检索结果-内蒙古大学图书馆

6th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2024

作者： Oberdiek, Sven Jalowy, Leah Vazquez, Flavio Gonzalez Risling, Monika Wahl, Katja Quality and Reliability Management Fraunhofer Institute for Manufacturing Engineering and Automation IPA Stuttgart Germany Dispersing Technology Fraunhofer Institute for Manufacturing Engineering and Automation IPA Stuttgart Germany Purity-specific Automation Systems Fraunhofer Institute for Manufacturing Engineering and Automation IPA Stuttgart Stuttgart Germany Data and Application Services for Digital Production Fraunhofer Institute for Manufacturing Engineering and Automation IPA Stuttgart Germany

ISBN: (纸本)9798350344349

This research paper explores the transition from batch mixing to continuous mixing processes for the production of slurries used in lithium-ion battery cells. The conventional batch mixing methods, prevalent in European industry, suffer from time-consuming cleaning processes, lengthy mixing times, and the inability to monitor paste conditions in real-Time. The study proposes a solution using continuous mixing with a twin-screw extruder, highlighting advantages such as reduced cleaning time, immediate sample characterization, and minimized production risks. The research aims to develop a test setup and procedure to accelerate the understanding of the continuous mixing process, leveraging minimal resources and time, and facilitating the training of artificial intelligence algorithms. The ultimate goal is to create a digital twin encompassing all influencing factors for predictive and prescriptive analytics. The methodology involves literature reviews, expert surveys, and experimental setups, with an emphasis on inline measuring devices. The paper presents results related to relevant product characteristics, influencing factors, and the selection of suitable measuring equipment. The experimental setup includes a database structure, human-machine interface, and visualization of measurement data. The study concludes with insights into the correlation analysis of influencing factors and product characteristics, emphasizing the need for further experiments and the development of algorithms for predictive quality assessments in continuous mixing processes. © 2024 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Intelligent scheduling of parallel harware tests: Evaluation and implementation of scheduling algorithms for constraint scheduling

引用

2012年

作者： Michael Galetzka

ISBN: (纸本)9783847301691

Scheduling tests with constraints is a complex problem, and there are many different algorithms to solve it. This book gives an insight into several of these algorithms. They were evaluated to create a test scheduling framework to test the Large Hadron Collider's equipment at CERN. These hardware tests come with many constraints as the stored energy from the superconducting magnet circuits is able to cause major equipment damage and downtime. For safety reasons, a high degree of dependability is a principal requirement for the scheduling component of this framework. The challenge presented in this work is not only to implement one of the scheduling algorithms but also to make the implementation easy to use, maintainable and reliable.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Process Variations and Probabilistic Integrated Circuit Design

引用

2014年

作者： Manfred Dietrich Joachim Haase

ISBN: (纸本)9781489988607

Uncertainty in key parameters within a chip and between different chips in the deep sub micron area plays a more and more important role. As a result, manufacturing process spreads need to be considered during the design process. Quantitative methodology is needed to ensure faultless functionality, despite existing process variations within given bounds, during product development. This book presents the technological, physical, and mathematical fundamentals for a design paradigm shift, from a deterministic process to a probability-orientated design process for microelectronic circuits. Readers will learn to evaluate the different sources of variations in the design flow in order to establish different design variants, while applying appropriate methods and tools to evaluate and optimize their design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DiffRenderGAN: Addressing Training Data Scarcity in Deep Segmentation Networks for Quantitative Nanomaterial Analysis through Differentiable Rendering and Generative Modelling

arXiv

引用

arXiv 2025年

作者： Possart, Dennis Mill, Leonid Vollnhals, Florian Hildebrand, Tor Suter, Peter Hoffmann, Mathis Utz, Jonas Augsburger, Daniel Thies, Mareike Wu, Mingxuan Wagner, Fabian Sarau, George Christiansen, Silke Breininger, Katharina Department Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-University Erlangen-Nürnberg Erlangen91052 Germany Pattern Recognition Lab Friedrich-Alexander-University Erlangen-Nürnberg Erlangen91058 Germany Institute for Nanotechnology and Correlative Microscopy Forchheim91301 Germany Lucid Concepts AG Zurich8005 Switzerland Correlative Microscopy and Materials Data Fraunhofer Institute for Ceramic Technologies and Systems Forchheim91301 Germany Institute of Experimental Physics Freie Universität Berlin Berlin91301 Germany Emeritus-Gruppe Leuchs Max Planck Institute for the Science of Light Erlangen91058 Germany Center for AI and Data Science Julius-Maximilians-University Würzburg Würzburg97074 Germany MIRA Vision Microscopy GmbH Göggingen73037 Germany

