检索结果-内蒙古大学图书馆

MMCSd:Multi-Modal Knowledge Graph Completion Based on Super-resolution and detailed description Generation

Computers, Materials & Continua 2025年第4期83卷 761-783页

作者： Huansha Wang ruiyang Huang Qinrang Liu Shaomei Li Jianpeng Zhang National Digital Switching System Engineering&Technological R&D Center Information Engineering UniversityZhengzhou450001China

Multi-modal knowledge graph completion(MMKGC)aims to complete missing entities or relations in multi-modal knowledge graphs,thereby discovering more previously unknown *** to the continuous growth of data and knowledge and the limitations of data sources,the visual knowledge within the knowledge graphs is generally of low quality,and some entities suffer from the issue of missing visual ***,previous studies of MMKGC have primarily focused on how to facilitate modality interaction and fusion while neglecting the problems of low modality quality and modality *** this case,mainstream MMKGC models only use pre-trained visual encoders to extract features and transfer the semantic information to the joint embeddings through modal fusion,which inevitably suffers from problems such as error propagation and increased *** address these problems,we propose a Multi-modal knowledge graph Completion model based on Super-resolution and detailed description Generation(MMCSd).Specifically,we leverage a pre-trained residual network to enhance the resolution and improve the quality of the visual ***,we design multi-level visual semantic extraction and entity description generation,thereby further extracting entity semantics from structural triples and visual ***,we train a variational multi-modal auto-encoder and utilize a pre-trained multi-modal language model to complement the missing visual *** conducted experiments on FB15K-237 and dB13K,and the results showed that MMCSd can effectively perform MMKGC and achieve state-of-the-art performance.

关键词： Multi-modal knowledge graph knowledge graph completion multi-modal fusion

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Named Entity recognition with Auxiliary Visual Knowledge and Word-Level Fusion

引用

Computers, Materials and Continua 2025年第3期83卷 5747-5760页

作者： Huansha Wang ruiyang Huang Qinrang Liu Xinghao Wang National Digital Switching System Engineering & Technological R&D Center Information Engineering University Zhengzhou 450001 China

Multi-modal Named Entity recognition (MNEr) aims to better identify meaningful textual entities by integrating information from images. Previous work has focused on extracting visual semantics at a fine-grained level, or obtaining entity related external knowledge from knowledge bases or Large Language Models (LLMs). However, these approaches ignore the poor semantic correlation between visual and textual modalities in MNEr datasets and do not explore different multi-modal fusion approaches. In this paper, we present MMAVK, a multi-modal named entity recognition model with auxiliary visual knowledge and word-level fusion, which aims to leverage the Multi-modal Large Language Model (MLLM) as an implicit knowledge base. It also extracts vision-based auxiliary knowledge from the image for more accurate and effective recognition. Specifically, we propose vision-based auxiliary knowledge generation, which guides the MLLM to extract external knowledge exclusively derived from images to aid entity recognition by designing target-specific prompts, thus avoiding redundant recognition and cognitive confusion caused by the simultaneous processing of image-text pairs. Furthermore, we employ a word-level multi-modal fusion mechanism to fuse the extracted external knowledge with each word-embedding embedded from the transformer-based encoder. Extensive experimental results demonstrate that MMAVK outperforms or equals the state-of-the-art methods on the two classical MNEr datasets, even when the large models employed have significantly fewer parameters than other baselines.

关键词： Multi-modal named entity recognition large language model multi-modal fusion

来源：评论

学校读者我要写书评

暂无评论

Network View and Cognitive Mechanism for Virtual Network resource Management Based Intelligent

引用

Chinese Journal of Electronics 2025年第3期23卷 574-578页

作者： Xiaochun Wu Chunming Wu Bin Wang Yaguan Qian Julong Lan Computer Science College Zhejiang University Hangzhou China Institute of Network and Communication Engineering Zhejiang Gongshang University Hangzhou China National Digital Switching System Engineering & Technology R&D Center Zhengzhou China

Network virtualization has been a particularly important driving force behind the development of NGN. Finding effective ways to control self-adapting virtual networks has become a research hot spot. This paper tries to find an efficient way in combining dynamic resource sensing with traffic character and requirements in virtual network, based on that an intelligent cognition based virtual network resources management model has been put forward. We design a network topology view by coloring network topology matrix with current resources model. We present an intelligent virtual resource management mechanism based on the proposed network topology view. Experiment results illustrate that the proposed mechanism can improve VN capacity by automatic resource adjust-ment, which can obtain high utilization of VN resources without increasing computational expenses.

