检索结果-内蒙古大学图书馆

Hydrodynamic parameter estimation using statistical machine learning for dynamic radiography

Hydrodynamic parameter estimation using statistical machine ...

2023 Computational Optical Sensing and Imaging, COSI 2023 in Optica Imaging Congress - Part of Imaging and Applied Optics Congress 2023

作者： De, Soumi Klasky, Marc Korobkin, Oleg Sidharth, G.S. Xu, Xiaojian Computer Computational and Statistical Sciences Division Los Alamos National Laboratory United States Theoretical Division Los Alamos National Laboratory United States Department of Aerospace Engineering Iowa State University United States Department of Electrical Engineering & Computer Science University of Michigan United States

Characterization of material properties of objects undergoing strong deformations is an important task in material science. Using neural networks with dynamic features extracted from radiographic projections we obtain... 详细信息

ISBN: (纸本)9781957171289

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

FedDGA: Federated Multitask Learning Based on Dynamic Guided Attention

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 268-280页

作者： Sun, Haoyun Zhao, Hongwei Xu, Liang Zhang, Weishan Guan, Hongqing Yang, Su China University of Petroleum Qingdao266580 China Shandong Data Open Innovative Application Laboratory Qingdao266580 China WINDAKA Technology Company Ltd. Qingdao266580 China Beijing University of Science and Technology Beijing100083 China Swansea University Department of Computer Science Faculty of Science and Engineering SwanseaSA2 8PP United Kingdom

The proliferation of privacy-sensitive data has spurred the development of federated learning (FL), which is an important technology for state-of-the-art machine learning and responsible AI. However, most existing FL methods are constrained in their applicability and generalizability due to their narrow focus on specific tasks. This article presents a novel federated multitask learning (FMTL) framework that is capable of acquiring knowledge across multiple tasks. To address the challenges posed by non-IID data and task imbalance in FMTL, this study proposes a federated fusion strategy based on dynamic guided attention (FedDGA), which adaptively fine-tunes local models for multiple tasks with personalized attention. In addition, this article designed dynamic batch weight (DBW) to balance the task losses and improve the convergence speed. Extensive experiments were conducted on various datasets, tasks, and settings, and the proposed method was compared with state-of-the-art methods such as FedAvg, FedProx, and SCAFFOLD. The results show that our method achieves significant performance gains, with up to 11.1% increase in accuracy over the baselines. © 2020 IEEE.

关键词： Scaffolds

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Cloud Computing in Wireless Communications 2

A Comprehensive Analysis of Cloud Computing in Wireless Comm...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Bansal, Anurag Sharma, Surbhi Shukla, Ajay Narayan Badhoutiya, Arti Research and Technology 13D Research & Strategy India Abes Engineering College Department of Computer Applications UP Ghaziabad India Computer Science & Engineering Graphic Era Hill University Uttarakhand Dehradun India Gla University Department of Electrical Engineering UP Mathura India

ISBN: (纸本)9798350371055

In the present-day digital landscape, cloud computing has grown to be a ubiquitous generation that offers numerous advantages to numerous businesses. Its software in wi-fi communications has had a mainly revolutionary effect, ultimately converting how data is transferred, considered, and saved. This looks at a thorough examination of how cloud computing has affected wireless communications, including its records, most important ideas, and programs. The primary phase of the object appears to be how cloud computing has changed over the years, moving from conventional on-premise computing to its current country, which includes a spread of service offerings and deployment methodologies. Subsequently, it explores the fundamental thoughts of cloud computing, which have virtualization, scalability, and on-demand provisioning, and talks about how these apply to wireless communications. The ability of cloud computing to grow network availability and dependability is one of its primary benefits for wi-fi communications. Using cloud-based computing and garage sources, network operators may additionally lower downtime and increase uptime for their services. They can also better manage unforeseen surges in community visitors and provide a higher user revel. The look additionally addresses how cloud computing helps the short rollout of the latest services and packages within the wireless communications industry. © 2024 IEEE.

