检索结果-内蒙古大学图书馆

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Meng, Dan Fu, Zhihui Kong, Chao Qi, Yue Cao, Guitao Oppo Research Institute Shenzhen China Anhui Polytechnic University School of Computer and Information Wuhu China East China Normal University Shanghai Key Laboratory of Trustworthy Computing Shanghai China MoE Engineering Research Center of SH/HW Co-design Technology and Application Ecnu Shanghai China

ISBN: (纸本)9798350346558

Federated learning (FL) is proposed to enable efficient machine learning while protecting the privacy of user data. In non-federated scenarios, machine learning models are vulnerable to adversarial attacks. The attacker can construct elaborate adversarial examples, which can greatly reduce the performance of the victim model. It is worth exploring how FL models differ from traditional models in face of complex adversarial attacks. We are also curious about the robustness of different FL modeling methods against adversarial attacks, providing suggestions for selecting suitable FL models in practical applications. Consequently, we perform adversarial example attacks on vertical federated learning and design experiments to study how vertical federated models perform under adversarial example attacks. The simulation results show that federated models are more robust than non-federated models. Besides, in vertical federation learning, decision trees and XGBoost are much more robust than logistic regression and neural networks. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation of Kvlcc2 Self-Propulsion with Ducted Propeller in Head Waves

SSRN

引用

SSRN 2023年

作者： Cai, Boao Mao, Xiaofei Xu, Qing Chai, Wei Tian, Binbin Qiu, Liaoyuan Zhan, Xingyu Ministry of Education Wuhan430063 China China Ship Development and Design Center Wuhan430064 China School of Naval Architecture Ocean and Energy Power Engineering Wuhan University of Technology Wuhan430063 China

In order to meet the Energy Efficiency design Index (EEDI) requirements, consideration of reducing added power in waves is important for large tankers operating in ocean environments. In this study, the Reynolds-averaged Navier-Stokes (RANS) solver is employed in Computational Fluid Dynamics (CFD) method to simulate the self-propulsion of KVLCC2 model with a ducted KP458 propeller in head waves, especially for comparison with the non-ducted cases. Two methods are adopted for simulating the ducted propeller: the discretized propeller method and the improved body force ducted propeller method. The latter method incorporates an improved principle of momentum conservation to solve the advance speed of the ducted virtual disk precisely in real time, resulting in similar accuracy and higher efficiency compared to the former method. For some wavelengths, the ducted cases display higher propulsive efficiency and lower power than the non-ducted cases, especially under very short wavelength conditions, where negative thrust deduction fraction is observed in the ducted case. With the increase of wave height, the effect of the duct becomes more pronounced, resulting in an increase in propulsive efficiency and a reduction in power, both of which can exceed 10%. © 2023, The Authors. All rights reserved.

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

design and preliminary evaluation of a deployable mobile makerspace for informal additive manufacturing education 28

Design and preliminary evaluation of a deployable mobile mak...

引用

28th Annual International Solid Freeform Fabrication Symposium - An Additive Manufacturing Conference, SFF 2017

作者： Sinha, Swapnil Rieger, Kelsey Knochel, Aaron D. Meisel, Nicholas A. Made By Design Laboratory School of Engineering Design Technology and Professional Programs Penn State United States School of Visual Arts Penn State United States

Additive Manufacturing (AM) has played an integral part in the growth of makerspaces as democratization of manufacturing continues to evolve. AM has also shown potential in enabling the successful amalgamation of art (A) with science, technology, engineering, and math (STEM) disciplines, giving new possibilities to STEAM subjects and its implementation. This paper presents the conceptual design and development of a deployable, mobile makerspace curriculum focused on AM education for a diverse range of participant backgrounds, ages, and locations. The aim is to identify effective means of informal learning to broaden participation and increase engagement with STEAM subjects through the context of AM. The curriculum is envisioned as "material-to-form," offering separate modules that present opportunities for self-directed learning through all the stages of design, material use, and manufacturing associated with AM. Pilot studies of the curriculum were performed to identify potential changes to improve the effectiveness of the mobile makerspace. Copyright © SFF *** rights reserved.

