检索结果-内蒙古大学图书馆

Enhancing Entity Relationship Extraction in Dialogue Texts Using Hypergraph and Heterogeneous Graph

Chinese Journal of Electronics 2025年第1期34卷 295-308页

作者： Shunmiao Zhang Siyuan Zheng Degen Huang Dan Li School of Computer Science and Mathematics Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology School of Computer Science and Technology Dalian University of Technology Elsevier

Dialogue-based relation extraction(DialogRE) aims to predict relationships between two entities in dialogue. Current approaches to dialogue relationship extraction grapple with long-distance entity relationships in dialogue data as well as complex entity relationships, such as a single entity with multiple types of connections. To address these issues, this paper presents a novel approach for dialogue relationship extraction termed the hypergraphs and heterogeneous graphs model(HG2G). This model introduces a two-tiered structure, comprising dialogue hypergraphs and dialogue heterogeneous graphs, to address the shortcomings of existing methods. The dialogue hypergraph establishes connections between similar nodes using hyper-edges and utilizes hypergraph convolution to capture multi-level features. Simultaneously, the dialogue heterogeneous graph connects nodes and edges of different types, employing heterogeneous graph convolution to aggregate cross-sentence information. Ultimately, the integrated nodes from both graphs capture the semantic nuances inherent in dialogue. Experimental results on the DialogRE dataset demonstrate that the HG2G model outperforms existing state-of-the-art methods.

关键词： Convolution Aggregates Semantics Feature extraction data mining

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Privacy Protection Model in Advanced Metering Infrastructure Based on Cloud and Fog Assistance

引用

Computers, Materials & Continua 2024年第8期80卷 3193-3219页

作者： Linghong Kuang Wenlong Shi Jing Zhang School of Computer Science and Mathematics Fujian University of TechnologyFuzhou350118China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118China

The Advanced Metering Infrastructure(AMI),as a crucial subsystem in the smart grid,is responsible for measuring user electricity consumption and plays a vital role in communication between providers and ***,with the advancement of information and communication technology,new security and privacy challenges have emerged for *** address these challenges and enhance the security and privacy of user data in the smart grid,a Hierarchical Privacy Protection Model in Advanced Metering Infrastructure based on Cloud and Fog Assistance(HPPM-AMICFA)is proposed in this *** proposed model integrates cloud and fog computing with hierarchical threshold encryption,offering a flexible and efficient privacy protection solution that significantly enhances data security in the smart *** methodology involves setting user protection levels by processing missing data and utilizing fuzzy comprehensive analysis to evaluate user importance,thereby assigning appropriate protection ***,a hierarchical threshold encryption algorithm is developed to provide differentiated protection strategies for fog nodes based on user IDs,ensuring secure aggregation and encryption of user *** results demonstrate that HPPM-AMICFA effectively resists various attack strategies while minimizing time costs,thereby safeguarding user data in the smart grid.

关键词： AMI cloud and fog assistance fuzzy comprehensive analysis hierarchical threshold encryption

来源：评论

学校读者我要写书评

暂无评论

An Optimal Node Localization in WSN Based on Siege Whale Optimization Algorithm

引用

Computer Modeling in Engineering & Sciences 2024年第3期138卷 2201-2237页

作者： Thi-Kien Dao Trong-The Nguyen Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of TechnologyFuzhou350118China Multimedia Communication Lab University of Information TechnologyHo Chi Minh CityVietnam

Localization or positioning scheme in Wireless sensor networks (WSNs) is one of the most challenging andfundamental operations in various monitoring or tracking applications because the network deploys a large areaand allocates the acquired location information to unknown devices. The metaheuristic approach is one of themost advantageous ways to deal with this challenging issue and overcome the disadvantages of the traditionalmethods that often suffer from computational time problems and small network deployment scale. This studyproposes an enhanced whale optimization algorithm that is an advanced metaheuristic algorithm based on thesiege mechanism (SWOA) for node localization inWSN. The objective function is modeled while communicatingon localized nodes, considering variables like delay, path loss, energy, and received signal strength. The localizationapproach also assigns the discovered location data to unidentified devices with the modeled objective functionby applying the SWOA algorithm. The experimental analysis is carried out to demonstrate the efficiency of thedesigned localization scheme in terms of various metrics, e.g., localization errors rate, converges rate, and executedtime. Compared experimental-result shows that theSWOA offers the applicability of the developed model forWSNto perform the localization scheme with excellent quality. Significantly, the error and convergence values achievedby the SWOA are less location error, faster in convergence and executed time than the others compared to at least areduced 1.5% to 4.7% error rate, and quicker by at least 4%and 2% in convergence and executed time, respectivelyfor the experimental scenarios.