关键词： Cloud Computing Data Storage Mobile Technology Network Security Wireless Communications

来源：评论

学校读者我要写书评

暂无评论

Enhancing Stockpile Management Through Deep Learning with a Focus on Demand Forecasting and Inventory Optimization

Enhancing Stockpile Management Through Deep Learning with a ...

引用

2024 IEEE International Conference on Recent Advances in science and engineering Technology, ICRASET 2024

作者： Sheela, S. Latha, A.P. Jyothi, S. Vidyarani, H.J. Komala, M. Sharmila, N. Mallikarjunaswamy, S. Pavithra, G.S. Global Academy of Technology Department of Computer Science and Engineering Bengaluru India Dayananda Sagar College of Engineering Department of Information Science and Engineering Bengaluru India Dr. Ambedkar Institute of Technology Department of Information Science and Engineering Bengaluru India Sjb Institute of Technology Dept of Electronics and Communication Engineering Bengaluru India Jss Science and Technology University Dept of Electronics and Electrical Engineering Mysuru India Jss Academy of Technical Eduction Dept of Electronics and Communication Engineering Bengaluru India Rns Insitute of Technology Dept of Computer Science and Alml Bengaluru India

ISBN: (纸本)9798350388602

Stockpile management is essential for industries to efficiently meet customer demands while minimizing costs. Traditional methods like the Economic Order Quantity (EOQ) model and ARIMA often struggle with adaptability and accuracy, leading to inefficiencies such as overstocking or stockouts. This study proposes using Long Short-Term Memory (LSTM) networks to improve demand forecasting in stockpile management. LSTMs are designed to handle sequential data, capturing complex patterns and long-term dependencies that conventional methods miss. The LSTM-based approach achieved up to a 0.30% improvement in forecasting accuracy, resulting in more precise inventory control and better alignment with actual demand. The proposed system, termed Deep Inventory Management (DIM), incorporates LSTM models that adapt to changes in demand by considering factors such as seasonality and trends. This adaptive approach allows for proactive inventory predictions, enhancing decision-making in procurement and stock levels. Key abbreviations include LSTM (Long Short-Term Memory), EOQ (Economic Order Quantity), and DIM (Deep Inventory Management). By aligning inventory more closely with demand, this deep learning approach enhances operational efficiency, reduces costs, and improves customer satisfaction, making it a valuable advancement over traditional inventory management methods. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Thermoelastic damping in MEMS gyroscopes at high frequencies

引用

Microsystems & Nanoengineering 2023年第1期9卷 137-148页

作者： Daniel Schiwietz Eva M.Weig Peter Degenfeld-Schonburg Robert Bosch GmbH Corporate Research71272RenningenGermany Department of Electrical&Computer Engineering Technical University of Munich85748GarchingGermany Munich Center for Quantum Science and Technology(MCQST) 80799MunichGermany TUM Center for Quantum Engineering(ZQE) 85748GarchingGermany

Microelectromechanical systems(MEMS)gyroscopes are widely used,e.g.,in modern automotive and consumer applications,and require signal stability and accuracy in rather harsh environmental *** many use cases,device reliability must be guaranteed under large external loads at high *** sensitivity of the sensor to such external loads depends strongly on the damping,or rather quality factor,of the high-frequency mechanical modes of the *** this paper,we investigate the influence of thermoelastic damping on several high-frequency modes by comparing finite element simulations with measurements of the quality factor in an application-relevant temperature *** measure the quality factors over different temperatures in vacuum,to extract the relevant thermoelastic material parameters of the polycrystalline MEMS *** simulation results show a good agreement with the measured quantities,therefore proving the applicability of our method for predictive purposes in the MEMS design ***,we are able to uniquely identify the thermoelastic effects and show their significance for the damping of the high-frequency modes of an industrial MEMS *** approach is generic and therefore easily applicable to any mechanical structure with many possible applications in nano-and micromechanical systems.

关键词： uniquely generic quantities

来源：评论

学校读者我要写书评

暂无评论

Choice of Optimal Voltage for DC Power Distribution Systems on More Electric Aircraft

Choice of Optimal Voltage for DC Power Distribution Systems ...

