检索结果-内蒙古大学图书馆

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

IEEE Transactions on Mobile Computing 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing Advanced Information Network Laboratory Beijing China College of Computing and Data Science Singapore University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral Gables33146 United States University of Miami Department of Industrial and Systems Engineering Coral Gables33146 United States Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China North Carolina State University Department of Computer Science RaleighNC27695 United States Beijing Key Laboratory of Network System Architecture and Convergence China Beijing University of Posts and Telecommunications Beijing Advanced Information Network Laboratory Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025 IEEE. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm 29

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

29th IEEE International Conference on Parallel and Distributed systems, ICPADS 2023

作者： Zeng, Yan Huang, Chengchuang Ni, Yijie Zhou, Chunbao Zhang, Jilin Wang, Jue Zhou, Mingyao Xue, Meiting Zhang, Yunquan Hangzhou Dianzi University School of Computer Science and Technology Hangzhou310018 China Ministry of Education Key Laboratory for Modeling and Simulation of Complex Systems Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Hangzhou Dianzi University School of ITMO Joint Institute Hangzhou310018 China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing100086 China HuaWei China Institute of Computing Technology of the Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing100086 China

ISBN: (纸本)9798350330717

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network's dataflow graph and device cluster's topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method. © 2023 IEEE.

关键词： Auto-Parallel Distributed machine learning Genetic algorithm Integer linear programming Model parallelism

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

arXiv

引用

arXiv 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan The Beijing Key Laboratory of Network System Architecture and Convergence The Beijing Advanced Information Network Laboratory Beijing University of Posts and Telecommunications Beijing China Singapore The Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Department of Industrial and Systems Engineering University of Miami Coral GablesFL33146 United States The College of Information Science and Electronic Engineering Zhejiang University Zhejiang Hangzhou310027 China The Department of Computer Science North Carolina State University RaleighNC27695 United States The Beijing Key Laboratory of Network System Architecture and Convergence China The Beijing Advanced Information Network Laboratory Beijing University of Posts and Telecommunications Beijing100876 China

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Safety Guaranteed Power-Delivered-to-Load Maximization for Magnetic Wireless Power Transfer

Safety Guaranteed Power-Delivered-to-Load Maximization for M...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Wangqiu Zhou Xinyu Wang Hao Zhou Shenyao Jiang Zhi Liu Yusheng Ji LINKE Lab School of Computer Science and Technology University of Science and Technology of China CAS Key Laboratory of Wireless-Optical Communications University of Science and Technology of China Deqing Alpha Innovation Institute Huzhou China Department of Computer and Network Engineering The University of Electro-Communications Tokyo Japan Information Systems Architecture Science Research Division National Institute of Informatics Tokyo Japan

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Electromagnetic radiation (EMR) safety has always been a critical reason for hindering the development of magneticenabled wireless power transfer technology. People focus on the actual received energy at charging devices while paying attention to their health. Thus, we study this significant problem in this paper, and propose a universal safety guaranteed power-delivered-to-load (PDL) maximization scheme (called SafeGuard). Technically, we first utilize the off-the-shelf electromagnetic simulator to perform the EMR distribution analysis to ensure the universality of the method. Then, we innovatively introduce the concept of multiple importance sampling for achieving efficient EMR safety constraint extraction. Finally, we treat the proposed optimization problem as an optimal boundary point search problem from the perspective of space geometry, and devise a brand-new grid-based multi-constraint parallel processing algorithm to efficiently solve it. We implement a system prototype for SafeGuard, and conduct extensive experiments to evaluate it. The results indicate that our SafeGuard can obviously improve the achieved PDL by up to 1.75× compared with the state-of-the-art baseline while guaranteeing EMR safety. Furthermore, SafeGuard can accelerate the solution process by 29.12× compared with the traditional numerical method to satisfy the fast optimization requirement of wireless charging systems.

