检索结果-内蒙古大学图书馆

Pacific (formerly Asia-Pacific APVIS) visualization Symposium

作者： Theresia Gschwandtner Oliver Erhart Institute of Visual Computing and Human-Centered Technology TU Wien

Sensible data analysis requires data quality control. An essential part of this is data profiling, which is the identification and assessment of data quality problems as a prerequisite for adequately handling these problems. Differentiating between actual quality problems and unusual, but valid data values requires the "human-in-the-loop" through the use of visual analytics. Unfortunately, existing approaches for data profiling do not adequately support the special characteristics of time, which is imperative to identify quality problems in time series data - a data type prevalent in a multitude of disciplines. In this design study paper, we outline the design, implementation, and evaluation of "Know Your Enemy" (KYE) - a visual analytics approach to assess the quality of time series data. KYE supports the task of data profiling with (1) predefined data quality checks, (2) user-definable, customized quality checks, (3) interactive visualization to explore and reason about automatically detected problems, and (4) the visual identification of hidden quality problems.

关键词： Data integrity Time series analysis Data visualization Task analysis Prototypes Bars Taxonomy

来源：评论

学校读者我要写书评

暂无评论

Explaining automated gender classification of human gait

引用

Gait & Posture 2020年 81卷 159-160页

作者： Horst, F. Slijepcevic, D. Zeppelzauer, M. Raberger, A.M. Lapuschkin, S. Samek, W. Schöllhorn, W.I. Breiteneder, C. Horsak, B. Johannes Gutenberg-University Mainz Institute of Sport Science Mainz Germany Both authors contributed equally to this work l l Austria St. Pölten University of Applied Sciences Institute of Creative Media Technologies St. Pölten Austria St. Pölten University of Applied Sciences Institute of Health Sciences St. Pölten Austria Fraunhofer Heinrich Hertz Institute Department of Video Coding & Analytics Berlin Germany TU Wien Institute of Visual Computing and Human-Centered Technology Vienna Austria

来源：评论

学校读者我要写书评

暂无评论

Automatic Furniture Arrangement Using Greedy Cost Minimization

Automatic Furniture Arrangement Using Greedy Cost Minimizati...

引用

IEEE Annual International Symposium Virtual Reality

作者： Peter Kán Hannes Kaufmann Institute of Visual Computing and Human-Centered Technology TU Wien Vienna Austria

ISBN: (纸本)9781538633663

In this paper, we present a novel method for fast generation of furniture arrangements in interior scenes. Our method exploits the benefits of optimization-based approaches for global aesthetic rules and the advantages of procedural approaches for local arrangement of small objects. We generate the furniture arrangements for a given room in two steps: We first optimize the selection and arrangement of furniture objects in a room with respect to aesthetic and functional rules. The infinite trans-dimensional space of furniture layouts is rapidly explored by greedy cost minimization. In the second step, the procedural methods are locally applied in a stochastic fashion to generate important scene details. We demonstrate that our method achieves comparable results to a recent method for automatic interior design in terms of user preferences and that local procedural design enhances the result of optimization-based interior design. Additionally, our method is one order of magnitude faster than the compared method. Finally, the execution times of up to one second show that our method is suitable for generating large-scale indoor virtual environments during runtime.

关键词： Layout Cost function Minimization Three-dimensional displays Space exploration Stochastic processes

来源：评论

学校读者我要写书评

暂无评论

Assistenzroboter mit „Persönlichkeit“ ausstatten?

引用

Pflegezeitschrift 2018年第7期71卷 44-47页

作者： Peter Mayer Paul Panek Forschungsbereich HCI Institute of Visual Computing and Human-Centered Technology Technische Universität Wien Wien Österreich

