检索结果-内蒙古大学图书馆

Efficient Model Training in Edge networks with Hierarchical Split Learning

IEEE Transactions on Mobile Computing 2025年

作者： Zhang, Songge Wu, Wen Song, Lingyang Shen, Xuemin Peking University Shenzhen Graduate School School of Electronic and Computer Engineering Shenzhen518055 China Pengcheng Laboratory Frontier Research Center Shenzhen518055 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Xiangtan University Hunan Institute of Advanced Sensing and Information Technology Xiangtan China University of Waterloo Department of Electrical and Computer Engineering WaterlooN2L 3G1 Canada

In this paper, we propose an efficient model training scheme, named Group-based Hierarchical Split Learning (GHSL), which can accelerate the artificial intelligence (AI) training process in edge networks in a "first-sequential-then-parallel" manner. Specifically, the proposed scheme hierarchically splits an AI model into a user-side and server-side model, while dividing a number of users into multiple groups. Users in each group train user-side models with the interaction of the shared server-side model sequentially;different groups perform the above training process parallelly;the AI models of each group are aggregated into a global model. We also carry out the convergence analysis for the proposed scheme over non-independent and identically distributed data, which reveals that the convergence rate depends on user grouping. Furthermore, we propose a data-driven two-stage user grouping algorithm to minimize the overall training delay, taking user resource heterogeneity and the black-box training process into account. The proposed algorithm first utilizes the Gaussian process regression approach to determine the number of groups, and then employs the coalition game theory to determine the optimal user grouping decision. Comprehensive simulation results demonstrate that the proposed scheme can reduce training delay, user-side computational workload, and communication overhead by up to 19%, 53%, and 54%, respectively, comparing to state-of-the-art benchmarks. © 2002-2012 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

A Novel High-Gain Magneto-Electric Dipole Antenna Fed by ISGW 13

A Novel High-Gain Magneto-Electric Dipole Antenna Fed by ISG...

引用

13th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2021

作者： Zhou, Hang Shen, Dongya Yuan, Hong Zhang, Xiupu Zhou, Liping Yunnan University Yunnan Provincial Engineering Laboratory Of Cloud Wireless Access Heterogeneous Networks Kunming650500 China Concordia University IPhotonics Labs Department Of Electrical And Computer Engineering MontrealH3G1M8 Canada

ISBN: (纸本)9781665434379

A high-gain magneto-electric (ME) dipole antenna fed by Integrated Substrate Gap Waveguide (ISGW) for use in 5G communication systems is proposed. The ME dipole antenna is mainly composed of two pairs of printed dipoles grounded through metallized vias and a constructed current loop through ISGW, and one dipole is used as the electric dipole and the other for the magnetic dipole. The impedance bandwidth of this antenna ranges from 23.63 to 29.61 GHz (22.5%), and the average gain is higher than 9.56 dB. In addition, a stable gain and symmetrical radiation pattern are obtained. © 2021 IEEE.

关键词： Directional patterns (antenna)

来源：评论

学校读者我要写书评

暂无评论

Intelligent Energy-Efficient Resource Allocation for Multi-UAV-Assisted Mobile Edge Computing networks

引用

China Communications 2025年第4期22卷 339-355页

作者： Hu Han Shen Le Zhou Fuhui Wang Qun Zhu Hongbo The China Information Consulting and Designing Institute CO. Ltd.Nanjing 210000China The Jiangsu Key Laboratory of Wireless Communications(Nanjing University of Posts and Telecommunications) Nanjing 210003China The Engineering Research Center of Health Service System Based on Ubiquitous Wireless Networks Ministry of Education(Nanjing University of Posts and Telecommunications)Nanjing 210003China The College of Artificial Intelligence(Nanjing University of Aeronautics and Astronautics) Nanjing 210000China The Department of Computer Science(San Francisco State University) San FranciscoCAUSA

