检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Xiao, Wenjing Shi, Chenglong Chen, Miaojiang Liu, Zhiquan Chen, Min Song, H. Herbert Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China School of Computer Electronics and Information Guangxi University Nanning530004 China School of Computer Science and Engineering South China University of Technology Guangzhou510006 China Pazhou Laboratory Guangzhou510330 China College of Cyber Security Jinan University Guangzhou510632 China

With the exponential growth of Internet of Things (IoT) devices, edge computing (EC) is gradually playing an important role in providing cost-effective services. However, existing approaches struggle to perform well in graph-structured scenarios where user data is correlated, such as traffic flow prediction and social relationship recommender systems. In particular, graph neural network (GNN)based approaches lead to expensive server communication cost. To address this problem, we propose GraphEdge, an efficient GNN-based EC architecture. It considers the EC system of GNN tasks, where there are associations between users and it needs to take into account the task data of its neighbors when processing the tasks of a user. Specifically, the architecture first perceives the user topology and represents their data associations as a graph layout at each time step. Then the graph layout is optimized by calling our proposed hierarchical traversal graph cut algorithm (HiCut), which cuts the graph layout into multiple weakly associated subgraphs based on the aggregation characteristics of GNN, and the communication cost between different subgraphs during GNN inference is minimized. Finally, based on the optimized graph layout, our proposed deep reinforcement learning (DRL) based graph offloading algorithm (DRLGO) is executed to obtain the optimal offloading strategy for the tasks of users, the offloading strategy is subgraph-based, it tries to offload user tasks in a subgraph to the same edge server as possible while minimizing the task processing time and energy consumption of the EC system. Experimental results show the good effectiveness and dynamic adaptation of our proposed architecture and it also performs well even in dynamic scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

COO-DuDo: computation overhead optimization methods for dual-domain sparse-view CT reconstruction

引用

Expert Systems with Applications 2025年 286卷

作者： Deng, Zihan Wang, Zhisheng Shan, Yuanlin He, Guohang Du, Tiantian Wang, Shunli Center of Ultra-Precision Optoelectronic Instrument Engineering Harbin Institute of Technology Harbin150080 China Ministry of Industry and Information Technology Harbin150080 China Artificial Intelligence Media Computing Laboratory School of Computer Science and Technology Harbin Engineering University Harbin150080 China Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Electronic and Information Guangxi University Nanning530000 China Faculty of Education University of Hong Kong Hong Kong

Recently, deep learning methods have shown exciting effects in Sparse-view CT reconstruction. The Dual-Domain (DuDo) deep learning method is one of the representative methods, and it can process the information in both the sinogram and image domains. However, the existing DuDo methods do not pay enough attention to the allocation of training costs and strategies for the two domains, which will result in wasted computing overhead or insufficient training in one of the two domains. In this paper, we propose a Computation-Overhead Optimization (COO) DuDo training strategy for sparse-view CT reconstruction, i.e., COO-DuDo. The training ratio of different domains is controlled by calculating their computation overhead, loss, and gradient variation of the loss. To make our COO-DuDo strategy enable sparse-view CT reconstruction better, we adopt a DuDo-network (COO-DDNet) structure based on two coding-decoding-type subnetworks. The evaluation, animal and clinical experiments have verified the effectiveness of our training strategies and methods. Our research provides a broader perspective for dual-domain image restoration tasks from the perspective of computational overhead. © 2025 Elsevier Ltd

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

TDiffSal: Text-Guided Diffusion Saliency Prediction Model for Images 27th

TDiffSal: Text-Guided Diffusion Saliency Prediction Model fo...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhang, Nana Xiong, Min Zhu, Dandan Zhu, Kun Zhai, Guangtao School of Computer Science and Technology Donghua University No. 2999 Renmin North Road Songjiang District Shanghai201620 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210093 China Institute of AI Education Shanghai East China Normal University No. 3663 Zhongshan North Road Putuo District Shanghai200333 China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University No. 4800 Cao’an Highway Jiading District Shanghai201804 China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University No. 800 Dongchuan Road Minhang District Shanghai200240 China

