检索结果-内蒙古大学图书馆

Two-timescale Optimization for E2E Network Slicing-aided Cloud-edge Collaborative networks

IEEE Transactions on Vehicular Technology 2025年

作者： Wang, Yunfeng Zhao, Liqiang Chu, Xiaoli Song, Shenghui Deng, Yansha Nallanathan, Arumugam Zhou, Guorong Xidian University State Key Laboratory of Integrated Services Networks Xi'an710071 China Xidian University Guangzhou Institute of Technology Guangzhou510100 China University of Sheffield Department of Electronic and Electrical Engineering SheffieldS10 2TN United Kingdom Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong King's College London Department of Engineering LondonWC2R 2LS United Kingdom Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom Kyung Hee University Department of Electronic Engineering Gyeonggi-do Yongin-si17104 Korea Republic of

To leverage the synergy between cloud computing (CC) and edge computing (EC) to support various services while reducing the CC/EC switching overhead, the two-timescale utility maximization problem for an end-to-end network slicing-aided cloud-edge collaborative network (E2E-CECN) is formulated covering both the high throughput and low delay service requirements. To solve the utility maximization problem while dynamically adjusting the weights of the E2E-CECN utility to accommodate the variation of users' service requests, we proposed a reward comparison double deep Q network algorithm to optimize the large timescale joint virtual base station activation and CC-EC scheduling, and a reward comparison deep deterministic policy gradient algorithm to optimize the small timescale allocation of backhaul link capacity (BLC), CC/EC capability and transmission power. Numerical results show that both the high-throughput and low-delay service requirements can be satisfied simultaneously under the reasonable BLC usage and power consumption. © 1967-2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

FedForgery: Generalized Face Forgery Detection with Residual Federated Learning

arXiv

引用

arXiv 2022年

作者： Liu, Decheng Dang, Zhan Peng, Chunlei Zheng, Yu Li, Shuang Wang, Nannan Gao, Xinbo The State Key Laboratory of Integrated Services Networks School of Cyber Engineering Xidian University Shaanxi Xi’an710071 China The School of Cyber Engineering Xidian University Shaanxi Xi’an710071 China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai201112 China The State Key Laboratory of Integrated Services Networks School of Telecommunications Engineering Xidian University Shaanxi Xi’an710071 China The Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing400065 China

With the continuous development of deep learning in the field of image generation models, a large number of vivid forged faces have been generated and spread on the Internet. These high-authenticity artifacts could grow into a threat to society security. Existing face forgery detection methods directly utilize the obtained public shared or centralized data for training but ignore the personal privacy and security issues when personal data couldn’t be centralizedly shared in real-world scenarios. Additionally, different distributions caused by diverse artifact types would further bring adverse influences on the forgery detection task. To solve the mentioned problems, the paper proposes a novel generalized residual Federated learning for face Forgery detection (FedForgery). The designed variational autoencoder aims to learn robust discriminative residual feature maps to detect forgery faces (with diverse or even unknown artifact types). Furthermore, the general federated learning strategy is introduced to construct distributed detection model trained collaboratively with multiple local decentralized devices, which could further boost the representation generalization. Experiments conducted on publicly available face forgery detection datasets prove the superior performance of the proposed FedForgery. The designed novel generalized face forgery detection protocols and source code would be publicly available at https://***/GANG370/FedForgery. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

NoncovANM: Gridless DOA Estimation for LPDF System

arXiv

引用

arXiv 2023年

作者： Zhao, Yangying Chen, Peng Cao, Zhenxin Wang, Xianbin The State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China State Key Laboratory of Integrated Services Networks Xidian University Xi’an710071 China State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China The Department of Electrical and Computer Engineering Western University LondonONN6A 3K7 Canada

