检索结果-内蒙古大学图书馆

Simulation Winter Conference

作者： Oliver Reinhardt Adelinde M. Uhrmacher Martin Hinsch Jakub Bijak Visual and Analytic Computing University of Rostock Rostock GERMANY Social Statistics and Demography University of Southampton Southampton UK

ISBN: (数字)9781728132839

ISBN: (纸本)9781728120522

Developing a realistic agent-based model of human migration requires particular care. Committing too early to a specific model architecture, design, or language environment can later become costly in terms of the revisions required. To examine specifically the impact of differences in implementation, we have developed two instances of the same model in parallel. One model is realized in the programming language Julia, the underlying execution semantics is of a discrete stepwise stochastic process. The other is realized in an external domain-specific language ML3, based on a continuous-time Markov chain (CTMC) semantics. By developing models in pairs in different approaches, important properties of the target model can be more effectively revealed. In addition, the realization within a programming language and an external domain-specific modeling language respectively, helped identifying crucial features and trade-offs for the future implementation of the model and the design of the domain-specific modeling language.

关键词： Urban areas Biological system modeling Adaptation models Computational modeling Semantics Data models Stochastic processes

来源：评论

学校读者我要写书评

暂无评论

Virtual lenses as embodied tools for immersive analytics

arXiv

引用

arXiv 2019年

作者： Kluge, Sven Gladisch, Stefan von Lukas, Uwe Freiherr Staadt, Oliver Tominski, Christian Institute for Visual & Analytic Computing University of Rostock Fraunhofer Institute for Computer Graphics Research IGD Rostock Germany

Interactive lenses are useful tools for supporting the analysis of data in different ways. Most existing lenses are designed for 2D visualization and are operated using standard mouse and keyboard interaction. On the other hand, research on virtual lenses for novel 3D immersive visualization environments is scarce. Our work aims to narrow this gap in the literature. We focus particularly on the interaction with lenses. Inspired by natural interaction with magnifying glasses in the real world, our lenses are designed as graspable tools that can be created and removed as needed, manipulated and parameterized depending on the task, and even combined to flexibly create new views on the data. We implemented our ideas in a system for the visual analysis of 3D sonar data. Informal user feedback from more than a hundred people suggests that the designed lens interaction is easy to use for the task of finding a hidden wreck in sonar data. Copyright © 2019, The Authors. All rights reserved.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Simulation Experiment Schemas –Beyond Tools and Simulation Approaches

Simulation Experiment Schemas –Beyond Tools and Simulation ...

引用

Simulation Winter Conference

作者： Pia Wilsdorf Marcus Dombrowsky Adelinde M. Uhrmacher Julius Zimmermann Ursula van Rienen Institute for Visual and Analytic Computing University of Rostock Rostock GERMANY Institute of General Electrical Engineering University of Rostock Rostock GERMANY

ISBN: (数字)9781728132839

ISBN: (纸本)9781728120522

Simulation studies make use of various types of simulation experiments. For users, specifying these experiments is a demanding task since the specification depends on the experiment type and the idiosyncrasies of the used tools. Thus, we present an experiment generation procedure that guides users through the specification process, and abstracts away from the concrete execution environment. This abstraction is achieved by (1) developing schemas that define the properties of simulation experiments and dependencies between them, (2) specifying a mapping between schema properties and template fragments in the specification language of a target backend. We develop schema, template fragments, and mappings for stochastic discrete-event simulation, and show how the concepts can be transported to a different domain of modeling and simulation. Further, we expand the developed "simple" experiment schemas by a schema for experiment designs, and generate executable sensitivity analysis experiments, thereby demonstrating versatility and composability of our approach.

