检索结果-内蒙古大学图书馆

12th IEEE International Conference on computer Science and Network Technology, ICCSNT 2024

作者： Zhao, Ruoyu Wang, Tingdong Ma, Yinglong North China Electric Power University School of Control and Computer Engineering Beijing102206 China

ISBN: (纸本)9798350350791

Querying power big data across multiple sections plays an important role in achieving efficient power data sharing and emergent accident handling. However, power big data often suffers from the issues of data sparsity and low query efficiency. In this paper, we propose a power big data query acceleration method based on binary partitioning and workload-driven pre-joins (BP-WPJ). First, the original power property tables can be vertically partitioned into multiple binary tables (BTs) for eliminating null-value elements, producing the statistics of data type frequency in BTs. Second, a workload-driven pre-join processing method (WPJ) is proposed to identify the join patterns of the query statement in terms of predicates and join relations. Third, we optimize the order of query triples by dividing the query statement into multiple query triples based on the bounded elements for accelerating power data query. Experiments were made on three datasets compared to three popular methods, and the results show that BP-WPJ is very competitive against the three baselines. It can significantly accelerate big data query and achieves relatively lower memory consumption, thereby meeting the practical needs of power big data queries. © 2024 IEEE.

关键词： Binary Partitioning Electric Power Big Data Unbound Predicate Queries Workload-Driven Pre-join

来源：评论

学校读者我要写书评

暂无评论

Multi-step Image Enhancement for Incinerator Flame Recognition 43

Multi-step Image Enhancement for Incinerator Flame Recogniti...

引用

43rd Chinese control Conference, CCC 2024

作者： Ye, Lu Zheng, Zhao Ziyu, Zhou Haojie, Wang Dongzhuo, Zhao North China Electric Power University School of Control and Computer Engineering Baoding071003 China

ISBN: (纸本)9789887581581

In order to address the issue of low segmentation accuracy in the weak flame region of waste incineration flame images and the potential loss of texture details at the flame edge, this study proposes an algorithm for segmenting incinerator flame images based on multi-step image enhancement. The algorithm consists of several steps. Firstly, a single-scale Retinex algorithm is employed to enhance the details of the noise-reduced image. Subsequently, an adaptive gamma correction method based on the inverse color transform is proposed to enhance the contrast between the image foreground and background, in conjunction with the inverse color transform algorithm. Finally, a 2D-Otsu algorithm is utilized to segment the image and extract the target flame region. Experimental results demonstrate that the proposed incinerator flame image segmentation algorithm based on multi-step image enhancement achieves superior segmentation performance, effectively preserving more detailed information in the weak flame region. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Premixed flames

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Polynomial Positive Fuzzy System controllers Based on Markov Transitions

Design and Analysis of Polynomial Positive Fuzzy System Cont...

引用

2024 China Automation Congress, CAC 2024

作者： Chang, Sen Li, Xiaomiao Liu, Fucai Bao, Zhiyong Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao China

ISBN: (纸本)9798350368604

This study explores polynomial Markov positive fuzzy systems, formulating controllers for these systems by examining the prerequisites for positivity and stochastic stability. Initially, polynomials are incorporated into the Markov positive fuzzy system to represent nonlinear elements better and enhance its capacity to model nonlinear systems. Concurrently, the study discusses the non-convex scenarios encountered in the stability analysis of the closed-loop system once the positive fuzzy system controller is integrated and confirms the stability of the Markov polynomial positive fuzzy system. Ultimately, the effectiveness of the proposed approaches is demonstrated through a numerical simulation example. © 2024 IEEE.

关键词： Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Optimal Strategies to Contain Arboviruses Spread

引用

SN computer Science 2025年第5期6卷 1-13页

作者： Di Giamberardino, Paolo Iacoviello, Daniela Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Via Ariosto 25 Rome 00185 Italy

Globalization, the increase of human travelling and climate changes contribute to the emergency due to arboviruses diffusion. Generally, the infected patients show only mild symptoms, but in some cases, with fragile subjects, this kind of disease can be fatal. In this paper Dengue virus is considered and described by means of a new compartmental model in which the human and the mosquitos populations interact and can infect each other;containment measures, based both on human habits and on the reduction of mosquitoes in different phase of their lives, are determined in the framework of optimal control theory, aiming at decreasing the number of infected patients and limiting the actions to be applied. This latter aspect is particularly important, both for practical and economical aspects, and for ecological reasons, since a too strong actions against mosquitos can be dangerous for the equilibrium of the ecosystem. © The Author(s) 2025.