关键词： Node localization whale optimization algorithm wireless sensor networks siege whale optimization algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

HFANet: Hierarchical Feature-Enhanced Aggregation Network for Camouflaged Object Detection

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-9页

作者： Zhang, Xinchao Zhu, Hengliang Mao, Guojun Department of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118 China

Camouflaged object detection (COD) aims to identify target objects in complex scenes with extremely high similarity to their surroundings, and has significant applications in military, medical, and other fields. This paper proposes a hierarchical feature-enhanced aggregation network (HFANet) for COD, aiming to address the situations that the target object is highly similar to the background. First, we adopt the pyramid vision Transformer model as the backbone for feature extraction. On top of it, the object-region amplification module and deep interaction guidance module are stacked to enhance the perception of camouflaged objects in complex scenes. Second, an enhanced receptive field module is designed to improve edge perception of camouflaged objects. At last, a multi-scale interactive fusion module is designed by cross-scale connection through adjacent layers, effectively improving the accuracy of COD. The proposed method is evaluated on three challenging datasets: CAMO, CHAMELEON, and COD10K. Evaluation results demonstrate superior performance compared to the state-of-the-art methods. © Shanghai Jiao Tong University 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

FHO-based Hybrid Neural Networks for Short-Term Load Forecasting in Economic Dispatch of Power Systems

Journal of Network Intelligence

引用

Journal of Network Intelligence 2025年第1期10卷 262-284页

作者： Wei, Yi Wang, Chia-Hung Suo, Yi-Fan Zhao, Qi-Gen Yuan, Jin-Chen Chen, Shu-Meng College of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China

With the development of the smart grid era, the data volume of the power system on the user side is growing rapidly, and the dependence of citizens on electricity is increasing significantly. In this paper, we aim to maximize the benefits of both supply and demand in the power system, from two aspects: improving the accuracy of short-term load forecasting and optimizing the economic dispatch of the power system. Firstly, based on the analysis of electricity consumption data, an improved load forecasting method via hybrid neural network is proposed. After determining the prediction results of the proposed model, we solved a short-term economic dispatch problem with the objective function of minimizing the generation cost of the power system and constraints such as unit start-up and shutdown, to achieve optimization of economic dispatch. In this work, an improved hybrid neural network with Firehawk Optimization (FHO) algorithm is developed to improve the accuracy of the prediction model by optimizing hyperparameters such as input data, number of hidden layer neurons, and batch size. In a series of numerical experiments, the proposed method is compared with other well-known optimization algorithms, such as Particle Swarm Optimization (PSO), Grey Wolf Optimiser (GWO) and Wild Horse Optimisation (WHO). From the comparison results, it shows that our method acheives better performance evaluation, and also improves the prediction accuracy of neural network models. Based on the load forecasting results, we determine the optimal scheduling scheme for the combination of power supply units, which minimizes the load and achieves higher applicability. © 2025, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： economic dispatch problem electric load forecasting electric power system firehawk optimization algorithm smart power grids supply and demand sides

来源：评论

学校读者我要写书评

暂无评论

A Novel Action Recognition Method Based on Attention Enhancement and Relative Entropy 1

引用

2nd International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2022

作者： Liu, Xing-Sheng Liu, Shi-Jian Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fujian Fuzhou350118 China

ISBN: (数字)9789819945542

ISBN: (纸本)9789819945535

Action recognition is a hotspot field in computer vision for video understanding. To achieve accurate and real-time action recognition, a novel skeleton-based method combined with attention enhancement and relative entropy is proposed. Firstly, the data normalization method is presented to reduce the recognition error caused by human body posture and scale differences. Secondly, a joint attention strategy is proposed considering the different contributions of joints in an action. Finally, a relative entropy based acceleration strategy is employed to avoid unnecessary matching and save time. Experiments carried out on the Microsoft Research Cambridge-12 dataset show that the accuracy of our method is 90.32% and the time cost is 31.58 ms on average, which outperforms the others. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

A RECEPTIVE ENHANCED BASED MULTI-SCALE FEATURE FUSION NETWORK 18

A RECEPTIVE ENHANCED BASED MULTI-SCALE FEATURE FUSION NETWOR...

引用

18th International Conference on Interfaces and Human Computer Interaction 2024, IHCI 2024, the 17th International Conference on Game and Entertainment Technologies 2024, GET 2024 and the 18th International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing 2024, CGVCVIP 2024, Part of the 18th Multi Conference on Computer Science and Information Systems 2024, MCCSIS 2024

作者： Mao, Guojun Zhang, Xinchao Fujian Provincial Key Lab of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China