引用

2024 Energy Conversion Congress and Expo Europe, ECCE Europe 2024

作者： Wang, Xin Atkin, Jason Yeoh, Seang Shen Bozhko, Serhiy University of Nottingham Faculty of Engineering The Department of Electrical and Electronic Engineering Nottingham United Kingdom University of Nottingham Computational Optimisation and Learning Lab School of Computer Science Nottingham United Kingdom

ISBN: (纸本)9798350364446

The new generation of aircraft will experience increasing electrical power demands because of the more electric trends and advances in recent years. Adopting higher voltage levels is widely discussed for More Electric Aircraft (MEA) Power Distribution Systems (PDSs) to efficiently deliver the increased power ratings and reduce the system weight. However, higher voltage levels also indicate the risk of electrical insulation failures. Hence, it is essential to select optimised voltage levels for onboard PDSs considering the trade-offs. In addition, the relationship between the PDS weight/efficiency and voltage levels is complex rather than linear, resulting in infeasibility issues when optimising voltage levels. This study proposes a voltage optimisation method based on selecting among a set of components, i.e., converters and cables, for onboard DC PDSs. Moreover, to improve feasibility, the Integrated Converter Component (ICC) concept is proposed to combine each converter with its lightest input/output cables as an integrated block. Hence, the optimal bus voltages can be decided by selecting the lightest and most efficient ICCs while meeting the power delivery and voltage conversion requirements. © 2024 IEEE.

关键词： Bus voltage DC power distribution integrated converter component more electric aircraft optimisation

来源：评论

学校读者我要写书评

暂无评论

Enhancing supply chain security through laser-fabricated marks on stainless steel 19

Enhancing supply chain security through laser-fabricated mar...

引用

Laser-based Micro- and Nanoprocessing XIX 2025

作者： Tselios, Christos Mazzucato, Simone Politi, Christina Alexandropoulos, Dimitris Department of Electrical and Computer Engineering University of Patras Achaia Patras26504 Greece Department of Electrical and Computer Engineering University of Peloponnese Achaia Patras22100 Greece SISMA S.p.A. via dell’Industria 1 Piovene Rocchette VI36013 Italy Department of Materials Science University of Patras Achaia Patras26504 Greece

ISBN: (纸本)9781510684508

We present a novel method for generating cryptographic keys from laser-engraved holograms on stainless steel, designed to enhance supply chain security with a focus on industrial scalability, ease of verification, and compliance with National Institute of Standards and Technology (NIST) standards. Using laser-writing technology and off-the-shelf components for key extraction, our approach provides a straightforward, cost-effective, and reliable authentication mechanism between manufacturers and end users. By applying image processing and randomness extraction algorithms, we generate 16-kbit cryptographic keys from each engraving. To validate the effectiveness of these laser-fabricated marks, we analyze correlation coefficient maps and Hamming distance distributions between key sequences from different engravings, demonstrating minimal similarity and enhanced security. Furthermore, the generated 160-kbit key sequences successfully passed all statistical tests of the NIST SP 800-22 test suite. This method offers a practical and scalable solution for anti-counterfeiting and security in real-world applications. © 2025 SPIE.

关键词： Holograms

来源：评论

学校读者我要写书评

暂无评论

Adaptive delay-energy balanced partial offloading strategy in Mobile Edge Computing networks

引用

Digital Communications and Networks 2023年第6期9卷 1310-1318页

作者： Shumei Liu Yao Yu Lei Guo Phee Lep Yeoh Branka Vucetic Yonghui Li School of Computer Science and Engineering Northeastern UniversityShenyang110819China Key Laboratory of Intelligent Computing in Medical Image Ministry of EducationNortheastern UniversityShenyang110819China School of Communication and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing400065China School of Electrical and Information Engineering University of SydneySydneyNSW2006Australia

Mobile Edge Computing(MEC)-based computation offloading is a promising application paradigm for serving large numbers of users with various delay and energy *** this paper,we propose a flexible MECbased requirement-adaptive partial offloading model to accommodate each user's specific preference regarding delay and energy *** address the dimensional differences between time and energy,we introduce two normalized parameters and then derive the computational overhead of processing *** from existing works,this paper considers practical variations in the user request patterns,and exploits a flexible partial offloading mode to minimize computation overheads subject to tolerable delay,task workload and power *** the resulting problem is non-convex,we decouple it into two convex subproblems and present an iterative algorithm to obtain a feasible offloading *** experiments show that our proposed scheme achieves a significant improvement in computation overheads compared with existing schemes.