Direction of arrival (DOA) estimation is an important research in the area of array signal processing, and has been studied for decades. High resolution DOA estimation requires large array aperture, which leads to the increase of hardware cost. Besides, high accuracy DOA estimation methods usually have high computational complexity. In this paper, the problem of decreasing the hardware cost and algorithm complexity is addressed. First, considering the ability of flexible controlling the electromagnetic waves and low-cost, an intelligent reconfigurable surface (IRS)-aided low-cost passive direction finding (LPDF) system is developed, where only one fully functional receiving channel is adopted. Then, the sparsity of targets direction in the spatial domain is exploited by formulating an atomic norm minimization (ANM) problem to estimate the DOA. Traditionally, solving ANM problrm is complex and cannot be realized efficiently. Hence, a novel nonconvex-based ANM (NC-ANM) method is proposed by gradient threshold iteration, where a perturbation is introduced to avoid falling into saddle points. The theoretical analysis for the convergence of the NC-ANM method is also given. Moreover, the corresponding Cramér-Rao lower bound (CRLB) in the LPDF system is derived, and taken as the referred bound of the DOA estimation. Simulation results show that the proposed method outperforms the compared methods in the DOA estimation with lower computational complexity in the LPDF system. Copyright © 2023, The Authors. All rights reserved.

关键词： Radio direction finding systems

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimization of Space-Air-Ground Integrated Network Slicing Relying on a Pair of Central and Distributed Learning Algorithms

arXiv

引用

arXiv 2023年

作者： Zhou, Guorong Zhao, Liqiang Zheng, Gan Song, Shenghui Zhang, Jiankang Hanzo, Lajos Key Laboratory of Integrated Service Networks Xidian University Xi’an710071 China Key Laboratory of Integrated Service Networks Xidian University Xi’an710071 China School of Engineering University of Warwick CoventryCV4 7AL United Kingdom Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong Department of Computing & Informatics Bournemouth University BH12 5BB United Kingdom School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom

As an attractive enabling technology for next-generation wireless communications, network slicing supports diverse customized services in the global space-air-ground integrated network (SAGIN) with diverse resource constraints. In this paper, we dynamically consider three typical classes of radio access network (RAN) slices, namely high-throughput slices, low-delay slices and wide-coverage slices, under the same underlying physical SAGIN. The throughput, the service delay and the coverage area of these three classes of RAN slices are jointly optimized in a non-scalar form by considering the distinct channel features and service advantages of the terrestrial, aerial and satellite components of SAGINs. A joint central and distributed multi-agent deep deterministic policy gradient (CDMADDPG) algorithm is proposed for solving the above problem to obtain the Pareto optimal solutions. The algorithm first determines the optimal virtual unmanned aerial vehicle (vUAV) positions and the inter-slice sub-channel and power sharing by relying on a centralized unit. Then it optimizes the intra-slice sub-channel and power allocation, and the virtual base station (vBS)/vUAV/virtual low earth orbit (vLEO) satellite deployment in support of three © 2023, CC BY-NC-ND.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Computing Safest $st$-Paths in Backbone networks: Efficiently Solvable Cases and Fast Heuristics

Computing Safest $st$-Paths in Backbone Networks: Efficientl...

引用

International Workshop on Reliable networks Design and Modeling (RNDM)

作者： Balázs Vass Péter Revisnyei Alija Pašíć Department of Telecommunications and Artificial Intelligence (TMIT) Faculty of Electrical Engineering and Informatics (VIK) High Speed Networks Laboratory (HSNLab) Budapest University of Technology and Economics (BME) Budapest Hungary Faculty of Mathematics and Computer Science Babeș-Bolyai University Cluj Napoca Romania HUN-REN-BME Information Systems Research Group Budapest Hungary

ISBN: (数字)9798331518189

ISBN: (纸本)9798331518196

For proper evaluation and optimization of the expected availability of a backbone network service, two related very fundamental modeling and algorithmic questions are the following. 1) Realistically estimate the availability of a given $st$ -path for some source and target pair of communicating nodes $s$ and $t$ , and 2) Find a safest $st$ -path. For these, traditional approaches suppose network element failures are independent. In this paper, we show that, by not considering joint failure probabilities, the traditional approaches may misguess the $st$ -path availabilities and, consequently, the total connection availability, which can lead to more frequent Service Level Agreement (SLA) violations and a financial burden on the Communication Service Provider (CSP). Due to the inconsistent estimations, the supposedly safest paths yielded by these approaches may turn out to be suboptimal. On the positive side, we propose a fast algorithmic approach, that, under some assumptions, returns with a (truly) safest $st$ -path accompanied by its exact expected availability. When the aforementioned assumptions do not hold, in our simulations, the proposed algorithmic scheme proved to be a good heuristic, performing at least as well as the traditional method.