ISBN: (纸本)9783031781858

Existing visual saliency prediction methods mainly focus on single-modal visual saliency prediction, while ignoring the significant impact of text on visual saliency. To more comprehensively explore the influence of text on human attention in images, we propose a text-guided diffusion saliency prediction model, named TDiffSal. In specific, recent studies on stable diffusion models have shown promising performance in unifying tasks due to their inherent generalization ability. Inspired by this, a novel diffusion model for generalized visual-text saliency prediction is proposed, which formulates the prediction issue as a conditional generative task of the saliency map by employing input visual and text as the conditions. Meanwhile, we introduce a multi-head fusion module to effectively integrate text features and image features, which can efficiently guide the image denoising process and progressively refine the generated saliency map to make it semantically relevant to the text. Additionally, we employ an efficient pre-training strategy to enhance the robustness and generalization of the proposed model. We conduct extensive experiments on benchmark datasets to demonstrate its superior performance compared to other state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Self-Attention Policy Optimization for Task Offloading and Resource Allocation in Low-Carbon Agricultural Consumer Electronic Devices

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Huang, Yi Zeng, Jisong Wei, Yanting Chen, Miaojiang Xiao, Wenjing Yang, Yang Liu, Zhiquan Farouk, Ahmed Song, Houbing Herbert Guangxi University School of Computer Electronics and Information China Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China Jinan University College of Cyber Security Guangzhou510632 China Faculty of Computers and Artificial Intelligence Egypt Department of Information Systems BaltimoreMD21250 United States

In recent years, the widespread use of edge agricultural consumer electronics has greatly contributed to the level of intelligence in agricultural production, bringing higher efficiency and quality. However, offloading all tasks to the cloud incurs significant latency and resource waste, while relying solely on edge computing fails to meet the computational demands of the entire system. To solve the above problems, we introduce the device-edge-cloud (DEC) three-layer architecture, where agri-consumer electronics devices can partially offload tasks to the edge, and the edge can partially offload tasks to the cloud, i.e., agri-consumer electronics can realize device-edge-cloud collaborative computation. Second, we model the joint computation offloading and resource allocation optimization problem as a non-convex optimization and propose a novel Self-Attention Policy Optimization (SAPO) algorithm to solve it. Experiments show that the joint optimization performance of the proposed SAPO exceeds the baseline, and it is suitable for many different models. Compared with fully connected networks, it has better convergence and robustness, with a convergence speed 50% faster than the fully connected networks. The proposed SAPO algorithm has good scalability and adaptability, and has the potential to be extended to smart agricultural computing scenarios with non-convex optimization. © 1975-2011 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

A Survey of Secure Semantic communications

arXiv

引用

arXiv 2025年

作者： Meng, Rui Gao, Song Fan, Dayu Gao, Haixiao Wang, Yining Xu, Xiaodong Wang, Bizhu Lv, Suyu Zhang, Zhidi Sun, Mengying Han, Shujun Dong, Chen Tao, Xiaofeng Zhang, Ping State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Department of Broadband Communication Peng Cheng Laboratory Guangdong Shenzhen518066 China School of Information Science and Technology Beijing University of Technology Beijing100124 China National Engineering Laboratory for Mobile Network Technologies Beijing University of Posts and Telecommunications Beijing100876 China

Semantic communication (SemCom) is regarded as a promising and revolutionary technology in 6G, aiming to transcend the constraints of "Shannon’s trap" by filtering out redundant information and extracting the core of effective data. Compared to traditional communication paradigms, SemCom offers several notable advantages, such as reducing the burden on data transmission, enhancing network management efficiency, and optimizing resource allocation. Numerous researchers have extensively explored SemCom from various perspectives, including network architecture, theoretical analysis, potential technologies, and future applications. However, as SemCom continues to evolve, a multitude of security and privacy concerns have arisen, posing threats to the confidentiality, integrity, and availability of SemCom systems. This paper presents a comprehensive survey of the technologies that can be utilized to secure SemCom. Firstly, we elaborate on the entire life cycle of SemCom, which includes the model training, model transfer, and semantic information transmission phases. Then, we identify the security and privacy issues that emerge during these three stages. Furthermore, we summarize the techniques available to mitigate these security and privacy threats, including data cleaning, robust learning, defensive strategies against backdoor attacks, adversarial training, differential privacy, cryptography, blockchain technology, model compression, and physical-layer security. Lastly, this paper outlines future research directions to guide researchers in related fields. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Joint Placement and Beamforming Design in UAV Enabled Multi-Stage ISAC System