Das EU Forschungsprojekt „HOBBIT“ hat Prototypen von assistiven Robotern zur Unterstützung eines sicheren und selbstständigen Lebens entwickelt und bei älteren Personen in der häuslichen Umgebung getestet. Im Projekt „personAAL“ wurde untersucht, ob verschiedene Verhaltensweisen („Persönlichkeiten“) eines solchen Roboterprototyps bei ansonsten gleicher Funktion (Überbringen einer Nachricht) von Testpersonen als unterschiedliche Persönlichkeiten wahrgenommen werden. Der Roboter wurde mit zwei Verhaltensweisen (introvertiert/extrovertiert) ausgestattet und 13 Testpersonen (großteils älteren Personen bzw. Experten aus der Pflege) vorgeführt. Der „extrovertierte“ Roboter wurde weit überwiegend präferiert. Bei den Teilfragen „Anthropomorphismus“ und „Belebtheit“ sowie in der Gesamtbewertung wurden signifikante Wahrnehmungsunterschiede gefunden, nicht jedoch für die Teilfragen „Sympathie“ und „Sicherheit“. Es gab keinerlei signifikante Korrelation zwischen bevorzugtem Verhalten des Roboters und Selbsteinschätzung der Testperson als introvertiert oder extrovertiert. Es kann vermutet werden, dass die Akzeptanz eines Roboters nicht rein von der nüchternen Funktion abhängt, und es daher sinnvoll sein wird, für bessere Akzeptanz verschiedene Verhaltensweisen zur Wahl zu stellen.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature-based groupwise registration of historical aerial images to present-day ortho-photo maps

arXiv

引用

arXiv 2018年

作者： Zambanini, Sebastian Computer Vision Lab Institute of Visual Computing and Human-Centered Technology TU Wien Favoritenstrasse 9/1931 ViennaA-1040 Austria

In this paper, we address the registration of historical WWII images to present-day ortho-photo maps for the purpose of geolocalization. Due to the challenging nature of this problem, we propose to register the images jointly as a group rather than in a step-by-step manner. To this end, we exploit Hough Voting spaces as pairwise registration estimators and show how they can be integrated into a probabilistic groupwise registration framework that can be efficiently optimized. The feature-based nature of our registration framework allows to register images with a-priori unknown translational and rotational relations, and is also able to handle scale changes of up to 30% in our test data due to a final geometrically guided matching step. The superiority of the proposed method over existing pairwise and groupwise registration methods is demonstrated on eight highly challenging sets of historical images with corresponding ortho-photo *** Codes 68U10 (Primary), 65K10 (Secondary) Copyright © 2018, The Authors. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Explaining machine learning models for age classification in human gait analysis

引用

Gait & Posture 2022年 97卷 S252-S253页

作者： Slijepcevic, D. Horst, F. Simak, M. Lapuschkin, S. Raberger, A.M. Samek, W. Breiteneder, C. Schöllhorn, W.I. Zeppelzauer, M. Horsak, B. St. Pölten University of Applied Sciences Institute of Creative Media Technologies St. Pölten Austria Both Authors Contributed Equally to this Work l l Austria Johannes Gutenberg-University Mainz Institute of Sport Science Mainz Germany Fraunhofer Heinrich Hertz Institute Department of Artificial Intelligence Berlin Germany St. Pölten University of Applied Sciences Institute of Health Sciences St. Pölten Austria TU Wien Institute of Visual Computing and Human-Centered Technology Vienna Austria St. Pölten University of Applied Sciences Center for Digital Health & Social Innovation St. Pölten Austria

来源：评论

学校读者我要写书评

暂无评论

P 011—Towards an optimal combination of input signals and derived representations for gait classification based on ground reaction force measurements

引用

Gait and Posture 2018年第Sup1期65卷 249-250页

作者： Slijepcevic, D. Zeppelzauer, M. Schwab, C. Raberger, A.-M. Dumphart, B. Baca, A. Breiteneder, C. Horsak, B. St. Pölten University of Applied Sciences Institute of Creative Media Technologies St. Pölten Austria St. Pölten University of Applied Sciences Institute of Health Sciences St. Pölten Austria University of Vienna Department of Biomechanics Kinesiology and Computer Science in Sport Vienna Austria TU Wien Institute of Visual Computing and Human-Centered Technology Vienna Austria

来源：评论

学校读者我要写书评

暂无评论

Handwritten Music Object Detection: Open Issues and Baseline Results

Handwritten Music Object Detection: Open Issues and Baseline...

引用

IAPR International Workshop on Document Analysis Systems, DAS

作者： Alexander Pacha Kwon-Young Choi Bertrand Coüasnon Yann Ricquebourg Richard Zanibbi Horst Eidenberger Institute of Visual Computing and Human-Centered Technology TU Wien Vienna Austria Yann Ricquebourg Univ Rennes CNRS IRISA Rennes France IRISA Univ. Rennes Rennes France Rochester Institute of Technology Rochester USA Technische Universitat Wien Wien Wien AT

Optical Music Recognition (OMR) is the challenge of understanding the content of musical scores. Accurate detection of individual music objects is a critical step in processing musical documents because a failure at this stage corrupts any further processing. So far, all proposed methods were either limited to typeset music scores or were built to detect only a subset of the available classes of music symbols. In this work, we propose an end-to-end trainable object detector for music symbols that is capable of detecting almost the full vocabulary of modern music notation in handwritten music scores. By training deep convolutional neural networks on the recently released MUSCIMA++ dataset which has symbol-level annotations, we show that a machine learning approach can be used to accurately detect music objects with a mean average precision of over 80%.

