检索结果-内蒙古大学图书馆

32nd CIRP Design Conference, CIRP Design 2022

作者： Förster, Magdalena Kürpick, Christian Hobscheidt, Daniela Kühn, Arno Dumitrescu, Roman Fraunhofer Institute For Mechatronic Systems Design Zukunftsmeile 1 Paderborn33102 Germany Advances Systems Engineering University Of Paderborn Zukunftsmeile 1 Paderborn33102 Germany

The digital transformation describes a far-reaching change process that does not stop at any industry. Companies and entire industries must realign themselves in order to respond to these fundamental changes of business models and processes. Therefore, digital transformation should be on the strategic agenda of every company, independently from its size and industry. Especially, small and medium-sized enterprises (SMEs) face the challenge of firmly integrating the topic of digital transformation into their strategy. SMEs from all industries have to cope with the general challenge of tackling the issue of digital transformation in a sustainable approach. In addition to this cross-industry challenge, the respective companies face industry-and company-specific tasks when developing their digital strategy. For this reason, this paper presents a procedure model, and a method kit that enables companies in different industries to develop a digital strategy. Within this procedure model, the respective initial situation and industry specific challenge of a company is taken into account. The procedure model is extended by methods for the corresponding strategy development phase to enable companies to elaborate their digital strategy in a problem-specific approach. The application of the procedure model as well as selected methods are within the furniture and the tool manufacturer industry. © 2022 The Authors.

关键词： separated by semicolons Type your keywords here

来源：评论

学校读者我要写书评

暂无评论

Enabling Communication-Efficient Federated Learning via Distributed Compressed Sensing 42

Enabling Communication-Efficient Federated Learning via Dist...

引用

42nd IEEE International Conference on Computer Communications, INFOCOM 2023

作者： Guan, Yixuan Liu, Xuefeng Ren, Tao Niu, Jianwei Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing China Zhongguancun Laboratory Beijing China Chinese Academy of Sciences Laboratory for Internet Software Technologies Institute of Software Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9798350334142

Federated learning (FL) trains a shared global model by periodically aggregating gradients from local devices. Communication overhead becomes a principal bottleneck in FL since participating devices usually suffer from limited bandwidth and unreliable connections in uplink transmission. To address this problem, the gradient compression methods based on compressed sensing (CS) theory have been put forward recently. However, most existing CS-based works compress gradients independently, ignoring the gradient correlations between participants or adjacent communication rounds, which constrains the achievement of higher compression rates. In view of the above observation, we propose a novel gradient compression scheme named FedDCS, guided by distributed compressed sensing (DCS) theory. Following the design philosophy of separate encoding and joint decoding in DCS, FedDCS compresses gradients for participants in each round separately while reconstructing them at the central server jointly via fully exploiting correlated gradients from the previous round, which are known as side information (SI). Benefiting from this design, reconstruction performance is significantly improved with fewer decoding errors also iterations under the identical compression rate, and the total uploading bits to achieve model convergence are considerably reduced. Theoretical analysis and extensive experiments conducted on MNIST and Fashion-MNIST both verify the effectiveness of our approach. © 2023 IEEE.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Aspect-Based Sentiment Analysis on Amharic Text for Evaluating Ethio-Telecom Services 2

Aspect-Based Sentiment Analysis on Amharic Text for Evaluati...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Tesfa, Tarikwa Belete, Befikadu Abera, Samuel Mohapatra, Sudhir Kumar Das, Tapan Kumar Addis Ababa Science and Technology University Department of Software Engineering Addis Ababa Ethiopia Ethio Telecom Services Addis Ababa Ethiopia Sri Sri University Faculty of Emerging Technologies Cuttack India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350328202

