检索结果-内蒙古大学图书馆

STAR-RIS Assisted MISO-NOMA Networks: A Simultaneous Signal Enhancement and Interference Mitigation design

IEEE Transactions on Communications 2024年

作者： Li, Jie Song, Zhengyu Hou, Tianwei Huang, Chongwen Li, Anna Zhou, Gui Liu, Yuanwei China Mobile Group Design Institute Company Ltd China Mobile Research and Development Center for Network Planning and Optimization Beijing100080 China Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Lancaster University School of Computing and Communications Lancaster United Kingdom Katholieke Universiteit Leuven KU Leuven Leuven Belgium Institute for Digital Communications Erlangen91054 Germany The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong Hong Kong

Simultaneous transmitting and reflecting (STAR) reconfigurable intelligent surface (RIS) technique has recently received considerable attention due to its omni-directional radiation capability. In this paper, motivated by the interference-mitigation-based (IMB) and signal-enhancement-based (SEB) designs, we introduce an innovative STAR-RIS assisted simultaneous-signal-enhancement-and-interference-mitigation (SSEIM) design in non-orthogonal multiple access (NOMA) multiple-input single-output cellular communication networks. Our objective is to maximize the system spectral efficiency (SE) by jointly optimizing the reflection and transmission phase shifts at the STAR-RIS, the precoding matrix of BSs, and the power allocation factors of NOMA users. We propose a low-complexity simultaneous enhancement and mitigation algorithm. Furthermore, by exploiting the manifold optimization technique, we introduce the Riemannian conjugate gradient algorithm to solve the non-convex subproblems with unit modulus constraint. Our analysis reveals that the proposed SSEIM design exceeds the traditional RIS-aided SEB and IMB designs. © 1972-2012 IEEE.

关键词： Mobile telecommunication systems

来源：评论

学校读者我要写书评

暂无评论

Cloud-Magnetic Resonance Imaging System: In the Era of 6G and Artificial Intelligence

arXiv

引用

arXiv 2023年

作者： Zhou, Yirong Wu, Yanhuang Su, Yuhan Li, Jing Cai, Jianyun You, Yongfu Guo, Di Qu, Xiaobo The Department of Electronic Science Biomedical Intelligent Cloud R&D Center Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance National Institute for Data Science in Health and Medicine Institute of Artificial Intelligence Xiamen University Xiamen361104 China The Department of Electronic Science Key Laboratory of Digital Fujian on IoT Communication Architecture and Safety Technology Xiamen University Xiamen361104 China Shanghai Electric Group CO. LTD Shanghai200001 China China Telecom Group Quanzhou362000 China China Mobile Group Xiamen361005 China School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen361024 China

Magnetic Resonance Imaging (MRI) plays an important role in medical diagnosis, generating petabytes of image data annually in large hospitals. This voluminous data stream requires a significant amount of network bandwidth and extensive storage infrastructure. Additionally, local data processing demands substantial manpower and hardware investments. Data isolation across different healthcare institutions hinders cross-institutional collaboration in clinics and research. In this work, we anticipate an innovative MRI system and its four generations that integrate emerging distributed cloud computing, 6G bandwidth, edge computing, federated learning, and blockchain technology. This system is called Cloud-MRI, aiming at solving the problems of MRI data storage security, transmission speed, AI algorithm maintenance, hardware upgrading, and collaborative work. The workflow commences with the transformation of k-space raw data into the standardized Imaging Society for Magnetic Resonance in Medicine Raw Data (ISMRMRD) format. Then, the data are uploaded to the cloud or edge nodes for fast image reconstruction, neural network training, and automatic analysis. Then, the outcomes are seamlessly transmitted to clinics or research institutes for diagnosis and other services. The Cloud-MRI system will save the raw imaging data, reduce the risk of data loss, facilitate inter-institutional medical collaboration, and finally improve diagnostic accuracy and work efficiency. Copyright © 2023, 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

The Pairing Analysis Improvement of Magnetized Structure in Electromagnetic Bulging Process in Case of Tube with Field Shaper