引用

IEEE Transactions on communications 2025年

作者： Xu, Linlin Zhu, Qi Xia, Wenchao Wang, Zhongbin Quek, Tony Q. S. Zhu, Hongbo Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Wireless Communications Nanjing210003 China ZTE Corporation State Key Laboratory of Mobile Network and Mobile Multimedia Technology Wireless Computing Research Institute Shenzhen518055 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore Yonsei University Yonsei Frontier Laboratory Seoul03722 Korea Republic of

In this paper, we propose an unmanned aerial vehicle (UAV) enabled multi-stage integrated sensing and communications (ISAC) system, where a multi-antenna equipped UAV performs location sensing for a target whose location is initially unknown, while serves the communication users simultaneously, with the aid of an existing receive access point (RAP). By fusing the measurement results of the UAV and RAP, the location of the target is estimated. To improve the location sensing accuracy, we propose a multi-stage location sensing scheme. Specifically, in the first stage, in the absence of prior knowledge about the target’s location, the UAV fixes at the initial location and adjusts the beamformer to perform wide beam sensing to probe the target. In the following stages, with the previous coarse estimation result of the target’s location, the UAV performs narrow beam sensing by jointly adjusting the placement and also transmit beamformer. Besides, the quality of service requirements of the users are guaranteed in all stages. Accordingly, optimization problems are formulated for the first and following stages, respectively. By involving the semidefinite relaxation technique and then solving a quadratic semidefinite programming problem, the solution in the first stage is obtained. In the following stages, we jointly apply the alternating optimization, successive convex approximation, trust region, and also Dinkelbach’s methods to address the intricate coupling between the UAV placement and beamformer. Finally, numerical results demonstrate the effectiveness of the proposed algorithms. © 1972-2012 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

MIFNet: Learning Modality-Invariant Features for Generalizable Multimodal Image Matching

arXiv

引用

arXiv 2025年

作者： Liu, Yepeng Sun, Zhichao Yu, Baosheng Zhao, Yitian Du, Bo Xu, Yongchao Cheng, Jun National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430070 China Lee Kong Chian School of Medicine Nanyang Technological University 308232 Singapore Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Zhejiang Ningbo315211 China 1 Fusionpolis Way #21-01 Connexis South Tower Singapore138632 Singapore

Many keypoint detection and description methods have been proposed for image matching or registration. While these methods demonstrate promising performance for single-modality image matching, they often struggle with multimodal data because the descriptors trained on single-modality data tend to lack robustness against the non-linear variations present in multimodal data. Extending such methods to multimodal image matching often requires well-aligned multimodal data to learn modality-invariant descriptors. However, acquiring such data is often costly and impractical in many real-world scenarios. To address this challenge, we propose a modality-invariant feature learning network (MIFNet) to compute modality-invariant features for keypoint descriptions in multimodal image matching using only single-modality training data. Specifically, we propose a novel latent feature aggregation module and a cumulative hybrid aggregation module to enhance the base keypoint descriptors trained on single-modality data by leveraging pretrained features from Stable Diffusion models. We validate our method with recent keypoint detection and description methods in three multimodal retinal image datasets (CF-FA, CF-OCT, EMA-OCTA) and two remote sensing datasets (Optical-SAR and Optical-NIR). Extensive experiments demonstrate that the proposed MIFNet is able to learn modality-invariant feature for multimodal image matching without accessing the targeted modality and has good zero-shot generalization ability. The source code will be made publicly available. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous UAV Resource Scheduling for Dynamic Time Sensitive Target Detection and Interference

引用

IEEE Internet of Things Journal 2025年

作者： Wan, Liangtian Wang, Jiashuai Sun, Lu Li, Kuixian Xiong, Xuanrui Lin, Yun Dalian University of Technology Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian116620 China Dalian Maritime University Institute of Information Science Technology Department of Communication Engineering Dalian116026 China Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China