关键词： Computational modeling analytical models Task analysis Data models Graphical user interfaces Tools Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Conducting systematic, partly automated simulation studies – Unde Venis et Quo Vadis

引用

AIP Conference Proceedings 2020年第1期2293卷

作者： Pia Wilsdorf Fiete Haack Kai Budde Andreas Ruscheinski Adelinde M. Uhrmacher Modeling and Simulation Group Institute for Visual and Analytic Computing Department of Computer Science and Electrical Engineering University of Rostock D-18055 Rostock Germany

Simulation studies are intricate processes in which model building, model refinement, and a wide variety of simulation experiments are typically closely intertwined to achieve the objective of the simulation study. To (semi-)automatically support this process, the central artifacts of a simulation study, such as simulation models and simulation experiments, need to be made explicit and accessible. Furthermore, the relations between the artifacts as well as their context (e.g., the objectives, data sources, and requirements) have to be made explicit in an unambiguous manner. If this information is enriched by knowledge about modeling and simulation approaches or specific application domains, interpretation and reuse of the various (intermediate) artifacts and activities are facilitated even more. The resulting information can then be exploited to assist modelers in selecting and conducting the subsequent simulation experiments, which we demonstrate using a cell biological simulation study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Validation of convolutional neural network relevance maps for revealing patterns of Alzheimer’s disease in MRI scans

引用

Alzheimer's & Dementia 2020年第S5期16卷

作者： Martin Dyrba Arjun H. Pallath Stefan J. Teipel German Center for Neurodegenerative Diseases (DZNE) Rostock Germany Institute of Visual and Analytic Computing University of Rostock Rostock Germany University Medical Center Rostock Rostock Germany

Background Although machine learning approaches achieve high diagnostic accuracy for detecting Alzheimer’s disease (AD) based on MRI scans, they are not applied in clinical routine due to a lack of suitable methods for model comprehensibility and interpretability. Recently developed visualization methods for convolutional neural networks (CNN) may fill this gap. We trained a CNN model to detect AD based on T1-weighted MRI and implemented a web application to provide an intuitive visualization of relevance maps. The aim of this study was to evaluate the association of relevance scores and hippocampus volume to validate the clinical utility of this approach. Method MRI scans for 254 cognitively normal controls (CN), 219 patients with amnestic mild cognitively impairment (MCI), and 189 patients with AD were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). MRI scans were tissue-segmented and normalized using VBM8. Hippocampal volume was extracted from the gray matter (GM) maps. Subsequently, GM maps and hippocampal volume were corrected for effects of total intracranial volume, age, gender and scanner magnetic field strength using a linear model. Thirty-two coronal slices covering the hippocampus were selected and the corresponding GM residual maps entered into the CNN. The model was evaluated using ten-fold cross-validation. Finally, we derived activation maps using the layer-wise relevance propagation (LRP) algorithm and calculated the sum of hippocampus relevance scores. Result We obtained highly accurate results of an AUC of 93±6% for AD vs. CN. For MCI vs. CN, group separation was lower with an AUC of 74±9%. The relevance maps for four exemplary patients are shown in Fig. 1. Relevance maps confirmed that hippocampal atrophy is the most informative region for AD detection with minor contributions from other cortical and subcortical regions. Relevance scores within the hippocampus were correlated with hippocampal volume with a Pearson correlation

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning models for generating diagnostic explanations

引用

Alzheimer's & Dementia 2020年第S5期16卷

作者： Martin Dyrba Arjun H. Pallath Eman N. Marzban Stefan J. Teipel German Center for Neurodegenerative Diseases (DZNE) Rostock Germany Institute of Visual and Analytic Computing University of Rostock Rostock Germany Cairo University Giza Egypt Rostock University Medical Center Rostock Germany