Nanomaterials exhibit distinctive properties governed by parameters such as size, shape, and surface characteristics, which critically influence their applications and interactions across technological, biological, and environmental contexts. Accurate quantification and understanding of these materials are essential for advancing research and innovation. In this regard, deep learning segmentation networks have emerged as powerful tools that enable automated insights and replace subjective methods with precise quantitative analysis. However, their efficacy depends on representative annotated datasets, which are challenging to obtain due to the costly imaging of nanoparticles and the labor-intensive nature of manual annotations. To overcome these limitations, we introduce DiffRenderGAN, a novel generative model designed to produce annotated synthetic data. By integrating a differentiable renderer into a Generative Adversarial Network (GAN) framework, DiffRenderGAN optimizes textural rendering parameters to generate realistic, annotated nanoparticle images from non-annotated real microscopy images. This approach reduces the need for manual intervention and enhances segmentation performance compared to existing synthetic data methods by generating diverse and realistic data. Tested on multiple ion and electron microscopy cases, including titanium dioxide (TiO2), silicon dioxide (SiO2), and silver nanowires (AgNW), DiffRenderGAN bridges the gap between synthetic and real data, advancing the quantification and understanding of complex nanomaterial systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

On event detection from spatial time series for urban traffic applications

On event detection from spatial time series for urban traffi...

引用

European Conference on Machine Learning, ECML 1989

作者： Souto, Gustavo Liebig, Thomas Fraunhofer Institute for Software and Systems Engineering Fraunhofer ISST Dortmund Germany Artificial Intelligence Group TU Dortmund University Dortmund Germany

ISBN: (纸本)9783319417059

Since the last decades the availability and granularity of location-based data has been rapidly growing. Besides the proliferation of smartphones and location-based social networks, also crowdsourcing and voluntary geographic data led to highly granular mobility data, maps and street networks. In result, location-aware, smart environments are created. The trend for personal self-optimization and monitoring named by the term ‘quantified self’ will speed-up this ongoing process. The citizens in conjunction with their surrounding smart infrastructure turn into ‘living sensors’ that monitor all aspects of urban living (traffic load, noise, energy consumption, safety and many others). The "Big Data"- based intelligent environments and smart cities require algorithms that process these massive amounts of spatio-temporal data. This article provides a survey on event processing in spatio-temporal data streams with a special focus on urban traffic. © Springer International Publishing Switzerland 2016.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Extending PCTE with object-oriented capabilities 4th

Extending PCTE with object-oriented capabilities

引用

4th International Conference on Database and Expert systems Applications, DEXA 1993

作者： Wu, Xuequn Neuhaus, Jan Fraunhofer Gesellschaft Institute for Software Engineering and Systems Engineering c/o University of Dortmund Software Technology DortmundD-44221 Germany

ISBN: (纸本)9783540572343

In this paper we briefly describe our work accomplished for the Eureka ECMA PCTE project. Our task was to define an object-oriented extension to the well-known and internationally standardized Portable Common Tool Environment (PCTE) [3]. The PCTE types are extended to be associated with methods. High-level types are introduced and their mappings to the PCTE data model are discussed. © Springer-Verlag Berlin Heidelberg 1993.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

POTENTIALS AND CHALLENGES OF ARTIFICIAL INTELLIGENCE IN FINANCIAL TECHNOLOGIES 43

POTENTIALS AND CHALLENGES OF ARTIFICIAL INTELLIGENCE IN FINA...