关键词： Performance evaluation Monte Carlo methods System performance Inductive charging Prototypes Wireless power transfer Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Lightweight Task-Oriented Semantic Communication Empowered by Large-Scale AI Models

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Liu, Chuanhong Guo, Caili Yang, Yang Chen, Mingzhe Quek, Tony Q. S. Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing100876 China University of Miami Department of Electrical and Computer Engineering Institute for Data Science and Computing Coral GablesFL United States Singapore University of Technology and Design Dept. of Information Systems Technology and Design 487372 Singapore

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant challenges for real-time communication scenarios. To address this, this paper proposes utilizing knowledge distillation (KD) techniques to extract and condense knowledge from LAI models, effectively reducing model complexity and computation latency. Nevertheless, the inherent complexity of LAI models leads to prolonged inference times during distillation, while their lack of channel awareness compromises the distillation performance. These limitations make standard KD methods unsuitable for task-oriented semantic communication scenarios. To address these issues, we propose a fast distillation method featuring a pre-stored compression mechanism that eliminates the need for repetitive inference, significantly improving efficiency. Furthermore, a channel adaptive module is incorporated to dynamically adjust the transmitted semantic information based on varying channel conditions, enhancing communication reliability and adaptability. In addition, an information bottleneck-based loss function is derived to guide the fast distillation process. Simulation results verify that the proposed scheme outperform baselines in term of task accuracy, model size, computation latency, and training data requirements. © 1967-2012 IEEE.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

International Conference on Parallel and Distributed systems (ICPADS)

作者： Yan Zeng ChengChuang Huang YiJie Ni ChunBao Zhou JiLin Zhang Jue Wang MingYao Zhou MeiTing Xue YunQuan Zhang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou China Data Security Governance Zhejiang Engineering Research Center Hangzhou China School of ITMO Joint Institute Hangzhou Dianzi University Hangzhou China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing China HuaWei State Key Laboratory of Computer Architecture Institute of Computing Technology of the Chinese Academy of Sciences Beijing China

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network’s dataflow graph and device cluster’s topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Left ventricle contouring in cardiac images based on deep reinforcement learning

TechRxiv

引用

TechRxiv 2021年

作者： Yin, Sixing Han, Yameng Pan, Judong Wang, Yining Li, Shufang Yu, F. Richard Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China University of California San Francisco San FranciscoCA94117 United States State Key Laboratory of Complex Severe and Rare Diseases Chinese Academy of Medical Sciences Peking Union Medical College Beijing100730 China The Department of Systems and Computer Engineering Carleton University OttawaONK1S 5B6 Canada

Assessment of the left ventricle segmentation in cardiac magnetic resonance imaging (MRI) is of crucial importance for cardiac disease diagnosis. However, conventional manual segmentation is a tedious task that requires excessive human effort, which makes automated segmentation highly desirable in practice to facilitate the process of clinical diagnosis. In this paper, we propose a novel reinforcement-learning-based framework for left ventricle contouring, which mimics how a cardiologist outlines the left ventricle in a cardiac image. Since such a contour drawing process is simply moving a paintbrush along a specific trajectory, it is thus analogized to a path finding problem. Following the algorithm of proximal policy optimization (PPO), we train a policy network, which makes a stochastic decision on the agent’s movement according to its local observation such that the generated trajectory matches the true contour of the left ventricle as much as possible. Moreover, we design a deep learning model with a customized loss function to generate the agent’s landing spot (or coordinate of its initial position on a cardiac image). The experiment results show that the coordinate of the generated landing spot is sufficiently close to the true contour and the proposed reinforcement-learning-based approach outperforms the existing U-net model even with limited training set. © 2021, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Improvement on the Linear Algebraic Attack for the Indeterminate Equation Encryption Scheme

An Improvement on the Linear Algebraic Attack for the Indete...

引用

International Symposium on Information Theory and Its Applications, ISITA

作者： Yasuhiko Ikematsu Koichiro Akiyama Tsuyoshi Takagi Department of Mathematical Informatics The University of Tokyo Tokyo Japan Computer Architecture and Network Systems Laboratory Corporate R&D Center Toshiba Corporation

ISBN: (纸本)9781538682234;9784885523182

At SAC2017, Akiyama et al. proposed the indeterminate equation encryption scheme whose security is based on a solution problem of indeterminate equation. It is an extension of algebraic surface encryption scheme. A public key X for this scheme is a polynomial in two variables over a finite ring. Akiyama et al. also proposed two attacks, the linear algebraic attack (LAA) and the key recovery attack (KRA), by using the lattice structure associated with this scheme. In this paper, we give an improvement on LAA. Also we explain the relation between our improvement and the improvement on LAA proposed by Xagawa and examine parameters that those attacks fail by experiments. As a result, we conclude that if the total degree of the public key X is one, then KRA is more efficient than LAA and if that of X is two, then LAA is more efficient than KRA.

关键词： Encryption Lattices Public key Informatics Quantum computing

来源：评论

学校读者我要写书评

暂无评论

A Pattern Division Multiple Access Scheme with Low Complexity Iterative Receiver for 5G Wireless Communication systems

A Pattern Division Multiple Access Scheme with Low Complexit...