People are increasingly expressing their views and opinions about a company's goods or service on social media these days. For all types of businesses and organizations, sentiment analysis in text can be used to find prospective customers and obtain quick feedback on the services or goods they provided. As a result, the organization has a better chance and opportunity to meet the needs of the consumer. Using sentiment analysis, we may extract important information from the thoughts and emotions of an organization's supporters and clients. It examines natural language content produced about services and goods. Detailed opinion mining at the aspect/feature level to serve consumer and organizational needs. In this study, three different machine learning algorithms, these are Naïve Bayes (NB), Support Vector Machine (SVM), and K- Nearest Neighbor (KNN) are used to build the proposed aspect-based sentiment analysis model from the customer comments in Amharic text which is collected from Ethio-telecom official Facebook page. The collected data is annotated into sentiment polarity and aspect-based sentiment classes by the help of five annotators. After data annotation, different preprocessing tasks were implemented. Bag of words and TF-IDF word representation techniques were used to represent each unique word to their vector representation. The experiment was conducted on those three models and the result was validated. The labeled aspects were not balanced so that a SMOTE class imbalance handling technique was employed to the dataset. Finally, SVM model trained with TF-IDF word representation technique with SMOTE oversampled dataset has achieved the highest accuracy result of 98% as compared to NB and KNN. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

SafeSens - Uncertainty Quantification of Complex Perception systems

SafeSens - Uncertainty Quantification of Complex Perception ...

引用

International Conference on Intelligent Transportation

作者： Iwo Kurzidem Simon Burton Philipp Schleiss Systems Safety Engineering Fraunhofer Institute for Cognitive Systems IKS Munich Germany Research Division Safety Fraunhofer Institute for Cognitive Systems IKS Munich Germany

Safety testing and validation of complex autonomous systems requires a comprehensive and reliable analysis of performance and uncertainty. Especially uncertainty quantification plays a vital part in perception systems operating in open context environments that are neither foreseeable nor deterministic. Therefore, safety assurance based on field tests or corner cases alone is not a feasible option as effort and potential risks are high. Simulations offer a way out. They allow, for example, simulation of potentially hazardous situations, without any real danger, by systematically computing a variety of different (input) parameters quickly. In order to do so, simulations need accurate models to represent the complex system and in particular include uncertainty as inherent property to accurately reflect the interdependence between system components and the environment. We present an approach to creating perception architectures via suitable meta-models to enable a holistic safety analysis to quantify the uncertainties within the system. The models include aleatoric or epistemic uncertainty, dependent on the nature of the approximated component. A showcase of the proposed method highlights, how validation under uncertainty can be used for a camera-based object detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SPECIFICATION-GUIDED TEMPORAL LOGIC CONTROL FOR STOCHASTIC systems: A MULTI-LAYERED APPROACH

arXiv

引用

arXiv 2024年

作者： van Huijgevoort, Birgit C. Wang, Ruohan Soudjani, Sadegh Haesaert, Sofie The Department of Electrical Engineering TU Eindhoven Netherlands The Max Planck Institute for software systems Germany

Designing controllers to satisfy temporal requirements has proven to be challenging for dynamical systems that are affected by uncertainty. This is mainly due to the states evolving in a continuous uncountable space, the stochastic evolution of the states, and infinite-horizon temporal requirements on the system evolution, all of which makes closed-form solutions generally inaccessible. A promising approach for designing provably correct controllers on such systems is to utilize the concept of abstraction, which is based on building simplified abstract models that can be used to approximate optimal controllers with provable closeness guarantees. The available abstraction-based methods are further divided into discretization-based approaches that build a finite abstract model by discretizing the continuous space of the system, and discretization-free approaches that work directly on the continuous state space without the need for building a finite space. To reduce the conservatism in the sub-optimality of the designed controller originating from the abstraction step, this paper develops an approach that naturally has the flexibility to combine different abstraction techniques from the aforementioned classes and to combine the same abstraction technique with different parameters. First, we develop a multi-layered discretization-based approach with variable precision by combining abstraction layers with different precision parameters. Then, we exploit the advantages of both classes of abstraction-based methods by extending this multi-layered approach guided by the specification to combinations of layers with respectively discretization-based and discretization-free abstractions. We achieve an efficient implementation that is less conservative and improves the computation time and memory usage. We illustrate the benefits of the proposed multi-layered approach on several case studies. © 2024, CC BY-NC-SA.