The unmanned aerial vehicle(UAV)-assisted mobile edge computing(MEC)has been deemed a promising solution for energy-constrained devices to run smart applications with computationintensive and latency-sensitive requirements,especially in some infrastructure-limited areas or some emergency ***,the multi-UAVassisted MEC network remains largely *** this paper,the dynamic trajectory optimization and computation offloading are studied in a multi-UAVassisted MEC system where multiple UAVs fly over a target area with different trajectories to serve ground *** considering the dynamic channel condition and random task arrival and jointly optimizing UAVs'trajectories,user association,and subchannel assignment,the average long-term sum of the user energy consumption minimization problem is *** address the problem involving both discrete and continuous variables,a hybrid decision deep reinforcement learning(DRL)-based intelligent energyefficient resource allocation and trajectory optimization algorithm is proposed,named HDRT algorithm,where deep Q network(DQN)and deep deterministic policy gradient(DDPG)are invoked to process discrete and continuous variables,*** results show that the proposed HDRT algorithm converges fast and outperforms other benchmarks in the aspect of user energy consumption and latency.

关键词： dynamic trajectory optimization intelligent resource allocation unmanned aerial vehicle uav assisted uav assisted mec energy efficiency smart applications mobile edge computing mec deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Kerr effect in ultra-compact hybrid plasmonic metal-insulator-metal nano-focusing structure

引用

Chinese Optics Letters 2022年第3期20卷 106-110页

作者： Kejian Zhu Pengfei Sun F|engfei Xu Xingpeng Liu Tangyou Sun Haiou Li Zhiping Zhou State Key Laboratory of Advanced Optical Communication Systems and Networks Department of ElectronicsSchool of Electronics Engineering and Computer SciencePeking UniversityBeijing 100871China Guangxi Key Laboratory of Precision Navigation Technology and Application Guilin University of Electronic TechnologyGuilin 541004China Shanghai Institute of Optics and Fine Mechanics Chinese Academy of SciencesShanghai 201800China

Nano-focusing structures based on hybrid plasmonic waveguides are likely to play a key role in strong nonlinear optical *** the insertion loss is considerable,a significant nonlinear phase shift may be achieved by decreasing the nano-focusing device footprint and careful parameter ***,we study the Kerr effect in hybrid plasmonic waveguides by analyzing the mode effective area,energy velocity,and insertion ***,by utilizing plasmonics to manipulate the effective index and mode similarity,the TM mode is reflected and absorbed,while the TE mode passes through with relatively low propagation *** providing a deep understanding of hybrid plasmonic waveguides for nonlinear applications,we indicate pathways for their future optimization.

关键词： silicon photonics plasmonics nonlinear optics nano-focusing

来源：评论

学校读者我要写书评

暂无评论

AEMIM: Adversarial Examples Meet Masked Image Modeling

arXiv

引用

arXiv 2024年

作者： Xiang, Wenzhao Liu, Chang Su, Hang Yu, Hongyang Beijing100190 China Peng Cheng Laboratory Shenzhen10587 China University of the Chinese Academy of Sciences Beijing100049 China Institute of Image Communication and Networks Engineering Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Technology Tsinghua University Beijing100084 China

Masked image modeling (MIM) has gained significant traction for its remarkable prowess in representation learning. As an alternative to the traditional approach, the reconstruction from corrupted images has recently emerged as a promising pretext task. However, the regular corrupted images are generated using generic generators, often lacking relevance to the specific reconstruction task involved in pre-training. Hence, reconstruction from regular corrupted images cannot ensure the difficulty of the pretext task, potentially leading to a performance decline. Moreover, generating corrupted images might introduce an extra generator, resulting in a notable computational burden. To address these issues, we propose to incorporate adversarial examples into masked image modeling, as the new reconstruction targets. Adversarial examples, generated online using only the trained models, can directly aim to disrupt tasks associated with pre-training. Therefore, the incorporation not only elevates the level of challenge in reconstruction but also enhances efficiency, contributing to the acquisition of superior representations by the model. In particular, we introduce a novel auxiliary pretext task that reconstructs the adversarial examples corresponding to the original images. We also devise an innovative adversarial attack to craft more suitable adversarial examples for MIM pre-training. It is noted that our method is not restricted to specific model architectures and MIM strategies, rendering it an adaptable plug-in capable of enhancing all MIM methods. Experimental findings substantiate the remarkable capability of our approach in amplifying the generalization and robustness of existing MIM methods. Notably, our method surpasses the performance of baselines on various tasks, including ImageNet, its variants, and other downstream tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

SJA: Server-driven Joint Adaptation of Loss and Bitrate for Multi-Party Realtime Video Streaming

SJA: Server-driven Joint Adaptation of Loss and Bitrate for ...