关键词： Technological innovation Network topology Computational modeling Force dynamics Network resource management dynamic scheduling Sensors Virtualization Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Control, Modeling and Stability Analysis of drU-based Grid-forming Converter

引用

Chinese Journal of Electrical engineering 2025年第1期11卷 83-92页

作者： Wencong Wu Minzhi Wang Liang Tu Haiqing Cai Guanglei Yan Xiaohui Qu Haohan Gu Wei Chen State Key Laboratory of HVDC China Southern Power GridGuangzhou 510663China National Energy Power Grid Technology R&D Center Guangzhou 510663China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power Systems China Southern Power GridGuangzhou 510663China CSG Key Laboratory for Power System Simulation China Southern Power GridGuangzhou 510663China School of Electrical Engineering Southeast UniversityNanjing 210096China

diode rectifier unit(drU)-based high-voltage direct current(HVdC)transmissionsystems areeffectivein achieving the stableandeconomical operation of offshore *** theuncontrollable characteristicsof drUs,a grid-forming(GFM)strategy forwind-turbine converters isnecessary to support offshore AC voltageand ***,the active power-synchronization control in traditional GFM converters is unsuitable for drU-based GFM ***,the stability issue for drU-based HVdC systems involving drU-based GFM and grid-following(GFL)converters has not yet been *** solve these issues,this study begins with the characteristics of a drU-based HVdC system and presents a control scheme for drU-based GFM converters for power ***,the dq-frame impedance model of the drU-based GFM converteris proposed for the stability analysis of the entire HVdC ***,a simulation platform is built to verify the model accuracy and system stability.

关键词： diode rectifier unit offshore wind-powergeneration grid-forming converter impedance model stabilityanalysis

来源：评论

学校读者我要写书评

暂无评论

BCdAN: A balanced method for community detection in attributed networks

引用

Neurocomputing 2025年 644卷

作者： Liu, Yuchen Peng, Yabin Chen, Hongchang Zhang, Jianpeng Li, Shaomei Institute of Information Technology Information Engineering University Henan Zheng Zhou450002 China National Digital Switching System Engineering and Technological R&D Center Henan Zheng Zhou450002 China School of Cyber Science and Engineering Southeast University Jiangsu Nanjing211189 China

Community detection in attribute networks is a fundamental problem in complex network analysis, aiming to identify well-connected communities based on both topology and node attributes. Although numerous methods for community detection in attribute networks have been proposed, they often fail to balance the use of structural and attribute information. In these approaches, attribute information typically plays a dominant role, while higher-order structural information, such as motif structures, is often neglected. To address this issue, we propose a balanced method for community detection in attribute networks (BCdAN). First, for structural information, we construct structural vectors for each node and employ a structure autoencoder to learn the nodes’ structural embeddings. Concurrently, for attribute information, we use an attribute autoencoder and a graph convolution module to jointly learn the nodes’ attribute embeddings, linking the two types of neural networks via a delivery operator. Furthermore, we introduce a self-supervised module that integrates both structural and attribute information from the target distribution to guide iterative updates of the model, thereby facilitating the community detection task. This approach enables a balanced utilization of both attribute and structural information, improving the identification of community features in attribute networks. Extensive experimental results demonstrate that BCdAN outperforms most baseline algorithms. © 2025 Elsevier B.V.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Prioritized recovery Strategy For robust UAV Swarm Communication via Graph reinforcement Learning

引用

IEEE Internet of Things Journal 2025年

作者： Peng, Yabin Wu, Jiangxing duan, Tong Liu, Yuchen Zhang, Zhen Zhang, Jinfeng Southeast University School of Cyber Science and Engineering Nanjing211189 China Purple Mountain Laboratories Nanjing211111 China National Digital Switching System Engineering and Technological R and D Center Zhengzhou450002 China PLA Information Engineering University Zhengzhou450002 China

Network failures, whether due to random disruptions or malicious attacks, pose significant challenges for unmanned aerial vehicle (UAV) swarm networks. One critical concern is determining which failed UAVs to recover or replace under limited resource conditions to enhance the robustness of their communication networks. Current research primarily considers static structural characteristics of the network and struggles to uncover deep features that influence network robustness, and the efficiency cannot meet the real-time needs in UAV swarm scenarios. To address these issues, we introduce a Prioritized recovery strategy for failed nodes based on Graph reinforcement Learning (PrGrL). This approach integrates a random SAmpling neighbor method with a multi-head attention mechanism to create a novel Graph Convolutional Kernel (SAGCK). This kernel is designed to extract global structural information and relative positional information of nodes within the graph. Additionally, we develop a deep Policy Network (dPN) that explores the intricate relationships between graph-level and node embedding features, enabling the assessment of nodes’ impact on overall robustness. PrGrL’s network parameters are automatically updated and optimized using scalable deep reinforcement learning. Importantly, PrGrL prioritizes the recovery of boundary nodes within connected components to enhance network robustness further. Our experiments, conducted on both simulated and real-world networks, demonstrate that PrGrL outperforms existing methods of robustness enhancement across various recovery ratios, attack strategies, and network sizes while delivering superior real-time performance. © 2014 IEEE.