关键词： Containment strategies Dengue virus Epidemic control Optimal control

来源：评论

学校读者我要写书评

暂无评论

A DDoS Identification Method for Unbalanced Data CVWGG

引用

computers, Materials & Continua 2024年第12期81卷 3825-3851页

作者： Haizhen Wang Na Jia Yang He Pan Tan College of Computer and Control Engineering Qiqihar UniversityQiqihar161006China Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar UniversityQiqihar161006China

As the popularity and dependence on the Internet increase,DDoS(distributed denial of service)attacks seriously threaten network *** accurately distinguishing between different types of DDoS attacks,targeted defense strategies can be formulated,significantly improving network protection *** attacks usually manifest as an abnormal increase in network traffic,and their diverse types of attacks,along with a severe data imbalance,make it difficult for traditional classification methods to effectively identify a small number of attack *** solve this problem,this paper proposes a DDoS recognition method CVWGG(Conditional Variational Autoencoder-Wasserstein Generative Adversarial Network-gradient penalty-Gated Recurrent Unit)for unbalanced data,which generates less noisy data and high data quality compared with existing *** mainly includes unbalanced data processing for CVWG,feature extraction,and *** uses the CVAE(Conditional Variational Autoencoder)to improve the WGAN(Wasserstein Generative Adversarial Network)and introduces a GP(gradient penalty)term to design the loss function to generate balanced data,which enhances the learning ability and stability of the ***,the GRU(Gated Recurrent Units)are used to capture the temporal features and patterns of the ***,the logsoftmax function is used to differentiate DDoS attack *** PyCharm and Python 3.10 for programming and evaluating performance with metrics such as accuracy and precision,the results show that the method achieved accuracy rates of 96.0%and 97.3%on two datasets,***,comparison and ablation experiment results demonstrate that CVWGG effectively mitigates the imbalance between DDoS attack categories,significantly improves the classification accuracy of different types of attacks and provides a valuable reference for network security defense.

关键词： Conditional variational autoencoder generating adversarial networks DDoS attack

来源：评论

学校读者我要写书评

暂无评论

Recommendation System Based on Perceptron and Graph Convolution Network

引用

computers, Materials & Continua 2024年第6期79卷 3939-3954页

作者： Zuozheng Lian Yongchao Yin Haizhen Wang College of Computer and Control Engineering Qiqihar UniversityQiqihar161006China Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar UniversityQiqihar161006China

The relationship between users and items,which cannot be recovered by traditional techniques,can be extracted by the recommendation algorithm based on the graph convolution *** current simple linear combination of these algorithms may not be sufficient to extract the complex structure of user interaction *** paper presents a new approach to address such issues,utilizing the graph convolution network to extract association *** proposed approach mainly includes three modules:Embedding layer,forward propagation layer,and score prediction *** embedding layer models users and items according to their interaction information and generates initial feature vectors as input for the forward propagation *** forward propagation layer designs two parallel graph convolution networks with self-connections,which extract higher-order association relevance from users and items separately by multi-layer graph ***,the forward propagation layer integrates the attention factor to assign different weights among the hop neighbors of the graph convolution network fusion,capturing more comprehensive association relevance between users and items as input for the score prediction *** score prediction layer introduces MLP(multi-layer perceptron)to conduct non-linear feature interaction between users and items,***,the prediction score of users to items is *** recall rate and normalized discounted cumulative gain were used as evaluation *** proposed approach effectively integrates higher-order information in user entries,and experimental analysis demonstrates its superiority over the existing algorithms.

关键词： Recommendation system graph convolution network attention mechanism multi-layer perceptron

来源：评论

学校读者我要写书评

暂无评论

DDoS Attack Detection in Smart Grid Networks Using Visual Features 2

DDoS Attack Detection in Smart Grid Networks Using Visual Fe...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Ali Naqvi, Sardar Shan Li, Yuancheng Uzair, Muhammad School Of Control And Computer Engineering North China Electric Power University Beijing102206 China Comsats University Islamabad Department Of Computer Engineering Wah cantt Pakistan

ISBN: (纸本)9798350394962

Smart grid networks play a key role in making electric power infrastructure more efficient and ensuring reliable energy distribution. However, the interconnected communication devices in these networks expose the system to several network threats, such as the distributed denial of service (DDoS) attacks. Timely DDoS attack detection and mitigation is an important but challenging task for maintaining service integrity. In this paper, we propose to leverage computer vision models to detect DDoS attacks in smart grid networks. After preprocessing the input network data and extracting features, we transform the features into two-dimensional images, employing them to train and fine-tune a vision MLP mixer model. Our approach offers the advantage of adaptability, as any pre-existing computer vision model can be utilized for fine-tuning purposes, providing flexibility in the absence of readily available pretrained models in the DDoS detection domain. Performance metrics, including accuracy, precision, recall, and F1 score obtained from our experiments, show promising results for DDoS attack detection in smart grid networks using the UNB-ISCX-IDS dataset, which contains real-world network traffic data containing different attack scenarios. Our approach will be beneficial for robust and secure smart grid operation in real-world scenarios. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

GraphSA: Smart Contract Vulnerability Detection Combining Graph Neural Networks and Static Analysis 26

GraphSA: Smart Contract Vulnerability Detection Combining Gr...