引用

Journal of Electromagnetic Analysis and applications 2024年第4期16卷 43-67页

作者： Blaise Kevine Lenz Soronga Zhanqian Zhan Jing Liu Jonas Asamoah Mohamed Bangali Bangura Matala Makiese N’kodia Kambani Chrionie Md Jobayer Hossain Yongdong Chen Program Debugging and Design Department Guangdong Lyric Robot Automation Co. Ltd Huizhou China Electrical and Automation Department China Three Gorges University Yichang China Electronic Department Power Electronic Research Center University of Kent Giles Ln Canterbury UK Program Debugging Department Guangdong Lyric Robot Automation Co. Ltd. Huizhou China Electrical and Computer Engineering Department South China University of Technology Guangzhou China World Standardization Certification and Testing Group (Shenzhen) Co. Ltd. Shenzhen China Electrical Engineering-Power System Mapon University Kindu Democratic Republic of Congo Department of Economy Managment School of Management Computer and Telecomunication Rabbat Marocco Materials Visual Calibration Department Guangdong Lyric Robot Automation Co. Ltd. Huizhou China Program Design Department Guangdong Lyric Robot Automation Co. Ltd. Huizhou China

In the current practical science, the accuracy in the formability of metal alloys being the goal when using electromagnetic forming (EMF) technology, which is a high-speed processing technology that uses Lorentz forces to achieve plastic deformation of sheet metal;according to the previous analysis, the results have shown that in most cases, the Lorentz force acting on the workpiece (metal) is not uniform, there are uneven axial deformations of the metal plates which prevent the rapid advancement of today’s technology. In this article, we presented some advanced analyzes which will lead us to improve the technical solution for the problems of non-uniform axial deformations of the metals in the traditional tube electromagnetic forming technology (EMF). A field shaper is used as a practical forming tool to influence the magnetic field and magnetic pressure distribution, thereby improving the forming ability and result during the electromagnetic forming (EMF) process and we see that induced eddy current control is realized by changing the structural parameters of the magnetic field shaper;which improves the strength and controllability of the magnetic force that acts on the workpiece;thereby a greater radial magnetic pressure can be achieved with field shaper than the case without it;the field shaper regulates the electromagnetic force, the distribution of the magnetic pressure decreases, and the uniform force area of the tube increases which effectively enhances the uniform range of the pipe electromagnetic bulging and the electromagnetic induction coupling between the coil and the metallic workpiece is generally required to produce the Lorentz forces. Using COMSOL Multiphysics® simulation software helped us to accurately represent the real world, simulating multiple physical effects that happened in this model during the process.

关键词： Electromagnetic Forming Field Shaper Lorentz Force Magnetic Pressure Distribution

来源：评论

学校读者我要写书评

暂无评论

An Efficient Multi-Order Cascade Distillation Model for the Detection of Small Targets and Occluded Objects in Transmission Line Inspection

SSRN

引用

SSRN 2023年

作者： Qu, Zhaoyang Zang, Jiye Dong, Yunchang Qu, Nan Song, Siqi Jiang, Tao Li, Min Liang, Feng Li, Lingcong School of Computer Northeast Electric Power University Jilin132012 China Jilin Electric Power Big Data Intelligent Processing Engineering Technology Research Center Jilin132012 China State Grid Jilin Electric Power Research Institute Changchun130012 China State Grid Jiangsu Electric Power Co. Ltd. Nanjing Power Supply Company 210000 China Northeast Electric Power Design Institute Co. Ltd. of China Power Engineering Consulting Group Changchun130021 China

The proposed cascade distillation detection model improves the accuracy of small target defect detection and robustness in complex environments during UAV inspection of transmission lines. Firstly, the cascading modules of the shared backbone network are designed: the dynamic anchor box generation module and the bounding box refinement module. The former collects and processes areas where there may be targets, outputs high-quality location information, and distills it to the latter, and the latter is responsible for refining and filtering this part of the information, which solves the problems of missed detection of model targets and lack of a priori information on target locations. A high-order aggregated feature extraction network is introduced to enhance feature extraction of small and obscured targets. Lastly, a spatially deformable attention mechanism optimizes sampling point selection and attention weight calculation by aggregating nearby contextual information, improving bounding box adjustment. © 2023, The Authors. All rights reserved.