Background Although machine learning approaches achieve high diagnostic accuracy when detecting Alzheimer’s disease (AD) based on MRI scans, they are rarely applied in clinical studies due to a lack of suitable methods for model comprehensibility and interpretability. Recent advances in convolutional neural networks (CNN) visualization algorithms and methods for generating textual explanations may fill this gap. Here, we will introduce these novel approaches, present first prototypical software using these techniques, and outline the potential of such tools for clinical studies. Method We implemented a CNN model trained on 662 T1-weighted MRI scans obtained from ADNI. Various CNN visualization algorithms were compared, which generate relevance maps indicating the contribution of individual image areas for detecting AD. Further, we created an interactive web application to display them and interactively change visualization parameters. For evaluation, we compared relevance scores in the hippocampus region with hippocampal volume. Result The CNN model reached a cross-validated area under the curve (AUC) of 0.93±0.06 for AD vs. controls and 0.74±0.09. The layer-wise relevance propagation (LRP) algorithm was found to provide most informative and robust results (Fig. 1). The web app is shown in Fig. 2. Hippocampal volume and relevance scores of the hippocampus region-of-interest correlated with r= -0.79 (Fig. 3). Additionally, relevance maps highlighted various other image regions with local cortical and subcortical atrophy. Conclusion CNN relevance maps may support clinicians in their MRI examinations. CNN models for generating textual explanations may offer additional information, but are not yet available due to the vast amount of labeled training samples required for training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: Evaluation in Alzheimer's disease

arXiv

引用

arXiv 2020年

作者： Dyrba, Martin Hanzig, Moritz Altenstein, Slawek Bader, Sebastian Ballarini, Tommaso Brosseron, Frederic Buerger, Katharina Cantré, Daniel Dechent, Peter Dobisch, Laura Düzel, Emrah Ewers, Michael Fliessbach, Klaus Glanz, Wenzel Haynes, John-Dylan Heneka, Michael T. Janowitz, Daniel Keles, Deniz B. Kilimann, Ingo Laske, Christoph Maier, Franziska Metzger, Coraline D. Munk, Matthias H. Perneczky, Robert Peters, Oliver Preis, Lukas Priller, Josef Rauchmann, Boris Roy, Nina Scheffler, Klaus Schneider, Anja Schott, Björn H. Spottke, Annika Spruth, Eike J. Weber, Marc-André Ertl-Wagner, Birgit Wagner, Michael Wiltfang, Jens Jessen, Frank Teipel, Stefan J. Rostock Germany Institute of Visual and Analytic Computing University of Rostock Rostock Germany Berlin Germany Department of Psychiatry and Psychotherapy Charité - Universitätsmedizin Berlin Campus Charité Mitte Berlin Germany Bonn Germany Department for Neurodegenerative Diseases and Geriatric Psychiatry University Hospital Bonn Bonn Germany Munich Germany University Hospital Ludwig Maximilian University Munich Germany Institute of Diagnostic and Interventional Radiology Pediatric Radiology and Neuroradiology Rostock University Medical Center Rostock Germany MR-Research in Neurosciences Department of Cognitive Neurology Georg-August-University Goettingen Germany Magdeburg Germany Otto-von-Guericke University Magdeburg Germany Bernstein Center for Computational Neuroscience Berlin Germany Department of Psychiatry and Psychotherapy Charité - Universitätsmedizin Berlin Campus Benjamin Franklin Berlin Germany Department of Psychosomatic Medicine Rostock University Medical Center Rostock Germany Tuebingen Germany Section for Dementia Research Hertie Institute for Clinical Brain Research Tuebingen Germany Department of Psychiatry and Psychotherapy University of Tuebingen Tuebingen Germany Department of Psychiatry Medical Faculty University of Cologne Cologne Germany Department of Psychiatry and Psychotherapy Otto-von-Guericke University Magdeburg Germany Systems Neurophysiology Department of Biology Darmstadt University of Technology Darmstadt Germany Department of Psychiatry and Psychotherapy University Hospital Ludwig Maximilian University Munich Germany Ludwig Maximilian University Munich Germany School of Public Health Imperial College London London United Kingdom Department of Psychiatry and Psychotherapy Klinikum rechts der Isar Technical University Munich Munich Germany Department for Biomedical Magnetic Resonance University of Tuebingen Tuebingen Germany Goettingen Germany Department of Psychiatry and Psychotherapy