关键词： Computational modeling Heuristic algorithms Conferences Estimation Hazards Computational efficiency Optimization Service level agreements

来源：评论

学校读者我要写书评

暂无评论

Covert Communication via IRS with Unequal Transmit Prior Probabilities

Covert Communication via IRS with Unequal Transmit Prior Pro...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Yujie Wu Mingqian Liu Lexi Xu Nan Zhao Xianbin Wang Derrick Wing Kwan Ng School of Information and Communication Engineering Dalian University of Technology Dalian China State Key Laboratory of Integrated Service Networks Xidian University Xian Shaanxi China China Unicom Research aInstitute Beijing China Department of Electrical and Computer Engineering Western University London Canada School of Electrical Engineering and Telecommunications University of New South Wales Sydney NSW Australia

Covert communication assisted by intelligent reflecting surface (IRS) has been widely investigated. Specifically, IRS can reconfigure wireless propagation environment to introduce uncertainty to the warden for covertness provisioning. In this paper, we propose an IRS-assisted finite-blocklength covert communication scheme with unequal transmit prior probabilities (UTPP) resulting from random packet generation at the transmitter. First, we analyze the warden's detection performance with its optimal detection threshold derived, which is the worst case for covert transmission. Then, we jointly optimize the transmit power, the blocklength, the phase shifts of IRS, and the transmit prior probabilities to maximize the effective covert throughput (ECT). Theoretical analysis reveal that UTPP can perform better tradeoff between ECT and covertness than equal transmit prior probabilities. Finally, numerical results demonstrate the superiority of the proposed covert communication scheme with UTPP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network Enhanced Chip-on-Board Hybrid-Packaged Photonic-Electrical Silicon Transceiver for High-speed Optical Interconnects

Deep Neural Network Enhanced Chip-on-Board Hybrid-Packaged P...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Jun Qin Qipeng Yang Changhao Han Yan Zhou Yunhao Zhang Yichen WU Yu Sun Junde Lu Siming Liu Yueqin Li Jian Sun Miao Min Weiwei Hu Zhixue He Lei Wang Shaohua Yu Haowen Shu Xingjun Wang Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument Beijing Information Science and Technology University Beijing China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing China Department of Electrical and Computer Engineering University of California Santa Barbara CA USA Peking University Yangtze Delta Institute of Optoelectronics Nantong China Peng Cheng Laboratory Shenzhen China State Key Laboratory of Information Photonics and Optical Communications BUPT Beijing China

We explore implementing a multilevel deep neural network to enhance the performance of a 4-channel photonic-electrical hybrid-packaged silicon transceiver. Stable transmission and reception of 150 Gbps/λ PAM4 signals... 详细信息

ISBN: (纸本)9798350369311

关键词： Electric potential Optical interconnections System performance Artificial neural networks Transceivers Silicon Electro-optical waveguides Photonics

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Delegated Private Set Intersection Cardinality Protocol

SSRN

引用

SSRN 2023年

作者： Yang, Xiaoyi Zhao, Yanqi Zhou, Sufang Wang, Lianhai Department of Computing The Hong Kong Polytechnic University Hong Kong School of Cyberspace Security Xi’an University of Posts and Telecommunications Xi’an710121 China School of Computer and Information Engineering Henan University Kaifeng475004 China Shandong Provincial Key Laboratory of Computer Networks Qilu University of Technology Shandong Academy of Sciences Jinan250014 China

