检索结果-内蒙古大学图书馆

Enhancing graph representation learning via type-aware decoupling and node influence allocation

Applied Intelligence 2025年第6期55卷 1-14页

作者： Zhu, Guochang Hu, Jun Liu, Li Zhang, Qinghua Wang, Guoyin School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongwen Road Chongqing Chongqing400065 China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongwen Road Chongqing Chongqing400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing400065 China

The traditional graph representation methods can fit the information of graph with low-dimensional vectors, but they cannot interpret their composition, resulting in insufficient security. Graph decoupling, as a method of graph representation, can analyze the latent factors composing the graph representation vectors. However, in current graph decoupling methods, the number of factors is a hyperparameter, and enforce uniform decoupling vector dimensions which leads to information loss or redundancy. To address these issues, we propose a type-aware graph decoupling based on influence called Variational Graph Decoupling Auto-Encoder (VGDAE). It uses node labels as interpretable and objectively existing natural semantics for decoupling and allocates embedding space based on node influence, addressing the issues of manually setting the number of factors in traditional graph decoupling and the mismatch between node information size and embedding space. On the Cora, Citeseer, and fb-CMU datasets, VGDAE shows the impact of different node classes as decoupling targets on classification tasks. Furthermore, we perform visualization of the representations, VGDAE exhibits performance improvements of 2% in classification tasks and 12% in clustering tasks when compared with baseline models. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Multi-FDMF: An Agile Management Framework of Multi-domain data in Decentralized Heterogeneous Environments 9

Multi-FDMF: An Agile Management Framework of Multi-domain Da...

引用

9th International Conference on big data and Information Analytics, bigDIA 2023

作者： Ge, Ningchao Chen, Haiwen Wu, Jibing Hu, Ying National University of Defense Technology Laboratory for Big Data and Decision Changsha China Criminal Investigation Section Public Security Department Changsha China

ISBN: (纸本)9798350330076

With the in-depth development of big data and artificial intelligence technology, traditional financial, transportation, manufacturing, military and other industries are gradually developing in the direction of digitalization, intelligence and diversification of service scenarios. The transformation of data level is from single-domain data demand to multi-domain data demand. However, the traditional single-domain data management methods are difficult to meet the needs of large-scale multi-domain data management. Aiming at the characteristics of independent autonomy, complex structure and difficult aggregation that are common in distributed heterogeneous environments. This paper puts forward a multi-domain data agile management framework: multi-federated distributed management framework (Multi-FDMF). Based on the idea of "star atom structure"and "federal management institution", the framework realizes the internal federal management of all kinds of data in the field by constructing a local distributed federal system in each "atom"layer. Some "atoms"are linked to the "molecular"center through data channels to form a multi-domain "molecular"external federated system. Finally, multi-federated distributed management of multi-domain data is realized through multiple links at the "molecular"level and above. © 2023 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Study on IGBT Based on Multi-physical Field Model

Study on IGBT Based on Multi-physical Field Model

引用

2024 International Conference on New Power System and Power Electronics, NPSPE 2024

作者： Li, Jie Du, Liping Chongqing College of Mobile Communication Chongqing China Chongqing Key Laboratory of Public Big Date Security Technology Chongqing China Chongqing Vocational College of Public Transportation Chongqing China

ISBN: (纸本)9798350389869

With the proposal and implementation of "carbon peak"and "carbon neutral"policies, the vigorous development of new energy vehicles, wind energy, photovoltaic, energy storage, the core components IGBT devices play a vital role in energy conversion and electric energy control, so the reliability and safety of Insulated Gate Bipolar Transistor (IGBT) work is particularly important. How to effectively carry out IGBT accelerated aging test problem is the basis of studying its reliability. Based on this, in this paper, a multi-physical field coupling model is established according to the structure of IGBT, and the temperature distribution inside IGBT is analyzed, showing that the chip solder layer is a weak point. Secondly, based on the electric-thermal coupling model, this paper analyzes the sensitivity of the external characteristic parameters of power electronic devices under different control strategies, and obtains the optimal accelerated aging test scheme with the control strategy of constant shell temperature difference. Finally, the effectiveness of the control strategy is proved by analyzing the change trend of characteristic parameters in the aging process of IGBT, which lays a theoretical foundation for the reliability research of IGBT. © 2024 IEEE.