关键词： Specifications

来源：评论

学校读者我要写书评

暂无评论

Framework for Dual Transformation: A Systematic Literature Review on the Interplays between Digitalization and Sustainability

Framework for Dual Transformation: A Systematic Literature R...

引用

Conference on Technologies for Sustainability (Sustech)

作者： Christian Kürpick Arno Kühn Luca Olszewski Roman Dumitrescu Product Engineering Fraunhofer Institute for Mechatronic Systems Design IEM Paderborn Germany Advanced Systems Engineering Heinz Nixdorf Institute / University of Paderborn

Digitalization and sustainability are two central fields of action in the company that are of crucial importance for future business success. The necessary transformation represents a strategically relevant and time-critical task for manufacturing companies that requires an integrative approach in the sense of a dual transformation. Successfully linking digitalization and sustainability enables companies to create long-term competitive advantages in the market for example by developing smart and sustainable products. Despite the strategic relevance, digital and sustainability transformation are often considered separately in corporate practice. One reason for this is that the interplays between digitalization and sustainability in the industrial context are multilayered and complex. This leads to a lack of transparency due to the broad spectrum of the entire research field. Therefore, we conducted a systematic literature review (SLR) to identify similarities and differences between digital and sustainability transformation. The analysis of the existing literature reveals several interplays that both transformation processes have. Based on the core results, we propose a framework for dual transformation supporting decision-makers in corporate practice.

关键词： Systematics Bibliographies Companies Manufacturing Time factors Sustainable development Task analysis

来源：评论

学校读者我要写书评

暂无评论

Design proposal and optimization potential for an electric drive motor in a 50 PAX hybrid-electric regional aircraft application 11

Design proposal and optimization potential for an electric d...

引用

11th International Conference on Power Electronics - ECCE Asia, ICPE 2023-ECCE Asia

作者： Meindl, M. Liu, X.J. Hilpert, F. Marciello, Valerio Di Stasio, Mario Maerz, M. Friedrich-Alexander-Universität Erlangen-Nürnberg Institute of Power Electronics Germany Fraunhofer Institute for Integrated Systems and Device Technology Iisb Germany University of Naples "Federico II" Department of Industrial Engineering Italy

ISBN: (纸本)9788957083505

Electric propulsion systems are considered one possibility to reach the ambitious goals of the European Union's Flightpath 2050 concerning greenhouse gas emissions and noise. This paper proposes an engineering architecture design of an electric motor for a propulsion system in a hybrid-electric regional aircraft. The project partners defined the performance requirements for the thrust of the propulsion system. The electric drive motor for the propellers was calculated and then simulated. The motor is specified in this paper, with the materials possible for construction. © 2023 The Korean institute of Power Electronics.

关键词： Electric drives

来源：评论

学校读者我要写书评

暂无评论

The Need for Smart Shop Floor Management in the Automotive Industry: Potentials, Challenges and Requirements 6

The Need for Smart Shop Floor Management in the Automotive I...

引用

6th International Conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Kutz, Janika Viljoen, Altus Feike, Maximilian Przybilla, Leonard Guhl, Jakob Neuhüttler, Jens Krcmar, Helmut Fraunhofer IAO Fraunhofer Institute for Industrial Engineering IAO Heilbronn74076 Germany Informatik 17 - Information Systems and Business Process Management Krcmar Lab Technical University of Munich i17 Boltzmannstraße 3Garching b München85748 Germany Bauhaus-University Weimar Weimar99423 Germany