关键词： Electric lines

来源：评论

学校读者我要写书评

暂无评论

Efficient Federated Learning for AIoT applications Using Knowledge Distillation

arXiv

引用

arXiv 2021年

作者： Liu, Tian Ling, Zhiwei Xia, Jun Fu, Xin Yu, Shui Chen, Mingsong MoE Engineering Research Center of Software/Hardware Co-design Technology and Application East China Normal University Shanghai200062 China Department of Information Science and Engineering Zaozhuang University Zaozhuang277160 China Department of Electrical and Computer Engineering University of Houston HoustonTX77204 United States School of Computer Science University of Technology Sydney Australia

As a promising distributed machine learning paradigm, Federated Learning (FL) trains a central model with decentralized data without compromising user privacy, which makes it widely used by Artificial Intelligence Internet of Things (AIoT) applications. However, the traditional FL suffers from model inaccuracy, since it trains local models only using hard labels of data while useful information of incorrect predictions with small probabilities is ignored. Although various solutions try to tackle the bottleneck of the traditional FL, most of them introduce significant communication overhead, making the deployment of large-scale AIoT devices a great challenge. To address the above problem, this paper presents a novel Distillation-based Federated Learning (DFL) method that enables efficient and accurate FL for AIoT applications. By using Knowledge Distillation (KD), in each round of FL training, our approach uploads both the soft targets and local model gradients to the cloud server for aggregation, where the aggregation results are then dispatched to AIoT devices for the next round of local training. During the DFL local training, in addition to hard labels, the model predictions approximate soft targets, which can improve model accuracy by leveraging the knowledge of soft targets. To further improve our DFL model performance, we design a dynamic adjustment strategy of loss function weights for tuning the ratio of KD and FL, which can maximize the synergy between soft targets and hard labels. Comprehensive experimental results on well-known benchmarks show that our approach can significantly improve the model accuracy of FL without introducing significant communication overhead. Copyright © 2021, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

eFAirWrite: Bringing energy efficient text entry to next generation smart devices

引用

Expert Systems with applications 2025年 289卷

作者： Ghaffar, Muhammad Mohsin Abdullah, Ahmad Younas, Junaid Rybalkin, Vladimir Ney, Jonas Lukowicz, Paul Wehn, Norbert Microelectronic Systems Design Research Group University of Kaiserslautern-Landau Kaiserslautern67663 Germany School of Electrical Engineering & Computer Science National University of Sciences & Technology Islamabad44000 Pakistan German Research Centre for Artificial Intelligence Kaiserslautern67663 Germany

Text entry tasks for emerging wireless Augmented Reality (AR) and Virtual Reality (VR) devices can be realized in many ways, one of the most promising methods is based on an Inertial Measurement Unit (IMU) sensor, which resembles a human writing style and is called air-writing. An existing air-writing Deep Neural Network (DNN) based algorithm called FAirWrite achieves state-of-the-art accuracy. However, this algorithm is optimized only for accuracy without considering the implementation constraints. State-of-the-art implementation executes the algorithm in a cloud, which is associated with large communication latency;privacy issues with respect to data transfer;and a need for reliable internet connection. A solution that tackles all three challenges is executing the algorithm locally at the edge in the closest proximity to the sensor. However, inference at the edge is challenging due to limited memory and computing resources, which can impact accuracy and increase latency. Additionally, battery-powered edge devices must adhere to strict power and energy consumption limits. All these constraints collectively restrict the model size and computational complexity that can be deployed near the sensor. In this work, we explore various optimizations required to enable state-of-the-art FAirWrite algorithm for a real-world deployment scenario, i.e. executing on an edge device. We perform a multi-layer design-space exploration considering multiple levels of design hierarchy spanning from optimizations applied on algorithmic level down to hardware level, considering various deployment run-times and edge platforms including embedded micro-controller, embedded Central Processing Unit (CPU), embedded Graphics Processing Unit (GPU), Neural Processing Unit (NPU), and Field-Programmable Gate Array (FPGA). The complexity reduction optimizations result in a 37× smaller eFAirWrite model without any accuracy degradation. We propose and implement a custom hardware architecture of the alg