关键词： Detectors Semantics Object detection Music Training Feature extraction Vocabulary

来源：评论

学校读者我要写书评

暂无评论

On the understanding and interpretation of machine learning predictions in clinical gait analysis using explainable artificial intelligence

arXiv

引用

arXiv 2019年

作者： Horst, F. Slijepcevic, D. Lapuschkin, S. Raberger, A.-M. Zeppelzauer, M. Samek, W. Breiteneder, C. Schollhorn, W.I. Horsak, B. Department of Training and Movement Science Institute of Sport Science Johannes Gutenberg-University Mainz Mainz Germany Department of Media and Digital Technologies Institute of Creative Media Technologies St. POlten University of Applied Sciences St. POlten Austria Department of Video Coding and Analytics Fraunhofer Heinrich Hertz Institute Berlin Germany Department of Health Sciences Institute of Health Sciences St. POlten University of Applied Sciences St. Polten Austria Institute of Visual Computing and Human-Centered Technology TU Wien Vienna Austria

Systems incorporating Artificial Intelligence (AI) and machine learning (ML) techniques are increasingly used to guide decision-making in the healthcare sector. While AI-based systems provide powerful and promising results with regard to their classification and prediction accuracy (e.g., in differentiating between different disorders in human gait), most share a central limitation, namely their black-box character. Understanding which features classification models learn, whether they are meaningful and consequently whether their decisions are trustworthy is difficult and often impossible to comprehend. This severely hampers their applicability as decisionsupport systems in clinical practice. There is a strong need for AI-based systems to provide transparency and justification of predictions, which are necessary also for ethical and legal compliance. As a consequence, in recent years the field of explainable AI (XAI) has gained increasing importance. XAI focuses on the development of methods that enhance transparency and interpretability of complex ML models, such as Deep (Convolutional) Neural Networks. The primary aim of this article is to investigate whether XAI methods can enhance transparency, explainability and interpretability of predictions in automated clinical gait classification. We utilize a dataset comprising bilateral three-dimensional ground reaction force measurements from 132 patients with different lower-body gait disorders and 62 healthy controls. In our experiments, we included several gait classification tasks, employed a representative set of classification methods, and a well-established XAI method-Layer-wise Relevance Propagation (LRP)-to explain decisions at the signal (input) level. The classification results are analyzed, compared and interpreted in terms of classification accuracy and relevance of input values for specific decisions. The decomposed input relevance information are evaluated from a statistical (using Statistical Parameter

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Asymmetric cascade networks for focal bone lesion prediction in multiple myeloma

arXiv

引用

arXiv 2019年

作者： Licandro, Roxane Hofmanninger, Johannes Perkonigg, Matthias Roehrich, Sebastian Weber, Marc-Andr Wennmann, Markus Kintzele, Laurent Piraud, Marie Menze, Bjoern Langs, Georg Computer Vision Lab Department of Visual Computing and Human-centered Technologies TU Wien Austria Computational Imaging Research Lab Department of Biomedical Imaging and Image-guided Therapy Medical University of Vienna Austria Institute f. Diagn. u. Intervent. Radiologie Medizinische Universität Rostock Germany Department of Interventional and Diagnostic Radiology Section Musco-Skelatal Imaging Heidelberg University Germany Institute of Biomedical Engineering - Image-based biomedical modelling Technische Universitt Mnchen Germany

The reliable and timely stratification of bone lesion evolution risk in smoldering Multiple Myeloma plays an important role in identifying prime markers of the disease's advance and in improving the patients' outcome. In this work we provide an asymmetric cascade network for the longitudinal prediction of future bone lesions for T1 weighted whole body MR images. The proposed cascaded architecture, consisting of two distinct configured U-Nets, first detects the bone regions and subsequently predicts lesions within bones in a patch based way. The algorithm provides a full volumetric risk score map for the identification of early signatures of emerging lesions and for visualising high risk locations. The prediction accuracy is evaluated on a longitudinal dataset of 63 multiple myeloma patients. Keywords: Longitudinal prediction, asymmetric cascade U-Net, Multiple Myeloma, bone lesion assessment. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

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：