ISBN: (纸本)9789898704580

Camouflaged Object Detection (COD) aims to identify target objects with high similarity to the surrounding environment in complex scenes, and has high application value in military, medical and other fields. This paper proposes a Receptive enhanced based Multi-scale feature fusion network, termed as RMNet. Firstly, it uses the popular pyramid visual network PVTv2 for feature extraction. By overlaying the target area amplification module OAA and deep interaction guidance module DIDM on it, the position ability for camouflaged objects in complex scenes is improved;Secondly, design an enhanced receptive field module REM to enhance the edge perception ability of camouflaged objects;Finally, the feature fusion module MCFM are designed through cross scale hierarchical connections between adjacent levels, effectively improving the accuracy of camouflage object detection. The presented model is evaluated on three highly challenging benchmark datasets, including CAMO, CHAMELEON and COD10K. The evaluation results show that compared with the current popular methods, our method demonstrates superior performance. © 2024 Interfaces and Human Computer Interaction. All Rights Reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Compact Multitasking Multichromosome Genetic Algorithm for Heuristic Selection in Ontology Matching

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6752-6766页

作者： Xue, Xingsi Lin, Jerry Chun-Wei Su, Tong Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian Fuzhou350118 China Silesian University of Technology Department of Distributed Systems and IT Devices Akademicka Gliwice44-100 Poland Fujian University of Technology School of Computer Science and Mathematics Fujian Fuzhou350118 China

Ontology matching (OM) is critical for knowledge integration and system interoperability on the semantic web, tasked with identifying semantically related entities across different ontologies. Despite its importance, the complexity of terminology semantics and the large number of potential matches present significant challenges. Existing methods often struggle to balance between accurately capturing the multifaceted nature of semantic relationships and computational efficiency. This work introduces a novel approach, a compact multitasking multichromosome genetic algorithm for Heuristic selection (HS) in OM, designed to navigate the nuanced hierarchical structure of ontologies and diverse entity mapping preferences. Our method combines compact genetic algorithms with multichromosome optimization for entity sequencing and assigning HS, alongside an adaptive knowledge transfer mechanism to finely balance exploration and exploitation efforts. Evaluated on the ontology alignment evaluation initiative's benchmark, our algorithm demonstrates superior ability to produce high-quality ontology alignments efficiently, surpassing comparative methods in both effectiveness and efficiency. These findings underscore the potential of advanced genetic algorithms in enhancing OM processes, offering significant contributions to the broader AI field by improving the interoperability and knowledge integration capabilities of semantic web technologies. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A new network intrusion detection system based on auto-encoding and variance analysis 5

A new network intrusion detection system based on auto-encod...

引用

5th IEEE International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2023

作者： Chen, Dequ Zhang, Ming Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian Fuzhou China

ISBN: (纸本)9798350310603

In today's big data era, ensuring the network security of information technology (IT) communication facilities is one of the most challenging issues. In fact, with progress in technology, hackers have developed increasingly complex and risky network attacks, making malicious access identification a very tired task. Under various threats, the existing analysis methods encounter many challenges in detecting and mitigating these illegal accesses. This work presents a new network intrusion detection system (IDS) which combines deep learning method and mathematical strategy. Indeed, our IDS makes full use of data analysis, mathematical modeling, and deep learning to select and optimize features that are more relevant for classification. We use NSL-KDD dataset to test the performance of the IDS. The experimental results show that our proposed method has better performance compared with traditional deep learning, machine learning and recently proposed advanced methods. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

A Multi-Objective Particle Swarm Optimization Algorithm Based on Decomposition and Multi-Selection Strategy

引用

Computers, Materials & Continua 2025年第1期82卷 997-1026页

作者： Li Ma Cai Dai Xingsi Xue Cheng Peng School of Computer Science Shaanxi Normal UniversityXi’an710119China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of TechnologyFuzhou350118China Information Construction and Management Center and Institute of Artificial Intelligence and Educational New Productivity Ningxia Normal UniversityGuyuan756099China

The multi-objective particle swarm optimization algorithm(MOPSO)is widely used to solve multi-objective optimization *** the article,amulti-objective particle swarm optimization algorithmbased on decomposition and multi-selection strategy is proposed to improve the search ***,two update strategies based on decomposition are used to update the evolving population and external archive,***,a multiselection strategy is *** first strategy is for the subspace without a non-dominated *** the neighbor particles,the particle with the smallest penalty-based boundary intersection value is selected as the global optimal solution and the particle far away fromthe search particle and the global optimal solution is selected as the personal optimal solution to enhance global *** second strategy is for the subspace with a non-dominated *** the neighbor particles,two particles are randomly selected,one as the global optimal solution and the other as the personal optimal solution,to enhance local *** third strategy is for Pareto optimal front(PF)discontinuity,which is identified by the cumulative number of iterations of the subspace without non-dominated *** the subsequent iteration,a new probability distribution is used to select from the remaining subspaces to ***,an adaptive inertia weight update strategy based on the dominated degree is designed to further improve the search ***,the proposed algorithmis compared with fivemulti-objective particle swarm optimization algorithms and five multi-objective evolutionary algorithms on 22 test *** results show that the proposed algorithm has better performance.

关键词： Multi-objective optimization multi-objective particle swarm optimization decomposition multi-selection strategy

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：