引用

43rd International Conference on Information systems: Digitization for the Next Generation, ICIS 2022

作者： Fabri, Lukas Beck, Sebastian Klos, Tim Wetzstein, Selina Kaymakci, Can Wenninger, Simon University of Applied Sciences Augsburg Branch Business & Information Systems Engineering of the Fraunhofer FIT Augsburg Germany University of Applied Sciences Augsburg Augsburg Germany Fraunhofer Institute for Manufacturing Engineering and Automation IPA Institute for Energy Efficiency in Production EEP Stuttgart Germany Branch Business & Information Systems Engineering of the Fraunhofer FIT Augsburg Germany

ISBN: (纸本)9781713893615

Artificial Intelligence (AI) made disruptive progress over the last years, becoming a key technology across industries. In particular, AI offers novel distinctive potentials for intelligent services in financial technology companies (financial technologies). However, given the potential of AI and its associated benefits, the question arises why financial technologies fail to leverage the full potential of AI. Drawing on existing literature, this paper elaborates on the potential and challenges associated with AI in the financial sector. This paper makes two key contributions: First, we discover the present challenges in literature to demonstrate the need for explainable AI. Second, we reveal the lack of guidance for applying explainable AI in financial technologies. We derive recommendations for research, policy, and practice and argue for the increased elaboration of legal frameworks for the responsible use of AI. © 2022 International Conference on Information systems, ICIS 2022: "Digitization for the Next Generation". All Rights Reserved.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Composition of semantic process fragments to domain-related process families

Composition of semantic process fragments to domain-related ...

引用

作者： Reuter, Claudia Fraunhofer Institute for Software and Systems Engineering Emil-Figge-Str. 91 Dortmund 44227 Germany

ISBN: (纸本)3642167810

Efficient and effective process management is considered as key success factor for competitiveness of enterprises in an increasingly complex and closely connected environment. Today, there exists a plentitude of IT-tools that support modeling, execution, monitoring, and even flexible change of processes. Though, most process management solutions offer possibilities for reusing workflow components, development of new process models is still a cost and time consuming task. Either common process knowledge is scattered among a growing amount of process models or it is divided into unspecific components, the interrelations of which are difficult to manage. This problem becomes even worse considering potential variations of workflows. In the SPOT project, we adapted the feature modeling approach in order to represent enterprise-specific process knowledge in the form of process families. Process families consist of semantically enriched process fragments and enable the composition of business processes that conform to domain-related rules and regulations. © 2010 IFIP International Federation for Information Processing.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A systematic literature review of ecosystems: An approach to introduce logistics ecosystems into academia 8

A systematic literature review of ecosystems: An approach to...

引用

8th International Conference on Information systems, Logistics and Supply Chain: Interconnected Supply Chains in an Era of Innovation, ILS 2020

作者： Lamberjohann, Marvin Otto, Boris Technical University Dortmund Dortmund Germany Fraunhofer Institute for Software and Systems Engineering ISST Dortmund Germany

The term ecosystem experiences a peak in academic attention, however, its usage varies as well as its application in certain industries. In the world of logistics, the usage of the term ecosystem is not common within academia. Hence, a systematic literature review has been performed by scanning 146 studies out of an original dataset of 2264 results. This systematic literature review has got the goal to create a methodological overview of the term ecosystem, create types of ecosystems, and merge them with similar studies out of the supply chain management research area. Finally, this paper identifies a commonality that justifies a merge of supply chain management collaboration approaches and the general research of ecosystems and sets a foundation for future research. © Interconnected Supply Chains in an Era of Innovation - Proceedings of the 8th International Conference on Information systems, Logistics and Supply Chain, ILS 2020. All rights reserved.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Specification technique for augmented reality based product service systems 15

Specification technique for augmented reality based product ...

引用

15th International Design Conference, DESIGN 2018

作者： Röltgen, D. Wortmann, F. Anacker, H. Dumitrescu, R. Fraunhofer Research Institute for Mechatronic Systems Design Product Engineering Zukunftsmeile 1 Paderborn33102 Germany

ISBN: (纸本)9789537738594

As one of the key technologies of digitalization, Augmented Reality (AR) provides significant innovation potentials for the product service business. However, the design of AR-based product service systems proves to be challenging due to interdependencies of product, service and AR functionalities. In this paper, a semi-formal, domain-spanning specification technique is presented. It helps companies to systematically create concepts for product service systems, taking into account the technology-specific requirements of AR, and enables a transparent communication between the domains involved. © 2018 Faculty of Mechanical engineering and Naval Architecture. All Rights Reserved.

关键词： Augmented reality

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：