关键词： 3D printers

来源：评论

学校读者我要写书评

暂无评论

Timetable Rescheduling for High-Speed Trains Based on a Multi-Agent Game Reinforcement Learning Method

Timetable Rescheduling for High-Speed Trains Based on a Mult...

引用

IEEE International Conference on Industrial technology (ICIT)

作者： Xiaomin Zhou Min Zhou Junfeng Cui Haifeng Song Hairong Dong School of Automation and Intelligence Beijing Jiaotong University Beijing China China Railway Signal and Communication Research & Design Institute Group Co. Ltd. Beijing China School of Electronic and Information Engineering Beihang University Beijing China Shandong University of Science and Technology Qingdao China Beijing Jiaotong University Beijing China

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

As the high-speed rail network grows, unexpected disruptions affecting train operations have become increasingly common. Consequently, efficiently adjusting train schedules to minimize delays has become a critical challenge in high-speed rail timetable rescheduling (TTR). To address this issue, this paper proposes a Multi-Agent Game Deep Reinforcement Learning (MAGDRL) approach to tackle the TTR problem during a complete blockage. Initially, the paper defines the MAGDRL state and action spaces, incorporating spatiotemporal distribution information, and develops an effective reward feedback system. Next, the Nash-Q learning algorithm ensures convergence to the Nash equilibrium strategy. Additionally, an approximate Nash equilibrium solving method is applied to enhance the computational efficiency of determining the Nash equilibrium strategy. Finally, simulation results based on the Beijing-Shanghai high-speed railway demonstrate that the proposed method effectively handles timetable rescheduling across multiple disruption scenarios involving complete blockages of segments.

关键词： Schedules Simulation Games Nash equilibrium Approximation algorithms Rail transportation Spatiotemporal phenomena Computational efficiency Delays Convergence

来源：评论

学校读者我要写书评

暂无评论

Pioneering Sodium Storage Solutions: Transition Metal Ion Enhancement and Cellulose Coating for Superior Performance

SSRN

引用

SSRN 2025年

作者： Chen, Xiangrui Zhao, Dengke Liu, Xupo Gao, Zhiyong Wang, Gongke Cao, Xiaoyu School of Materials Science and Engineering Henan Engineering Research Center of Design and Recycle for Advanced Electrochemical Energy Storage Materials Henan Normal University Henan Xinxiang453007 China School of Chemistry and Chemical Engineering Key Laboratory of Green Chemical Media and Reactions Ministry of Education Collaborative Innovation Center of Henan Province for Green Manufacturing of Fine Chemicals Henan Normal University Henan Xinxiang453007 China School of Chemistry and Chemical Engineering Henan University of Technology Zhengzhou450001 China School of Materials Science and Engineering Henan Normal University 46 Jian-she Road Mu Ye District Xinxiang453007 China

Identifying materials with high charge-discharge rates and kinetic performance is a crucial step in the development of sodium-ion battery systems. Due to their high capacity per unit mass and economic viability, transition metal sulphides have shown great potential as anode candidates. Herein, we conduct a comparative analysis of the performance of transition metal sulfides (XS2, X = Fe, Co or Ni) coated with CM as anodes in sodium storage systems. By optimizing the transition metal cations, we were able to achieve materials with enhanced crystallinity and a more uniform particle size. It is noteworthy that FeS₂ exhibited superior Na+ diffusion rates in comparison to CoS₂ and NiS₂, which resulted in enhanced cycling durability and rapid-charge/discharge capability. notably, FeS₂ exhibited an exceptional capacity of 594.2 mAh g−1 at 1 A g−1, which is due to its physical-chemical stability, rapid kinetics. This universal approach can broaden the design horizons for advanced electrodes, particularly in alkaline ion batteries. By harnessing the distinct properties of transition metal sulfides, we can make unique contributions to the development of more efficient and safer energy storage systems. © 2025, The Authors. All rights reserved.