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

H2-MARL: Multi-Agent Reinforcement Learning for Pareto Optimality in Hospital Capacity Strain and Human Mobility during Epidemic

arXiv

引用

arXiv 2025年

作者： Luo, Xueting Deng, Hao Yang, Jihong Shen, Yao Guo, Huanhuan Sun, Zhiyuan Liu, Mingqing Wei, Jiming Zhao, Shengjie School of Computer Science and Technology Tongji University Shanghai201804 China China Land Surveying and Planning Institute Beijing100035 China College of Architecture and Urban Planning Tongji University Shanghai200092 China Chongqing Institute of Planning and Natural Resources Investigation and Monitoring Chongqing401121 China Li-Fi Research and Development Centre University of Cambridge CambridgeCB3 0FA United Kingdom Guangdong Urban-rural Planning and Design Research Institute Technology Group Co. Ltd. Guangzhou510290 China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai201804 China

The necessity of achieving an effective balance between minimizing the losses associated with restricting human mobility and ensuring hospital capacity has gained significant attention in the aftermath of COVID-19. Reinforcement learning (RL)-based strategies for human mobility management have recently advanced in addressing the dynamic evolution of cities and epidemics;however, they still face challenges in achieving coordinated control at the township level and adapting to cities of varying scales. To address the above issues, we propose a multi-agent RL approach that achieves Pareto optimality in managing hospital capacity and human mobility (H2-MARL), applicable across cities of different scales. We first develop a township-level infection model with online-updatable parameters to simulate disease transmission and construct a city-wide dynamic spatiotemporal epidemic simulator. On this basis, H2-MARL is designed to treat each division as an agent, with a trade-off dual-objective reward function formulated and an experience replay buffer enriched with expert knowledge built. To evaluate the effectiveness of the model, we construct a township-level human mobility dataset containing over one billion records from four representative cities of varying scales. Extensive experiments demonstrate that H2-MARL has the optimal dual-objective trade-off capability, which can minimize hospital capacity strain while minimizing human mobility restriction loss. Meanwhile, the applicability of the proposed model to epidemic control in cities of varying scales is verified, which showcases its feasibility and versatility in practical applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Machine Learning for Multifactor Geospatial Prioritization of Suitable Healthcare Facility Sites

Multimodal Machine Learning for Multifactor Geospatial Prior...

引用

IEEE International Workshop on Imaging Systems and Techniques (IST)

作者： Nicolas Douard Joan LaRovere Vandan Parmar Daniel Straulino Matthew D. Harris Chandler McCann Allen Nasseri Corey Hanson Mohammed Bataglia Evan E. Afshin Mattia Filiaci Kim Azzarelli George Giakos Ebby Elahi Actionable Data Initiative Research Group Virtue Foundation New York NY USA Department of Electrical and Computer Engineering Manhattan University New York NY USA Department of Cardiology Boston Children's Hospital Boston MA USA Department of Pediatrics Harvard Medical School Boston MA USA DataRobot Boston MA USA Department of Regional Planning and Urban Design University of Pennsylvania Weitzman School of Design Philadelphia PA USA Department of Physiology and Biophysics Weill Cornell Medicine New York NY USA Department of Ophthalmology Otolaryngology and Global Health Icahn School of Medicine at Mount Sinai New York NY USA