关键词： Insulated gate bipolar transistors (IGBT)

来源：评论

学校读者我要写书评

暂无评论

A Learnable Graph Convolutional Neural Network Model for Relation Extraction 1

引用

28th China Conference on Information Retrieval, CCIR 2022

作者： Xu, Jinling Chen, Yanping Qin, Yongbin Huang, Ruizhang State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

ISBN: (数字)9783031247552

ISBN: (纸本)9783031247545

Relation extraction is the task of extracting the semantic relationships between two named entities in a sentence. The task relies on semantic dependencies relevant to named entities. Recently, graph convolutional neural networks have shown great potential in supporting this task, wherein dependency trees are usually adopted to learn semantic dependencies between entities. However, the requirement of external toolkits to parse sentences poses a problem, owing to them being error prone. Furthermore, entity relations and parsing structures vary in semantic expressions. Therefore, manually designed rules are required to prune the structure of the dependency trees. This study proposed a novel learnable graph convolutional neural network model (L-GCN) that directly encodes every word of a sentence as nodes of a graph neural network. Then, the L-GCN uses a learnable adjacency matrix to encode dependencies between nodes. The model offers the advantage of automatically learning high-order abstract representations of the semantic dependencies between words. Moreover, a fusion module was designed to aggregate the global and local semantic structure information of sentences. Further, the proposed L-GCN was evaluated on the ACE 2005 English dataset and Chinese Literature Text Corpus. The experimental results confirmed the effectiveness of L-GCN in learning the semantic dependencies of a relation instance. Moreover, it clearly outperformed previous dependency-tree-based models. © 2023, Springer Nature Switzerland AG.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Access Control Proxy Re-encryption with HRA security from Lattice 18th

Fine-Grained Access Control Proxy Re-encryption with HRA Se...

引用

18th International Conference on Green, Pervasive, and Cloud Computing, GPC 2023

作者： Hou, Jinqiu Peng, Changgen Tan, Weijie Zhong, Chongyi Niu, Kun Li, Hu State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China Key Laboratory of Advanced Manufacturing Technology Ministry of Education Guizhou University Guiyang550025 China School of Mathematics and Big data Guizhou Education University Guiyang550025 China

ISBN: (纸本)9789819998951

With the gradual formation of the cloud computing ecosystem, the value of cloud computing is becoming increasingly evident, and the accompanying information security issues have become core elements. The challenge lies in securely transmitting, computing, and sharing data in a cloud computing environment while keeping privacy. In this paper, we propose an access control proxy re-encryption scheme that supports inner product operations based on lattices in the standard model. First, the ciphertext is linked to the attributes, and condition for transition is associated with the re-encryption key. The proxy may re-encrypt ciphertext that meets attribute conditions instead of all ciphertext, thereby limiting the proxy’s conversion permissions. Furthermore, the user outputs the inner product value after decryption. Finally, honestly re-encryption attacks (HRA) security with increased CPA security is employed to better capture the target of proxy re-encryption. In addition, we propose a new method of hiding access policy, which uses differential privacy technology to perturb the attribute values to better safeguard the privacy of users. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Dense Pedestrian Detection Algorithm Based on Multiscale Feature Fusion in YOLOv8 5

Dense Pedestrian Detection Algorithm Based on Multiscale Fea...

引用

5th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2024

作者： Hu, Weichao Hu, Qian Pi, Jianyong Huang, Kun Li, Wenhua Wang, Juanmin Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China Guizhou Mobile Information Technology Company Guiyang China

ISBN: (纸本)9798350373820

The pedestrian target in large-scale crowded places has the characteristics of complex environment, diverse scales and dense arrangement, which makes the current target detection methods appear the phenomenon of false detection and missed detection when dense pedestrians. In order to solve this problem, based on YOLOv8, a dense pedestrian detection algorithm based on multi-scale feature fusion was proposed. Firstly, in view of the limitation of the performance of standard convolutional convolution due to the defect of convolutional kernel parameter sharing, RFCAConv was introduced into the backbone network. The convolution module can effectively improve the performance of convolution operation, so as to improve the feature extraction ability of the backbone network and fully extract the feature information at all levels. Secondly, a 160 × 160 scale small target detection head was added to improve the model's detection ability of small-scale targets. Finally, based on the ASFF design ASFF-4P module, QAFPN is proposed to fully integrate the feature information of four feature layers with different feature scales, effectively avoid the loss and degradation of information, reduce the distance of non-adjacent layer semantic information, and improve the detection accuracy and efficiency of the model for targets at different scales. Experimental results show that compared with YOLOv8n, the proposed method improves AP50% and AP50:95% by 3.7% and 4. 2% respectively on the CrowdHuman datasets, and is also highly competitive compared with other advanced pedestrian detection models. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Flame Detection Algorithm Based on Improved YOLOv8 5

Flame Detection Algorithm Based on Improved YOLOv8

引用

5th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2024

作者： Huang, Kun Hu, Qian Pi, Jianyong Hu, Weichao Li, Wenhua Wang, Juanmin Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China Guizhou Mobile Information Technology Company Guiyang China