关键词： Sodium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Dispersion-Selective Band engineering in an Artificial Kagome Superlattice

引用

Physical Review Letters 2024年第6期133卷 066302-066302页

作者： Shuai Wang Zhen Zhan Xiaodong Fan Yonggang Li Pierre A. Pantaleón Chaochao Ye Zhiping He Laiming Wei Lin Li Francisco Guinea Shengjun Yuan Changgan Zeng CAS Key Laboratory of Strongly-Coupled Quantum Matter Physics and Department of Physics International Center for Quantum Design of Functional Materials (ICQD) Hefei National Research Center for Physical Sciences at the Microscale Key Laboratory of Artificial Micro- and Nano-structures of the Ministry of Education and School of Physics and Technology Madrid 28015 Spain School of Advanced Manufacturing Engineering Hefei National Laboratory Paseo Manuel de Lardizabal 4 San Sebastian 20018 Spain Wuhan Institute of Quantum Technology Wuhan Hubei 430206 China

The relentless pursuit of band structure engineering continues to be a fundamental aspect in solid-state research. Here, we meticulously construct an artificial kagome potential to generate and control multiple Dirac bands of graphene. This unique high-order potential harbors natural multiperiodic components, enabling the reconstruction of band structures through different potential contributions. As a result, the band components, each characterized by distinct dispersions, shift in energy at different velocities in response to the variation of artificial potential. Thereby, we observe a significant spectral weight redistribution of the multiple Dirac peaks. Furthermore, the magnetic field can effectively weaken the superlattice effect and reactivate the intrinsic Dirac band. Overall, we achieve actively dispersion-selective band engineering, a functionality that would substantially increase the freedom in band design.

关键词： Electronic structure Flat bands Local density of states Transport phenomena 2-dimensional systems Graphene Kagome lattice Band structure methods Tight-binding model Transport techniques

来源：评论

学校读者我要写书评

暂无评论

Nonlinear dynamic analysis of low viscosity fluid-lubricated tilting-pad journal bearing for different design parameters

引用

Friction 2020年第5期8卷 930-944页

作者： Yingze JIN Fei CHEN Jimin XU Xiaoyang YUAN Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System Xi'an Jiaotong UniversityXi'an 710049China Institute of Tribology School of Mechanical EngineeringHefei University of TechnologyHefei 230009China

To reveal nonlinear dynamic rules of low viscosity fluid-lubricated tilting-pad journal bearings(TPJBs),the effects of design parameters on journal center orbits and dynamic minimum film thicknesses of water-lubricated TPJBs with and without static loads are *** hydrodynamic bearing force used in the nonlinear dynamic analysis is an approximate analytical solution including the turbulence *** results reveal the methods for vibration suppression and load capacity improvement and give an optimal pivot offset and clearance ratio that can maximize the minimum film *** results also show that four-pad TPJBs with loads between pads are preferred due to good dynamic performance and load *** study would provide some guidance for nonlinear design of low viscosity fluid-lubricated TPJBs under dynamic loads.

关键词： journal center orbit dynamic minimum film thickness tilting-pad journal bearing bearing design parameter

来源：评论

学校读者我要写书评

暂无评论

DPN: Decoupling Partition and Navigation for Neural Solvers of Min-max Vehicle Routing Problems

arXiv

引用

arXiv 2024年

作者： Zheng, Zhi Yao, Shunyu Wang, Zhenkun Tong, Xialiang Yuan, Mingxuan Tang, Ke Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China China Huawei Noah’s Ark Lab Shenzhen China