引用

IEEE Vehicular Technology Conference

作者： Kai Zhang Jin Xu Changchuan Yin Chunyu Pan Weiqiang Tan Guixian Xu Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing 100876 P. R. China Zhengzhou University of Light Industry School of Computer and Communication Engineering Zhengzhou 450001 P. R. China Guangzhou University School of Computer Science and Educational Software Guangzhou 510006 P. R. China Aalborg University Department of Electronic Systems Aalborg 9400 Denmark

ISBN: (纸本)9781538663592;9781538663585

Non-orthogonal multiple access schemes with higher spectral efficiency and the capability of accessing more users than orthogonal multiple access (OMA) scheme is preferred for the fifth generation (5G) wireless networks. In this work, a non-orthogonal transmission scheme called pattern division multiple access (PDMA) is proposed for the 5G wireless communication systems. Two pattern matrices are proposed for 150% and 200% overloaded PDMA systems. Then, a low complexity symbol-wise belief propagation iterative detection and decoding (BPIDD) algorithm for multiple user detection is proposed. Numerical results and analysis provided by utilizing extrinsic information transfer chart show that the proposed scheme outperforms the traditional OMA systems significantly, and the performance of the proposed scheme is better than that of the existing schemes up to 1 dB. Finally, simulation results show that the proposed scheme is superior to the existing schemes and the proposed BPIDD algorithm is better than that of the BP algorithm over 0.5 dB.

关键词： 5G mobile communication iterative decoding matrix algebra multi-access systems multiuser detection Multi access systems matrix algebra Multiuser detection Iterative decoding multiple access Wireless communication systems Scheme iterative receiver spectral efficiency Information Transfer

来源：评论

学校读者我要写书评

暂无评论

Changing life expectancy in European countries 1990–2021: a subanalysis of causes and risk factors from the Global Burden of Disease Study 2021