Industry 4.0 and the accompanying digital transformation of the modern-day factory have led to various advances in manufacturing. Shop floor management (SFM) - a core instrument of production management - has to align with these digital advances as well. However, due to SFM's strong human-centric roots and manufacturers predominantly conducting SFM through analog means, it raises the question of what sort of digital support should be used for SFM and what specifications should be included in digital SFM systems. This study, consisting of a case study comprising semi-structured interviews and on-site inspections at a large original equipment manufacturer (OEM), provides concrete requirements for digitally-supported SFM derived from practice. We investigated which elements from analog SFM should be retained and where possible improvements through digital support exist. Moreover, we identified definitive improvement potentials such as the aggregation of data sources, as well as the preparation, performance, and documentation of shop floor meetings without disruptions in information flows. We conclude that digital transformation in the SFM context neither implies the mere introduction of software to solve specific problems, nor the full automation of SFM processes through digital solutions (what we call "digital" SFM). Rather, we highlight the importance of "smart SFM": the adoption of sociotechnical systems in which SFM's traditional social characteristics are maintained but are simultaneously sensibly augmented with digital solutions to improve SFM processes. © 2025 Elsevier B.V.. All rights reserved.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Diving into Continual Ultra-fine-grained Visual Categorization

Diving into Continual Ultra-fine-grained Visual Categorizati...

引用

2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023

作者： Zhang, Pengcheng Yu, Xiaohan Bai, Xiao Zheng, Jin Wu, Xiaoyu Gao, Yongsheng Beihang University School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beijing China Griffith University Institute for Integrated and Intelligent Systems Nathan4111 Australia

ISBN: (纸本)9798350382204

Recent advance in ultra-fine-grained visual categorization (ultra-FGVC) has significantly boosted the capability of deep neural networks for ultra-FGVC tasks. However, building models for continually learning to recognize increasing ultra-fine-grained categories is still under-explored. This limits the application of ultra-FGVC techniques in real-world production. To this, we take the first attempt for continual ultra-FGVC. By evaluating existing continual learning methods on the constructed continual ultra-FGVC benchmark, we observe that the main bottleneck lies in the limited model plasticity for incrementally adapting to new tasks. This can be caused by excessive anti-forgetting constraints as the difficult ultra-FGVC task requires substantial update of parameters, and over-fitting on early tasks given that the ultra-fine-grained categories are with very few training samples. To tackle these problems, we propose a joint self-supervised learning and prompting model. The prompt-based continual learning framework offers proper anti-forgetting operation by fixed pretrained vision transformer and adaptive prompt selection. By jointly optimizing the learnable prompts with an adversarial self-supervised loss, the over-fitting on each continual learning task is mitigated. Extensive experiments demonstrate that the proposed method outperforms existing continual learning methods on the challenging continual ultra-FGVC problem. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Safe Control Architecture Based on Robust Model Predictive Control for Autonomous Driving

A Safe Control Architecture Based on Robust Model Predictive...

引用

2022 American Control Conference, ACC 2022

作者： Nezami, Maryam Nguyen, Ngoc Thinh Mannel, Georg Abbas, Hossam Seddik Schildbach, Georg University of Lübeck Institute for Electrical Engineering in Medicine Lübeck Germany University of Lübeck Institute for Robotics and Cognitive Systems Lübeck Germany Fraunhofer Imte Fraunhofer Research Institution for Individualized and CellBased Medical Engineering Lübeck Germany

ISBN: (数字)9781665451963

ISBN: (纸本)9781665451963

This paper proposes a Robust Safe Control Architecture (RSCA) for safe-decision making. The system to be controlled is a vehicle in the presence of bounded disturbances. The RSCA consists of two parts: a Supervisor MPC and a Controller MPC. Both the Supervisor and the Controller are tube MPCs (TMPCs). The Supervisor MPC provides a safety certificate for an operating controller and a backup control input in every step. After an unsafe action by the operating controller is predicted, the Controller MPC takes over the system. In this paper, a method for the computation of a terminal set is proposed, which is robust against changes in the road curvature and forces the vehicle to reach a safe reference. Moreover, two important proofs are provided in this paper. First, it is shown that the backup control input is safe to be applied to the system to lead the vehicle to a safe state. Next, the recursive feasibility of the RSCA is proven. By simulating some obstacle avoidance scenarios, the effectiveness of the proposed RSCA is confirmed. © 2022 American Automatic Control Council.

关键词： Controllers

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：