关键词： Mobile edge computing(MEC) Delay Energy consumption Dynamic balance Partial computation offloading

来源：评论

学校读者我要写书评

暂无评论

Classification of Real and Deepfakes Visual Samples with Pre-trained Deep Learning Models 7th

Classification of Real and Deepfakes Visual Samples with Pre...

引用

Proceedings of the 7th International Conference on Advances in Computing and Data sciences, ICACDS 2023

作者： Nawaz, Marriam Javed, Ali Nazir, Tahira Khan, Muhammad Attique Rajinikanth, Venkatesan Kadry, Seifedine Department of Software Engineering UET Taxila Taxila47050 Pakistan Department of Computing Riphah International University Islamabad Pakistan Department of Computer Science HITEC University Taxila Pakistan Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India Department of Applied Data Science Noroff University College Kristiansand4612 Norway Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

ISBN: (纸本)9783031379390

Serious security and privacy problems have arisen as a result of significant advancements in the creation of deepfakes. Attackers can easily replace a person’s face with the target person’s face in an image using sophisticated Deep learning (DL) algorithms to spoof their identity. Deepfakes detection algorithms have been proposed in response to the growing concerns about the potential harm caused by deepfakes. However, a reliable deepfakes detector that can keep up with contemporary deepfakes creation techniques is required. In this work, we have proposed an end-to-end methodology for detecting manipulated visual content. We used multiple CNN models i.e., ResNet18, ResNet50, DenseNet65, DenseNet77, and DenseNet100 along with the SVM classifier to compute effective cues from the input facial faces to distinguish between actual and altered content. We have also applied the concept of transfer learning to solve the issue of model over-fitting and improve generalizability against different manipulation algorithms. A comparison study is carried out to evaluate the performance of several feature extractors. Through thorough experiments performed using the Deepfakes Detection Challenge dataset, our results demonstrated that DenseNet100 surpasses the other CNN models by better recognizing deepfakes. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Identifying and Addressing Security Vulnerabilities in Hybrid Network Security Algorithms

Identifying and Addressing Security Vulnerabilities in Hybri...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Pipersenia, Arun Kumar Nidhya, M.S. Jain, Sandeep Kumar College of Engineering Teerthanker Mahaveer University Uttar Pradesh Moradabad India Department of Computer Science and Information Technology Bangalore India Electrical Engineering Vivekananda Global University Jaipur India

ISBN: (纸本)9798350383348

Hybrid network protection algorithms represent a critical vicinity in facts safety techniques. Inside the computation of networking environments, such algorithms provide a cozy and dependable mechanism for site visitor management, records storage, entry to manipulation, and so on. The security of this mechanism is, but suffering from the presence of certain safety vulnerabilities within the gadget. To ensure the powerful operation of modern-day networks, these vulnerabilities need to be identified and addressed. This paper explores some of the procedures to be had for the identification and addressing of the safety vulnerabilities in hybrid community security algorithms: The security goals the ones want to be worked on, consisting of authentication, authorization, records integrity, and confidentiality, are mentioned. Several assault fashions, consisting of insider attacks, man-in-the-center assaults, and brute-pressure assaults, are also stated to detail the vulnerabilities in hybrid protection algorithms. Modern practices for figuring out and addressing safety vulnerabilities in hybrid community security algorithms are supplied. Those consist of techniques which include reading network site visitors, assessing the trustworthiness of customers, enforcing encryption techniques, and applying community entry to controls. Several protection models, in addition to protocols for reaching secure verbal exchange in hybrid networks, are examined. © 2024 IEEE.

关键词： Algorithms Critical Examined Network Protection Vicinity

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：