ISBN: (数字)9798350378214

ISBN: (纸本)9798350378221

This study introduces a comprehensive multifactor geospatial methodology to identify and prioritize optimal locations for the construction of new healthcare facilities. Building on a previously developed geospatial machine learning pipeline designed to predict suitable sites, we introduce two complementary machine learning-based methodologies to enhance the decision-making process. The first methodology employs a population-density-based approach with the objective of maximizing the impact of new healthcare facilities by prioritizing areas with the highest population densities. This strategy ensures that the greatest number of individuals can benefit from new healthcare services. The second methodology is a geographical-distribution-based approach, which focuses on promoting equitable access to healthcare by targeting underserved and underrepresented areas, regardless of administrative boundaries. By prioritizing locations that currently lack sufficient healthcare resources, this approach aims to reduce disparities in healthcare accessibility and improve overall equity in resource allocation. The integration of these two methodologies provides a balanced framework that addresses both the need for widespread impact and the imperative for equitable access. The results of this study are expected to help improve healthcare access, ensuring that new facilities are strategically placed to serve densely populated regions and underserved communities, ultimately leading to more equitable and effective healthcare delivery.

关键词： Soft sensors Scalability Pipelines Medical services Machine learning Robustness Geospatial analysis Resource management Stakeholders Population density

来源：评论

学校读者我要写书评

暂无评论

Multi-GNSS simulation and its positioning performance for static and dynamic users

Multi-GNSS simulation and its positioning performance for st...

引用

International Symposium on Autonomous Systems (ISAS)

作者： Kun Li Mengzhi Gao Shuaiyong Zheng Xuanwen Wang Xiaoqin Jin Peng Yang Jianlei Yang Jing Lu Gaole Yao School of Integrated Circuit Science and Engineering Tianjin University of Technology Tianjin China College of Artificial Intelligence Nankai University Tianjin China School of Computer Science and Engineering Tianjin University of Technology Tianjin China State Key Laboratory of Satellite Navigation System and Equipment Technology The 54th Research Institute of China Electronics Technology Group Corporation Shijiazhuang China Land Satellite Remote Sensing Application Center Ministry of Natural Resources Beijing China Tianjin AtoN Division The Navigation Guarantee Centre of North China Sea Tianjin China

Global navigation satellite system plays an important role in military and civil fields, providing global positioning, navigation and timing services in real time. Unfortunately, the services provided by single constellation or double constellations cannot meet the requirements of high-level navigation, and there are still some problems such as low positioning accuracy and low number of visible satellites at specific circumstances to be solved. In this paper, multi-GNSSs are constructed and their global positioning performance is analyzed with respect to static and dynamic users. Results show that with more constellations, the position dilution of precision is decreased, and the number of visible satellites and the positioning accuracy are improved, which reveals that compared with single constellation or double constellations, multi-GNSSs can obviously improve the positioning performance. The methodology proposed can serve as a technical reference for national integrated PNT systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal Machine Learning for Multifactor Geospatial Prioritization of Suitable Healthcare Facility Sites

Multimodal Machine Learning for Multifactor Geospatial Prior...

引用

2024 IEEE International Conference on Imaging Systems and Techniques, IST 2024

作者： Douard, Nicolas Larovere, Joan Parmar, Vandan Straulino, Daniel Harris, Matthew D. McCann, Chandler Nasseri, Allen Hanson, Corey Bataglia, Mohammed Afshin, Evan E. Filiaci, Mattia Azzarelli, Kim Giakos, George Elahi, Ebby Manhattan University Department of Electrical and Computer Engineering 106 East 85th St NE1 New YorkNY10463 United States Virtue Foundation Actionable Data Initiative Research Group 3825 Corlear Ave New YorkNY10028 United States Boston Children's Hospital Department of Cardiology 300 Longwood Ave BostonMA02115 United States Harvard Medical School Department of Pediatrics 25 Shattuck St BostonMA02115 United States DataRobot 225 Franklin St 13th Floor BostonMA02110 United States University of Pennsylvania Weitzman School of Design Department of Regional Planning and Urban Design 210 S 34th St PhiladelphiaPA19104 United States Weill Cornell Medicine Department of Physiology and Biophysics 1300 York Ave New YorkNY10021 United States Icahn School of Medicine at Mount Sinai Department of Ophthalmology Otolaryngology and Global Health 1 Gustave L. Levy Place New YorkNY10029 United States

ISBN: (纸本)9798350378214

关键词： Resource allocation

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：