关键词： deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Thoughts on the development of novel network technology

引用

Science china(Information Sciences) 2018年第10期61卷 144-154页

作者： Jiangxing WU National Digital Switching System Engineering and Technological R&D Center

In this paper, we explore potential innovations that could lead to breakthrough developments in Internet technologies. The deep integration of the Internet and economic society brings professionalized service capacity demand, while existing Internet infrastructure with its current technological systems still face a number of challenges, such as intelligence, diversification, personalization, robustness, and ***, we analyze the actual foundation of innovation and specify the basic technical features of a novel network. Then, we propose a fully dimensionally definable open architecture as the primary direction, and consider reshaping baseline technologies as a starting point and discuss the core operational mechanisms of the novel network based on such reshaped baseline technologies.

关键词： novel Internet technology open architecture full-dimensional definability diversified addressing and routing intelligence general robust control

来源：评论

学校读者我要写书评

暂无评论

review on Security defense technology research in Edge Computing Environment

引用

Chinese Journal of Electronics 2024年第1期33卷 1-18页

作者： Ke SHANG Weizhen HE Shuai ZHANG National Digital Switching System Engineering and Technological R&D Center

Edge computing, which achieves quick data processing by sinking data computing and storage to the network edge, has grown rapidly along with the Internet of things. The new network architecture of edge computing brings new security challenges. Based on this, this paper investigates the edge computing security literature published in recent years and summarizes and analyzes research work on edge computing security from different attack surfaces. We start with the definition and architecture of edge computing. From the attack surface between device and edge server, as well as on edge servers, the research describes the security threats and defense methods of edge computing. In addition, the cause of the attack and the pros and cons of defense methods is introduced. The challenges and future research directions of edge computing are given.

关键词： Edge computing Security Threat defense Architecture Attack surface

来源：评论

学校读者我要写书评

暂无评论

Fast parallel algorithm for three-dimensional distance-driven model in iterative computed tomography reconstruction

引用

Chinese Physics B 2015年第2期24卷 513-520页

作者：陈建林李磊王林元蔡爱龙席晓琦张瀚铭李建新闫镔 National Digital Switching System Engineering & Technological R&D Center

The projection matrix model is used to describe the physical relationship between reconstructed object and *** a model has a strong influence on projection and backprojection,two vital operations in iterative computed tomographic *** distance-driven model（ddM） is a state-of-the-art technology that simulates forward and back *** model has a low computational complexity and a relatively high spatial resolution;however,it includes only a few methods in a parallel operation with a matched model *** study introduces a fast and parallelizable algorithm to improve the traditional ddM for computing the parallel projection and backprojection *** proposed model has been implemented on a GPU（graphic processing unit） platform and has achieved satisfactory computational efficiency with no *** runtime for the projection and backprojection operations with our model is approximately 4.5 s and 10.5 s per loop,respectively,with an image size of 256×256×256 and 360 projections with a size of 512×*** compare several general algorithms that have been proposed for maximizing GPU efficiency by using the unmatched projection/backprojection models in a parallel *** imaging resolution is not sacrificed and remains accurate during computed tomographic reconstruction.

关键词： computed tomography iterative reconstruction parallelizable algorithm distance-driven model

来源：评论

学校读者我要写书评

暂无评论

design and implementation of a novel enterprise network defense system by maneuvering multi-dimensional network properties

引用

Frontiers of Information technology & Electronic engineering 2019年第2期20卷 238-252页

作者： Yang CHEN Hong-chao HU Guo-zhen CHENG National Digital Switching System Engineering & Technological R&D Center

Although the perimeter security model works well enough when all internal hosts are credible, it is becoming increasingly difficult to enforce as companies adopt mobile and cloud technologies, i.e., the rise of bring your own device(BYOd). It is observed that advanced targeted cyber-attacks usually follow a cyber kill chain;for instance, advanced targeted attacks often rely on network scanning techniques to gather information about potential targets. In response to this attack method, we propose a novel approach, i.e., an "isolating and dynamic"cyber defense, which cuts these potential chains to reduce the cumulative availability of the gathered ***, we build a zero-trust network environment through network isolation, and then multiple network properties are maneuvered so that the host characteristics and locations needed to identify vulnerabilities cannot be ***, we propose a software-defined proactive cyber defense solution(SPd) for enterprise networks and design a general framework to strategically maneuver the IP address, network port, domain name, and path, while limiting the performance impact on the benign network user. Third, we implement our SPd proof-of-concept system over a software-defined network controller(Opendaylight). Finally, we build an experimental platform to verify the system's ability to prevent scanning, eavesdropping, and denial-of-service attacks. The results suggest that our system can significantly reduce the availability of network reconnaissance scan information, block network eavesdropping, and sharply increase the cost of cyber-attacks.

关键词： Intranet defense Software-defined network Multi-dimensional maneuvering

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：