引用

The Lancet Public Health 2025年第3期10卷 e172-e188页

作者： Steel, Nicholas Bauer-Staeb, Clarissa Maria Mercedes Ford, John A. Abbafati, Cristiana Abdalla, Mohammed Altigani Abdelkader, Atef Abdi, Parsa Zuñiga, Roberto Ariel Abeldaño Abiodun, Olugbenga Olusola Abolhassani, Hassan Abu-Gharbieh, Eman Abukhadijah, Hana J. Abu-Zaid, Ahmed Addo, Isaac Yeboah Addolorato, Giovanni Adekanmbi, Victor Adetunji, Juliana Bunmi Adeyeoluwa, Temitayo Esther Agardh, Emilie E. Agyemang-Duah, Williams Ahmad, Danish Ahmed, Ayman Ahmed, Syed Anees Akinosoglou, Karolina Akkaif, Mohammed Ahmed Al Awaidy, Salah Al Hasan, Syed Mahfuz Al Zaabi, Omar Ali Mohammed Aldridge, Robert W. Algammal, Abdelazeem M. Al-Gheethi, Adel Ali Saeed Ali, Abid Ali, Mohammed Usman Ali, Syed Shujait Ali, Waad Alicandro, Gianfranco Alif, Sheikh Mohammad Al-Jumaily, Adel Allebeck, Peter Alrawashdeh, Ahmad Al-Rifai, Rami H. Alsabri, Mohammed A. Alshahrani, Najim Z. Aluh, Deborah Oyine Al-Wardat, Mohammad Al-Zyoud, Walid A. Amiri, Sohrab Anderlini, Deanna Andrei, Catalina Liliana Anil, Abhishek Anvari, Saeid Anyasodor, Anayochukwu Edward Appiah, Seth Christopher Yaw Aquilano, Michele Arabloo, Jalal Arafat, Mosab Areda, Demelash Aremu, Abdulfatai Armani, Keivan Armocida, Benedetta Ärnlöv, Johan Asaduzzaman, Muhammad Astell-Burt, Thomas Aujayeb, Avinash Ausloos, Marcel Azadnajafabad, Sina Aziz, Shahkaar Azzam, Ahmed Y. Babu, Giridhara Rathnaiah Badache, Andreea Corina Badiye, Ashish D. Bahramian, Saeed Baig, Atif Amin Baker, Jennifer L. Bansal, Hansi Bärnighausen, Till Winfried Barone, Mark Thomaz Ugliara Barrow, Amadou Barteit, Sandra Bashir, Shahid Bashiru, Hameed Akande Basso, João Diogo Bastan, Mohammad-Mahdi Basu, Sanjay Batra, Kavita Bauckneht, Matteo Baune, Bernhard T. Beghi, Massimiliano Beiranvand, Maryam Béjot, Yannick Bell, Michelle L. Bello, Olorunjuwon Omolaja Belo, Luis Beloukas, Apostolos Beneke, Alice A. Bettencourt, Paulo J.G. Bhagavathula, Akshaya Srikanth Bhala, Neeraj Bhaskar, Sonu Bisulli, Francesca Bjørge, Tone Bodunrin, Aadam Olalekan Carvajal, Alejandro Botero Bouaoud, Souad Brayne, Carol Brenner, H Department of Primary Care and Public Health University of East Anglia Norwich United Kingdom Office for Health Improvement and Disparities Department of Health and Social Care London United Kingdom Department of Legal and Economic Studies La Sapienza University Rome Italy Rome Italy Hull York Medical School University of Hull Hull United Kingdom Department of Mathematics and Sciences Ajman University Ajman United Arab Emirates Department of Medicine Memorial University St. John's NL Canada Postgraduate Department University of Sierra Sur Miahuatlan de Porfirio Diaz Mexico Yhteiskuntadatatieteen keskus (Centre for Social Data Science) Helsinki Finland Department of Internal Medicine Federal Medical Centre Abuja Nigeria Research Center for Immunodeficiencies Tehran University of Medical Sciences Tehran Iran Department of Medical Biochemistry and Biophysics Karolinska Institutet (Karolinska Institute) Stockholm Sweden Department of Clinical Sciences University of Sharjah Sharjah United Arab Emirates Department of Biopharmaceutics and Clinical Pharmacy University of Jordan Amman Jordan Medical Research Center Hamad Medical Corporation Doha Qatar Department of Biochemistry and Molecular Medicine Alfaisal University Riyadh Saudi Arabia College of Graduate Health Sciences University of Tennessee Memphis TN United States School of Medicine Sydney NSW Australia Centre for Social Research in Health University of New South Wales Sydney NSW Australia Internal Medicine and Alcohol Related Disease Unit Fondazione Policlinico Universitario A. Gemelli IRCCS Rome Italy Department of Medical and Surgical Sciences Università Cattolica di Roma (Catholic University of Rome) Rome Italy Department of Obstetrics and Gynecology University of Texas Medical Branch Galveston TX United States Department of Biochemistry Osun State University Osogbo Nigeria Department of Pharmacology and Therapeutics University of Medical Sciences Ondo Ondo Nigeria Department of Veteri

Background: Decades of steady improvements in life expectancy in Europe slowed down from around 2011, well before the COVID-19 pandemic, for reasons which remain disputed. We aimed to assess how changes in risk factors and cause-specific death rates in different European countries related to changes in life expectancy in those countries before and during the COVID-19 pandemic. Methods: We used data and methods from the Global Burden of Diseases, Injuries, and Risk Factors Study 2021 to compare changes in life expectancy at birth, causes of death, and population exposure to risk factors in 16 European Economic Area countries (Austria, Belgium, Denmark, Finland, France, Germany, Greece, Iceland, Ireland, Italy, Luxembourg, the Netherlands, Norway, Portugal, Spain, and Sweden) and the four UK nations (England, Northern Ireland, Scotland, and Wales) for three time periods: 1990–2011, 2011–19, and 2019–21. Changes in life expectancy and causes of death were estimated with an established life expectancy cause-specific decomposition method, and compared with summary exposure values of risk factors for the major causes of death influencing life expectancy. Findings: All countries showed mean annual improvements in life expectancy in both 1990–2011 (overall mean 0·23 years [95% uncertainty interval [UI] 0·23 to 0·24]) and 2011–19 (overall mean 0·15 years [0·13 to 0·16]). The rate of improvement was lower in 2011–19 than in 1990–2011 in all countries except for Norway, where the mean annual increase in life expectancy rose from 0·21 years (95% UI 0·20 to 0·22) in 1990–2011 to 0·23 years (0·21 to 0·26) in 2011–19 (difference of 0·03 years). In other countries, the difference in mean annual improvement between these periods ranged from –0·01 years in Iceland (0·19 years [95% UI 0·16 to 0·21] vs 0·18 years [0·09 to 0·26]), to –0·18 years in England (0·25 years [0·24 to 0·25] vs 0·07 years [0·06 to 0·08]). In 2019–21, there was an overall decrease in mean annual life expectancy a

关键词：

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：