Secure multiparty computation (MPC) is an important means to realize privacy computing (PC). Private set intersection cardinality (PSI-CA) is a variant of an important problem in MPC research, that is private set intersection. PSI-CA allows multiple participants jointly compute the size of the common intersection of their private sets through interaction without revealing any other information about their respective sets. Delegated PSI-CA delegates a large number of computing in the protocol to some untrusted cloud servers, which makes the protocol efficient. Delegated PSI-CA is considered to be of great significance for the construction of privacy-preserving contact tracing systems recently. However, the existing work is still not ideal for the resource-limited mobile terminal of clients. In this paper, we propose a lightweight delegated PSI-CA protocol based on multi-point oblivious pseudorandom function and collision-resistant hash function. Our protocol does not need to do additional pre-operations, so the computation complexity and the communication complexity on the client side are further reduced compare to the existing works. In addition, we build a privacy-preserving contact tracing system by utilizing our protocol, which can be publicly checked, named PC-CONTrace. The experimental results show that our system is more practical and advantageous for densely populated areas. © 2023, The Authors. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

On a Scalable Path for Multimode MIMO-DSP

arXiv

引用

arXiv 2022年

作者： Barbosa, Fabio A. Rothe, Stefan Pohle, Dennis Czarske, Jürgen W. Ferreira, Filipe M. Optical Networks Dept Electronic & Electrical Eng University College London United Kingdom Laboratory of Measurement and Sensor System Technique Faculty of Electrical and Computer Engineering TU Dresden Dresden01062 Germany

A novel MIMO-DSP for space-division multiplexing over multimode fibres is proposed. A principal modes approach is shown to provide two-fold benefits: over 13 times channel memory reduction while minimising the number ... 详细信息

关键词： Space division multiple access

来源：评论

学校读者我要写书评

暂无评论

Augmented V2V Radio Fingerprinting With Heterogeneous Federated Scattering Network for Autonomous Vehicle Road Cooperation

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Zhang, Tiantian Xu, Dongyang Ma, Jing Alharbi, Abdullah Yu, Keping Guizani, Mohsen Leung, Victor C.M Xi'an Jiaotong University School of Cyber Science and Engineering Xi'an710049 China Xi'an Jiaotong University School of Information and Communication Engineering Xi'an710049 China Xidian University State Key Laboratory of Integrated Services Networks China King Saud University Computer Science Department Community College Riyadh11437 Saudi Arabia Hosei University Graduate School of Science and Engineering Tokyo184-8584 Japan 999041 United Arab Emirates Shenzhen MSU-BIT University Artificial Intelligence Research Institute Shenzhen518172 China Shenzhen University College of Computer Science and Software Engineering Shenzhen528060 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

Augmented Internet of vehicle (IoV) network, providing natural infrastructure support for autonomous vehicle road cooperation (VRC), has been deemed as one of key enablers for autonomous VRC while simultaneously facing the challenge of impersonation, tampering or replay attack towards the high layer digital certificate for critical information. In this paper, we propose a heterogeneous scattering fingerprinting network (HSFNet) which amalgamates wavelet scattering and deep learning to achieve lightweight, rapid and reliable physical layer authentication by radio frequency fingerprinting (RFF) which employs the unique inherent hardware impairments within for vehicle-to everything (V2X) communication. Particularly, we first exploit a wavelet scattering network to extract RFF coefficients and eliminate redundancies within heterogeneous datasets. The establishment of a high-information-density datasets facilitates the efficient processing of extensive heterogeneous data, especially for resource-limited vehicles nodes. To improve the interpretability, we combine the multi-scale coefficients of input waveform and shapley values, formulating a complete interpretable framework and completing parameters tuning. Finally, considering heterogeneous applications in practical scenarios, we design a distributed federated learning framework which not only completes distributed training but also protects privacy with the resources-constrained intelligent IoV nodes. Experimental results demonstrate that the proposed scheme maintains excellent performance while utilizing only about 25.7% of original samples, significantly improving identification accuracy. Furthermore, the identification accuracy of federated learning ultimately converges to 98.1%. © 1967-2012 IEEE.

关键词： Deep learning

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：