ISBN: (纸本)9798350373820

Flame detection is a key technology in intelligent firefighting, using object detection methods to locate and count flames in videos, thereby enabling intelligent monitoring of fire incidents. This has significant research value in areas such as public safety and community intelligent governance. In complex scenes, due to the complicated backgrounds of flame targets, non-uniform sizes and shapes, and sensitivity to lighting, there's a tendency for missed detections. This paper proposes an improved flame detection algorithm based on YOLOv8, named Fire-YOLOv8, addressing these issues. Firstly, a Tri-RepVGG module is introduced into the backbone network for better flame feature extraction without increasing computational costs, ensuring the timeliness of detection. Secondly, in the neck part of the YOLOv8 network, a Progressive Feature Pyramid Network (AFPN) structure is introduced to enhance the fusion of information between layers, solving the issues of information loss and degradation present in YOLOv8 feature fusion. Finally, based on the SE channel attention mechanism, an SE-Detect detection head is proposed to effectively mitigate the issues of flame detection sensitivity to lighting. Experimental results show that Fire-YOLOv8 achieves 74.5% mAP50 and 47.9% mAP50-95 on a self-made flame dataset Multi-Fire, representing improvements of 4.4% and 3.3% respectively over the original YOLOv8n, demonstrating strong competitive capabilities. © 2024 IEEE.

关键词： Lighting

来源：评论

学校读者我要写书评

暂无评论

An insider user authentication method based on improved temporal convolutional network

引用

High-Confidence Computing 2023年第4期3卷 87-95页

作者： Xiaoling Tao Yuelin Yu Lianyou Fu Jianxiang Liu Yunhao Zhang Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic TechnologyGuilin 541004China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic TechnologyGuilin 541004China

With the rapid development of information technology,information system security and insider threat detection have become important topics for organizational *** the current network environment,user behavioral bio-data presents the characteristics of nonlinearity and temporal *** of the existing research on authentication based on user behavioral biometrics adopts the method of manual feature *** do not adequately capture the nonlinear and time-sequential dependencies of behavioral bio-data,and also do not adequately reflect the personalized usage characteristics of users,leading to bottlenecks in the performance of the authentication *** order to solve the above problems,this paper proposes a Temporal Convolutional Network method based on an Efficient Channel Attention mechanism(ECA-TCN)to extract user mouse dynamics features and constructs an one-class Support Vector Machine(OCSVM)for each user for *** results show that compared with four existing deep learning algorithms,the method retains more adequate key information and improves the classification performance of the neural *** the final authentication,the Area Under the Curve(AUC)can reach 96%.

关键词： Insider users Mouse dynamics Feature extraction Temporal convolutional network Efficient channel attention mechanism Authentication

来源：评论

学校读者我要写书评

暂无评论

YOLOv5 Algorithm Optimization: Precise Target Detection Amidst Background Interference 4

YOLOv5 Algorithm Optimization: Precise Target Detection Amid...

引用

4th International Conference on Consumer Electronics and Computer Engineering, ICCECE 2024

作者： Xiong, Bingbing Shi, Wenxi Fu, Yanyun Zhu, Zhansheng Wang, Deyong Jia, Bin School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Lianhaichuangzhi Information Technology Co. Ltd. Key Laboratory of Big Data of Xinjiang Social Security Risk Beijing China Beijing Academy of Science and Technology Beijing China Xinjiang Lianhaichuangzhi Information Technology Co. Ltd. Key Laboratory of Big Data of Xinjiang Social Security Risk Urumqi China

ISBN: (纸本)9798350384062

This paper solves the challenge that the target is submerged in the background in the border security scenario, and proposes the enhancement of YOLOv5 algorithm. EfficientViT replaces the DarkNet backbone, leveraging Transformer models for improved feature extraction. Modifications to the Spatial Pyramid Pooling-Fast (SPPF) module enhance the algorithm's robustness to scale variations. Introducing SCYLLA-IoU (SIoU) in the loss function improves model convergence speed and accuracy. Validated on a custom border security dataset, the enhancements show an improved average precision mean (mAP) of 48.3%, a 2.2 percentage point increase over the original YOLOv5s model. © 2024 IEEE.

关键词： Border security Target Detection Transformer YOLOv5

来源：评论

学校读者我要写书评

暂无评论

Detecting the One-Shot Dummy Attack on the Power Industrial Control Processes With an Unsupervised data-Driven Approach

引用

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 550-553页

作者： Zhenyong Zhang Yan Qin Jingpei Wang Hui Li Ruilong Deng the State Key Laboratory of Public Big Data and the College of Computer Science and Technology Guizhou UniversityGuiyang 550025China the School of Chemical and Biomedical Engineering Nanyang Technological UniversitySingapore 639798Singapore the State Key Laboratory of Industrial Control Technology and the College of Control Science and Engineering Zhejiang UniversityHangzhou 310027China IEEE

Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this letter, targeting a more practical case, we aim to detect the oneshot DA, with the purpose of revealing the DA once it is ***, we first formulate an optimization problem to generate one-shot DAs. Then, an unsupervised data-driven approach based on a modified local outlier factor(MLOF) is proposed to detect them.

关键词： Dummy Power letter

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：