引用

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

作者： Kai Shen Dayou Zhang Zi Zhu Lei Zhang Fangxin Wang Dan Wang The Future Network of Intelligence Institute The Chinese University of Hong Kong Shenzhen School of Science and Engineering The Chinese University of Hong Kong Shenzhen College of Computer Science and Software Engineering Shenzhen University Peng Cheng Laboratory The Guangdong Provincial Key Laboratory of Future Networks of Intelligence Department of Computing The Hong Kong Polytechnic University

The outbreak of COVID-19 has dramatically promoted the explosive proliferation of multi-party realtime video streaming (MRVS) services, represented by Zoom and Microsoft Teams. Different from Video-on-Demand (VoD) or live streaming, MRVS enables all-to-all realtime video communication, bringing significant challenges to service providing. First, unreliable network transmission can cause network loss, resulting in delay increase and visual quality degradation. Second, the transformation from two-party to multi-party communication makes resource scheduling much more difficult. Moreover, optimizing the overall QoE requires a global coordination, which is quite challenging given the various impact factors such as bitrate and *** this paper, we propose the SJA framework, which is, to our best knowledge, the first server-driven joint loss and bitrate adaptation framework in multi-party realtime video streaming services towards maximized QoE. We comprehensively design an appropriate QoE model for MRVS services to capture the interplay among perceptual quality, variations, bitrate mismatch, loss damage, and streaming delay. We mathematically formulate the QoE maximization problem in MRVS services. A Lyapunov-based relaxation and the SJA algorithm are further designed to address the optimization problem with close-to-optimal performance. Evaluations show that our framework can outperform the SOTA solutions by 18.4% ∼ 46.5%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comments on "BSIF: Blockchain-Based Secure, Interactive, and Fair Mobile Crowdsensing"

TechRxiv

引用

TechRxiv 2023年

作者： Wang, Haiyan Luo, Fucai Yan, Xingfu The School of Mathematics and Statistics Minnan Normal University Zhangzhou China The Department of New Networks Peng Cheng Laboratory Shenzhen China The Guangdong Provincial Key School of Computer Science and Engineering South China University of Technology Guangzhou China

Mobile crowdsensing (MCS) is a promising sensing paradigm which allows users to outsource a range of sensing tasks to a crowd of mobile workers with mobile devices. Location-dependent MCS, as the name implies, is a geographically-dependent sensing paradigm in which service requestors outsource location-specific tasks to many workers with mobile devices, and the workers accepting the tasks collect data at a particular location by physically arriving at the desired locations. Many efforts have been devoted to protecting location privacy of the workers accepting the tasks while ensuring task allocation accuracy and efficiency. In 2022, Wang et al. [5] proposed BSIF, a blockchain-based MCS system (published in IEEE Journal on Selected Areas in Communications (JSAC)) that can prevent not only illegitimate participants but also location privacy leakage. For the purpose of protecting location privacy, they proposed a location-based symmetric key generation algorithm, which coordinates session keys for the target ranges between the service requestor and the workers accepting the tasks without revealing the location information. However, in this paper, we will point out a flaw in their location-based symmetric key generation algorithm, which indicates that BSIF does not work. Furthermore, we propose a novel approach to achieve the location-based symmetric key generation using a witness encryption scheme. © 2023, CC BY.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

