medical and Health journals are the main publication journals; The core research teams are mainly composed of universities and research institutes in Shanghai and Beijing; The clustering topics focus on exploring the elderly medical security system, the feasibility of the medical service model, the management of chronic diseases, the development of the silver industry, medical disputes and health education for the elderly. Finally, we come to the conclusion that the health management of chronic diseases has become a new research hotspot and the exploration of new medical service models is an important trend.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unveiling Multivariate EEG Features: A Novel Approach to Enhancing ADHD Diagnosis Through visual and Auditory Attention Tests

Unveiling Multivariate EEG Features: A Novel Approach to Enh...

引用

International conference on Fuzzy Theory and it's Applications (iFUZZY)

作者： Zuo-Cian Fan Ro-Wei Lin Ching-Shu Tsai Wen-Jiun Chou Chia-Jung Li Zih-Jun Huang Bin-Yu Shih Liang-Jen Wang Li-Wei Ko Department of Biological Science & Technology Center for Intelligent Drug Systems and Smart Bio-Devices (IDS2B) College of Biological Science and Technology National Yang Ming Chiao Tung University Hsinchu Taiwan International Ph.D. Program in Interdisciplinary Neuroscience National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Child and Adolescent Psychiatry Kaohsiung Chang Gung Memorial Hospit Department of Electronics and Electrical Engineering Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

We sought to revolutionize the classification of Attention-Deficit/Hyperactivity Disorder (ADHD) by pioneering an innovative approach that seamlessly integrated auditory and visual tests with electroencephalogram (EEG) coherence analysis, forming the foundation for our Support Vector Machine (SVM) models. Our primary objective was to achieve precise differentiation between individuals with ADHD and those without, aiming to reshape the landscape of ADHD diagnosis and early intervention. We constructed an SVM model based on CATA coherence, incorporating a carefully selected set of 180 features, and another grounded in CPT coherence with 70 features. Astonishingly, our exploration uncovered that a model incorporating CATA's coherence and Power Spectral Density (PSD) as features achieved an astounding accuracy rate of 97.7%, using only half the number of features. This revelation hints at untapped potential for multivariate advancements in the realm of ADHD classification. The landscape of ADHD diagnosis and intervention is perpetually evolving, most notably with the FDA's approval of game therapy for ADHD. Leveraging the transformative power of our findings, we envision the development of user-friendly game therapies for in-home use, empowering both clinicians and parents alike. This marks a paradigm shift in the realm of ADHD intervention, offering objective, data-driven tools for the early management of ADHD. Gamified therapy not only enhances accessibility but also fosters engagement and compliance, all of which are pivotal in the long-term care of individuals with ADHD. In summary, our study represents a significant advancement in our comprehension and classification of ADHD. By fusing auditory and visual tests with EEG coherence analysis, fortified by state-of-the-art machine learning techniques, we have achieved an unprecedented level of accuracy in identifying individuals with ADHD. Our findings, aligned with the FDA-approved game therapy, offer a glimpse into a

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on visualization data of hotspots and development trend of domestic smart scenic spots 4

Research on visualization data of hotspots and development t...

引用

4th International conference on E-Business, Information Management and Computer Science, EBIMCS 2021

作者： Zhang, Yuanjing Cultural And Tourism Inustry Research Center Of Wuhan Business University Hubei Wuhan China

ISBN: (纸本)9781450395687

In this paper, Knowledge Map is used to make a visual analysis of 802 Chinese papers related to smart scenic spot research collected by CNKI, discuss the hot spots and development trends of smart scenic spot research in China. The research finds that the promotion of smart tourism policy plays a positive role in promoting the national smart tourism reform plan and realizing the establishment and implementation of smart tourism scenic spots in various regions, thus driving the growth of literature quantity. Nowdays the hotspots of smart tourism research in China focus on "smart scenic spots""smart tourism""scenic spot management"and "tourist attractions", with increasing heat. However, core authors and institutions published fewer papers, and their cooperation with each other was scattered, so no representative academic group was formed. At the same time, the cooperation of most research institutions in China is divided by regional scope, and trans-regional, cross-disciplinary and cross-institutional cooperation needs to be further strengthened. At present, domestic researches on smart scenic spots have gone deep into the practical application level, at the present stage, the development results are uneven, and the efficiency of production, education and research institutes is not obvious. In the future, the high-quality development of smart scenic spots still needs the exploration and deepening of scientific researchers. © 2021 ACM.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

Matrix Profile XXVI: Mplots: Scaling Time Series Similarity Matrices to Massive data

Matrix Profile XXVI: Mplots: Scaling Time Series Similarity ...

引用

IEEE International conference on data Mining (ICDM)

作者： Maryam Shahcheraghi Ryan Mercer João Manuel De Almeida Rodrigues Audrey Der Hugo Filipe Silveira Gamboa Zachary Zimmerman Eamonn Keogh University of California Riverside Libphys-UNL NOVA Faculty of Science and Technology

Time series similarity matrices (informally, recurrence plots), are useful tools for time series data mining. They can be used to guide data exploration, and various useful features can be derived from them and then fed into downstream analytics. However, time series similarity matrices suffer from very poor scalability, taxing both time and memory requirements. In this work, we introduce novel ideas that allow us to scale the largest time series similarity matrices that can be examined by several orders of magnitude. The first idea is a novel algorithm to compute the matrices in a way that removes dependency on the subsequence length. This algorithm is so fast that it allows us to now address datasets where the memory limitations begin to dominate. Our second novel contribution is a multiscale algorithm that computes an approximation of the matrix appropriate for the limitations of the user’s memory/screen-resolution, then performs a local, just-in-time recomputation of any region that the user wishes to zoom-in on. Given that we can largely remove time and space barriers, human visual attention then becomes the bottleneck. We further introduce algorithms that search massive matrices with quadrillions of cells and then prioritize regions for later attention by either humans or algorithms. We will demonstrate the utility of our ideas for data exploration, segmentation, and classification in diverse domains.

关键词： visualization Scalability Time series analysis Memory management Approximation algorithms Classification algorithms data mining

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：