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： He, Long Zhao, Xiangfu Wang, Yichen Yang, Jiahui Sun, Xuelei School of Computer and Control Engineering Yantai University Yantai264005 China

ISBN: (纸本)9781643684369

Security incidents in smart contracts still occur frequently, as the underlying code is often vulnerable to attacks. However, traditional methods to detect vulnerabilities in smart contracts are limited by certain rigid rules, reducing accuracy and scalability. In this work, we propose GraphSA, which combines Graph neural networks (GNNs) and Static Analysis for smart contract vulnerability detection. First, we present the contract tree, which is obtained by converting the control flow graph (CFG) of a smart contract. Each node in the tree represents a crucial operation code (opcode) block, and each edge represents the control flow (execution order) between code blocks. Then, we propose an extended SAGConv and Topkpooling graph neural network (ST-GNN) to learn the features of each node in the tree. To enhance detection accuracy, we eliminate and merge some non-crucial nodes to highlight key nodes and execution orders. Finally, we evaluate our approach on 7,962 real-world smart contracts running on Ethereum and compare it with state-of-the-art approaches on six types of vulnerabilities. Experimental results show that our approach achieves higher detection accuracy than others. © 2023 The Authors.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Proactive Perception of Preferences Evolution Based on Graph Neural Networks 16th

Proactive Perception of Preferences Evolution Based on Gra...

引用

16th International Conference on Service Science, ICSS 2023

作者： Pang, Lixin Liu, Zhizhong Meng, Lingqiang Li, Linxia Song, Xiaoyu School of Computer and Control Engineering Yantai University Yantai264005 China

ISBN: (纸本)9789819944019

User preferences play an important role in intelligent services, smart recommendations, and so on. Unfortunately, user preferences are dynamic and always evolving. How to proactively perceive users’ preferences evolution has become a critical issue. Recently, some wonderful research results about preference learning or preference prediction has been achieved. However, existing works can only perceive the change of preferences implicitly, cannot present users’ preferences change explicitly. To tackle this issue, we propose an approach for proactive perception of preferences evolution based on graph neural networks (PPGNN). Firstly, PPGNN constructs a directed sequence graph based on the user’s historical item interaction sequence, and learns the embedded vector representation of nodes in the directed sequence graph with the gated graph neural network (GGNN). Secondly, PPGNN learns the complex correlation between users and items in the interaction sequence using attention networks to obtain users’ long-term preferences. Meanwhile, PPGNN uses the location-aware network to preserve the location information in the sequence, and extracts user’s short-term preferences from the sequence with the attention network. Thirdly, PPGNN combines the user’s long-term and short-term preferences through a gated-fusion network and recommends an item that the user is most interested in. Finally, PPGNN perceives the evolution of user preferences by comparing the recommended items with the items that the user was previously interested in. Extensive experiments have been conducted to validate the proposed method and demonstrate its effectiveness. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Weighted Slope One Collaborative Filtering Algorithm for Improved User Relevance

A Weighted Slope One Collaborative Filtering Algorithm for I...

引用

2023 International Conference on Artificial Intelligence and Automation control, AIAC 2023

作者： Li, Ruizhi Liu, Qicheng Yantai University School of Computer and Control Engineering Yantai264005 China

ISBN: (纸本)9798350383805

Considering the low accuracy of recommendation results of current collaborative filtering algorithms caused by data sparsity, this paper proposes a weighted Slope One collaborative filtering algorithm for improved user relevance (WSOCF-IUR). The proposed algorithm takes into account the influence of the number of different user comments and the number of common rating items on recommendation accuracy. In addition, by incorporating user activity and improving the Pearson correlation coefficient, the algorithm reduces the influence of interfering data on recommendations and improving the overall recommendation accuracy. Experimental results demonstrate that the proposed algorithm achieves better recommendation results than other collaborative filtering recommendation algorithms. © 2023 IEEE.

关键词： Collaborative filtering

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：