100 Gb/s NRZ OOK signal regeneration on a silicon chip

100 Gb/s NRZ OOK signal regeneration on a silicon chip

引用

CLEO: Science and Innovations, S and I 2022

作者： Wen, Hua Shun Cui, Jia Bin Zhou, Heng Chen, Yin Fang Jin, Ya Xu, Bo Rui Zhai, Kun Peng Sun, Jia Zheng Guo, Yuan Yuan Wu, Yan Ran Chen, Wen Chen, Wei Wang, Xin Zhu, Ning Hua Lu, Guo-Wei Ji, Gui Jun Zhou, Dennis Chi Cheng, Yiu-Kwok Yang, Da-Quan Li, Ming State Key Laboratory on Integrated Optoelectronics Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory of Information Photonics and Optical Communications School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Key Laboratory of Optical Fiber Sensing and Communication Networks School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China Division of Computer Engineering The University of Aizu Fukushima965-8580 Japan Ltd. Zhuhai519000 China

All-optical regeneration of 100 Gb/s NRZ OOK signal with 3.6 dB extinction ratio and 0.5 dB quality factor improvements is experimentally demonstrated using a silicon waveguide with reverse-biased p-i-n junction for t... 详细信息

ISBN: (纸本)9781557528209

关键词： Amplitude shift keying

来源：评论

学校读者我要写书评

暂无评论

Using Depth-Enhanced Spatial Transformation for Student Gaze Target Estimation in Dual-View Classroom Images

Using Depth-Enhanced Spatial Transformation for Student Gaze...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Haonan Miao Peizheng Zhao Yuqi Sun Fang Nan Xiaolong Zhang Yaqiang Wu Feng Tian School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Dual-view gaze target estimation in classroom environments has not been thoroughly explored. Existing methods lack consideration of depth information, primarily focusing on 2D image information and neglecting the latent 3D spatial context, which could lead to suboptimal transformation and cause the gaze cone to intersect with an incorrect object. This paper introduces a novel dual-view gaze target estimation method tailored for classroom settings, leveraging depth-enhanced spatial transformations. By formulating a depth-enhanced 2D space, our method uses depth-enhanced spatial transformation to accurately project students’ gaze cones to the teacher-oriented image. Additionally, we collected a dataset named DVSGE, specifically for student gaze target estimation in dual-view classroom images. Experimental results demonstrate significant performance improvements of 9.8% in AUC and 19.9% in L2-Distance for our method, surpassing existing methods.

关键词： Three-dimensional displays Estimation Focusing Signal processing Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Sal²RN: A Spatial-Spectral Salient Reinforcement Network for Hyperspectral and LiDAR Data Fusion Classification

引用

IEEE Transactions on Geoscience and Remote Sensing 2023年 61卷 1页

作者： Li, Jiaojiao Liu, Yuzhe Song, Rui Li, Yunsong Han, Kailiang Du, Qian Xidian University State Key Laboratory of Integrated Service Networks Xi'an710071 China Cas Key Laboratory of Spectral Imaging Technology Xi'an710119 China Shanghai Institute of Technical Physics Chinese Academy of Sciences Key Laboratory of Intelligent Infrared Perception Shanghai200083 China Mississippi State University Department of Electrical and Computer Engineering StarkvilleMS39762 United States

Hyperspectral image (HSI) and light detection and ranging (LiDAR) data fusion have been widely employed in HSI classification to promote interpreting performance. In the existing deep learning methods based on spatial-spectral features, the features extracted from different layers are treated fairly in the learning process. In reality, features extracted from the continuous layers contribute differentially to the final classification, such as large tracts of woodland and agriculture typically count on shallow contour features, whereas deep semantic spectral features have meaningful constraints for small entities like vehicles. Furthermore, the majority of existing classification algorithms employ a patch input scheme, which has a high probability to introduce pixels of different categories at the boundary. To acquire more accurate classification results, we propose a spatial-spectral saliency reinforcement network (Sal2RN) in this article. In spatial dimension, a novel cross-layer interaction module (CIM) is presented to adaptively alter the significance of features between various layers and integrate these diversified features. Moreover, a customized center spectrum correction module (CSCM) integrates neighborhood information and adaptively modifies the center spectrum to reduce intraclass variance and further improve the classification accuracy of the network. Finally, a statistically based feature weighted combination module is constructed to effectively fuse spatial, spectral, and LiDAR features. Compared with traditional and advanced classification methods, the Sal2RN achieves the state-of-the-art classification performance on three open benchmark datasets. © 1980-2012 IEEE.

关键词： Optical radar

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：