Background: Although convolutional neural networks (CNN) achieve high diagnostic accuracy for detecting Alzheimer's disease (AD) dementia based on magnetic resonance imaging (MRI) scans, they are not yet applied in clinical routine. One important reason for this is a lack of model comprehensibility. Recently developed visualization methods for deriving CNN relevance maps may help to fill this gap as they allow the visualization of key input image features that drive the decision of the model. We investigated whether models with higher accuracy also rely more on discriminative brain regions predefined by prior knowledge. Methods: We trained a CNN for the detection of AD in N=663 T1-weighted MRI scans of patients with dementia and amnestic mild cognitive impairment (MCI) and verified the accuracy of the models via cross-validation and in three independent samples including in total N=1655 cases. We evaluated the association of relevance scores and hippocampus volume to validate the clinical utility of this approach. To improve model comprehensibility, we implemented an interactive visualization of 3D CNN relevance maps, thereby allowing intuitive model inspection. Results: Across the three independent datasets, group separation showed high accuracy for AD dementia versus controls (AUC≥0.91) and moderate accuracy for amnestic MCI versus controls (AUC≈0.74). Relevance maps indicated that hippocampal atrophy was considered as the most informative factor for AD detection, with additional contributions from atrophy in other cortical and subcortical regions. Relevance scores within the hippocampus were highly correlated with hippocampal volumes (Pearson's r ≈ -0.86, p Copyright © 2020, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Using (Not-so) Large Language Models to Generate Simulation Models in a Formal DSL: A Study on Reaction Networks

引用

ACM Transactions on Modeling and Computer Simulation 1000年

作者： Justin Noah Kreikemeyer Miłosz Jankowski Pia Wilsdorf Adelinde M. Uhrmacher Faculty of Computer Science and Electrical Engineering Institute for Visual and Analytic Computing University of Rostock Rostock Germany

Formal languages are an integral part of modeling and simulation. They allow the distillation of knowledge into concise simulation models amenable to automatic execution, interpretation, and analysis. However, the arguably most humanly accessible means of expressing models is through natural language, which is not easily interpretable by computers. Here, we evaluate how a Large Language Model (LLM) might be used for formalizing natural language into simulation models. Existing studies only explored using very large LLMs, like the commercial GPT models, without fine-tuning model weights. To close this gap, we show how an open-weights, 7B-parameter Mistral model can be fine-tuned to translate natural language descriptions to reaction network models in a domain-specific language, offering a self-hostable, compute-, and memory efficient alternative. To this end, we develop a synthetic data generator to serve as the basis for fine-tuning and evaluation. Our quantitative evaluation shows that our fine-tuned Mistral model can recover the ground truth simulation model in up to \(84.5\%\) of cases. In addition, our small-scale user study demonstrates the model’s practical potential for one-time generation as well as interactive modeling in various domains. While promising, in its current form, the fine-tuned small LLM cannot catch up with large LLMs. We conclude that higher-quality training data are required, and expect future small and open-source LLMs to offer new opportunities.

关键词： simulation model generation natural language processing language model constrained decoding knowledge extraction

来源：评论

学校读者我要写书评

暂无评论

visualization of Time-Oriented Data 2

引用

丛书名： Human–Computer Interaction Series

1000年

作者： Wolfgang Aigner Silvia Miksch Heidrun Schumann Christian Tominski

ISBN: (数字)9781447175278

ISBN: (纸本)9781447175261;9781447175292

So, what is new for the second edition? First of all, the second edition is now published as an open-access book so that anyone interested in the visualization of time and time-oriented data can read it. Second, the entire content has been revised and expanded to represent state-of-the-art knowledge. The chapter on interaction support now includes advanced methods for interacting with visual representations of time-oriented data. The second edition also covers the topics of data quality as well as segmentation and labeling. The comprehensive survey of classic and contemporary visualization techniques now provides more than 150 self-contained descriptions accompanied by illustrations and corresponding references. A completely new chapter describes how the structured survey can be used for the guided selection of suitable visualization techniques.;For the second edition, our TimeViz Browser, the digital pendant to the survey of visualization techniques, received a major upgrade. It includes the same set of techniques as the book, but comes with additional filter and search facilities allowing scientists and practitioners to find exactly the solutions they are interested in.

关键词： User Interfaces and Human Computer Interaction visualization

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：