In complex electromagnetic environments, targets that need to be interfered with often possess high levels of concealment and anti-interference capabilities. Additionally, due to the dynamic characteristics of these targets, interference tasks must be conducted within strict time constraints to ensure interference effect. In this paper, we adopt a reconnaissance-first approach for concealed targets. After detecting the accurate location of the target, we deploy Unmanned Aerial Vehicles (UAVs) to interfere with the targets. First, we established a UAV swarm task scheduling optimization model after considering constraints such as target threat range, priority of reconnaissance and interference tasks, interference task time, and UAV energy consumption. Meanwhile, we model the anti-interference capability of the target as a threat range. Second, we propose a non-dominated sorting genetic algorithm based on distance in the solution space and a dynamic parent selection strategy (DPSNSGA-II) to solve UAV Resource Scheduling optimization problem. The diversity of the population is increased and the situation of falling into local optima is reduced by improving the parent individual selection strategy, mutation strategy, and elite solution retention mechanism. Finally, we construct two data sets of varying sizes to evaluate the quality of solution sets and the convergence performance of the proposed algorithm. The simulation results indicate that the proposed DPSNSGA-II algorithm has better result for population diversity and convergence compared to state-of-the-art algorithms. © 2014 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Efficient nonlinear equalization across S+C+L bands using online knowledge distillation in high-capacity DWDM systems

引用

Optics Express 2025年第10期33卷 20433-20448页

作者： Zhang, Tianqian He, Qingyu Luo, Ming Liu, Wu Wang, Dong Zhang, Dechao Zhang, Bin Yao, Shuchang Li, Chongyang Liu, Shouyin Dept. of Electronic and Information Engineering College of Physical Science and Technology Central China Normal University Hubei Wuhan430074 China State Key Laboratory of Optical Communication Technologies and Networks China Information Communication Technologies Group Corporation Hubei Wuhan430074 China Department of Fundamental Network Technology China Mobile Research Institute Beijing100053 China Fiberhome Telecommunication Technologies Co. Ltd Wuhan430074 China

We propose an online knowledge distillation method using a teacher-student model for nonlinear equalization in high-symbol-rate dense wavelength division multiplexing (DWDM) system spanning the S+C+L bands. The system features 195 WDM channels with 100 GHz spacing, transmitting 98 GBaud polarization division multiplexing (PDM) probability constellation shaping (PCS) 256-quadrature amplitude modulation (QAM) signals over 150 km of G.654.E standard single mode fiber (SSMF). Teacher models trained on five representative C-band channels are distilled to one or two lightweight student models on each of the C, S, L bands to achieve the whole triple-band equalization. This approach improves the system’s net data-rate from 201.5 Tb/s to 231.6 Tb/s, and reduces computational complexity by up to 97.1% in C band and 80% in S and L band. The results highlight that the student model can achieve comparable performance to teacher models with significantly reduced complexity. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Quadrature amplitude modulation

来源：评论

学校读者我要写书评

暂无评论

Secure Semantic communication With Homomorphic Encryption

arXiv

引用

arXiv 2025年

作者： Meng, Rui Fan, Dayu Gao, Haixiao Yuan, Yifan Wang, Bizhu Xu, Xiaodong Sun, Mengying Dong, Chen Tao, Xiaofeng Zhang, Ping Niyato, Dusit The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The Department of Broad-band Communication Peng Cheng Laboratory Guangdong Shenzhen518066 China The National Engineering Laboratory for Mobile Network Technologies Beijing University of Posts and Telecommunications Beijing100876 China Nanyang Technological University Singapore

In recent years, Semantic communication (SemCom), which aims to achieve efficient and reliable transmission of meaning between agents, has garnered significant attention from both academia and industry. To ensure the security of communication systems, encryption techniques are employed to safeguard confidentiality and integrity. However, traditional cryptography-based encryption algorithms encounter obstacles when applied to SemCom. Motivated by this, this paper explores the feasibility of applying homomorphic encryption to SemCom. Initially, we review the encryption algorithms utilized in mobile communication systems and analyze the challenges associated with their application to SemCom. Subsequently, we employ scale-invariant feature transform to demonstrate that semantic features can be preserved in homomorphic encrypted ciphertext. Based on this finding, we propose a task-oriented SemCom scheme secured through homomorphic encryption. We design the privacy preserved deep joint source-channel coding (JSCC) encoder and decoder, and the frequency of key updates can be adjusted according to service requirements without compromising transmission performance. Simulation results validate that, when compared to plaintext images, the proposed scheme can achieve almost the same classification accuracy performance when dealing with homomorphic ciphertext images. Furthermore, we provide potential future research directions for homomorphic encrypted SemCom. Copyright © 2025, The Authors. All rights reserved.

关键词： Channel coding

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：