The min-max vehicle routing problem (min-max VRP) traverses all given customers by assigning several routes and aims to minimize the length of the longest route. Recently, reinforcement learning (RL)-based sequential planning methods have exhibited advantages in solving efficiency and optimality. However, these methods fail to exploit the problem-specific properties in learning representations, resulting in less effective features for decoding optimal routes. This paper considers the sequential planning process of min-max VRPs as two coupled optimization tasks: customer partition for different routes and customer navigation in each route (i.e., partition and navigation). To effectively process min-max VRP instances, we present a novel attention-based Partition-and-Navigation encoder (P&N Encoder) that learns distinct embeddings for partition and navigation. Furthermore, we utilize an inherent symmetry in decoding routes and develop an effective agent-permutation-symmetric (APS) loss function. Experimental results demonstrate that the proposed Decoupling-Partition-Navigation (DPN) method significantly surpasses existing learning-based methods in both single-depot and multi-depot minmax VRPs. Our code is available at 1 Copyright © 2024, The Authors. All rights reserved.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Patients' perspectives on digital health tools

引用

PEC Innovation 2023年 2卷 100171-100171页

作者： Madanian, Samaneh Nakarada-Kordic, Ivana Reay, Stephen Chetty, T'heniel Department of Computer Science and Software Engineering School of Engineering Computer and Mathematical Science Auckland University of Technology (AUT) 6 St. Paul Street AUT WZ Building Auckland 1010 New Zealand Good Health Design School of Art and Design Auckland University of Technology (AUT) 27 St. Paul Street AUT WE Building Auckland 1010 New Zealand

Objective: Digital technology has changed the way healthcare is delivered and accessed. However, the focus is mostly on technology and clinical aspects. This review aimed to integrate and critically analyse the available knowledge regarding patients' perspectives on digital health tools and identify facilitators and barriers to their uptake. Methods: A narrative review was conducted using the Scopus and Google Scholar databases. Information related to facilitators and barriers to uptake was synthesised and interpreted using thematic and content analyses, respectively. Results: Seventy-one out of 1722 articles identified were eligible for inclusion. Patient empowerment, self-management, and personalisation were identified as the main factors that contributed to patient uptake in using digital health tools. Digital literacy, health literacy, and privacy concerns were identified as barriers to the uptake of digital health technology. Conclusion: Digital health technologies have changed the way healthcare is experienced by patients. Research highlights the disconnect between the development and implementation of digital health tools and the patients they are created for. This review may serve as the foundation for future research incorporating patients' perspectives to help increase patients' engagement with emerging technologies. Innovation: Participatory design approaches have the potential to support the creation of patient-centred digital health tools. © 2023 The Authors

关键词： Digital health Digital health technologies Mobile health Patient-centered care Telehealth Telerehabilitation

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification in Ballistic Drone Capturing Based on Transfer Learning Networks Using Infrared Images

Detection and Classification in Ballistic Drone Capturing Ba...

引用

Conference on Information and Communication technology (CICT)

作者： Harsha Vardhan Reddy M Rajkumar Gothandaraman Sreekumar Muthuswamy Department of Mechanical Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Chennai Department of Mechanical Engineering Center for Al IoT and Robotics Indian Institute of Information Technology Design and Manufacturing Kancheepuram Chennai

ISBN: (数字)9781665473125

ISBN: (纸本)9781665473132

Unmanned aerial vehicles and drones are flying objects carrying small payloads for various applications, including agriculture, photography for weddings & religious ceremonies, e-commerce deliveries, remote sensing, 3D mapping, surveillance and defense. These flying objects also called as drones are available in two variants; 1. Fixed wing propeller type, and 2. Multi-wings propeller type. Nowadays, UAVs and Drones are the primary threat to the national security on the mainland and the line of actual control. Generally, these threat-rising drones can be eradicated by anti-missile techniques, which are not economical however will destroy them. The objective of the work here is to design and develop a ballistic drone capturing system comprising two main steps; 1. classification of UAVs from the flying birds and 2. Capturing the UAVs without causing significant damage to the drone. Here, the methodology uses computer-generated infrared images of the drone in the pretrained network architecture, which acts as the Convolution Neural Network (CNN) for classifying drones and birds. The performance of AlexNet and ResNet-50 performs better and it shows 100 percent efficiency and small distribution with more stability. In the near future, the ballistic capturing system will be designed and developed as a product, which would support acquiring data about malicious drones.

关键词： Three-dimensional displays Propellers Surveillance Transfer learning Computer architecture Network architecture Birds

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：