检索结果-内蒙古大学图书馆

22nd International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2022

作者： Chen, Sixin Tang, Bing Yang, Qing Liu, Yuanyuan School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China Hunan Key Laboratory for Service Computing and Novel Software Technology Hunan University of Science and Technology Xiangtan411201 China School of Information and Communication Engineering Guangzhou Maritime University Guangzhou510725 China

ISBN: (纸本)9783031226762

With the rapid development of IoT applications, how to process large and continuous data streams in real time for IoT applications has become a challenge in recent years. This paper presents a model to predict the Maximum Sustainable Throughput (MST) of data streaming applications at the edge, and then proposes GACP, a constraint programming-base operator placement strategy to maximize MST using the genetic algorithm. We evaluated the proposed operator placement strategy in terms of MST, the number of edge servers in usage, and the percentage of communications within edge servers. Experimental results show that compared with the existing heuristic algorithms, the proposed GACP strategy can achieve better MST, which is 2–5 times higher than existing algorithms. © 2023, Springer Nature Switzerland AG.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

EventMon: Real-Time Event-based Streaming Network Monitoring Data Recovery

引用

IEEE Transactions on Dependable and Secure computing 2024年第03期22卷 2413-2429页

作者： Li, Yuhui Liang, Wei Xie, Kun Zhang, Dafang Li, Kuanching Xiong, Neal N. Hunan University of Science and Technology China Hunan University Hunan University of Science and Technology China The Hong Kong Polytechnic University China Hunan Key Laboratory for Service Computing and Novel Software Technology School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China Hunan University of Science and Technology Sanya Research Institute Sanya572024 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Northeastern State University Department of Mathematics and Computer Science TahlequahOK74464 United States

Data recovery is a fundamental task for sparse network monitoring with a significant impact on many downstream tasks, such as congestion control, network capacity planning, and traffic engineering. To better capture the network dynamically and quickly respond to network failure, network monitoring systems take finer temporal granularity to collect data to form a real-time view of the network. Unfortunately, the current data recovery for network monitoring relies on matrix and tensor completion algorithms, which fail to satisfy the requirements of real-time recovery. To combat this problem, in this paper, we propose Real-Time Event-based Streaming Network Monitoring Data Recovery (EventMon) that achieves ultra-low latency data recovery in network measurement data streams. Specifically, we leverage a mixture of offline and online architecture, with the offline component learns to capture the historical spatial-temporal correlation while the online component is a novel streaming encoder that updates factor matrices incrementally. To enable training our event-level stream processing module, we devise a novel Stream2Batch algorithm to enable mini-batch style training and ensure the encoder generates the same results with one-by-one stream processing. We conduct extensive experiments on three network monitoring datasets and our evaluation and analysis of the experimental results demonstrate shows that the proposed method outperforms existing schemes in terms of accuracy, inference latency, and high processing throughput. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

A Web service Classification Method Based on Graph Neural Network Knowledge Distillation 19

A Web Service Classification Method Based on Graph Neural Ne...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Huang, Hao Cao, Buqing Liu, Shanpeng Zhou, Dong Tang, Mingdong Xiao, Feng Hunan University of Science and Technology School of Computer Science and Engineering Hunan Key Laboratory of Service Computing and New Software Service Technology Xiangtan China Guangdong University of Foreign Studies School of Information Science and Technology Guangzhou China

ISBN: (纸本)9798350346558

With the increasing number of Web services, service discovery becomes a significant challenge, and service classification methods based on Graph Neural Network (GNN) are considered to be an efficient way for service discovery. However, these methods rarely exploit the structure-based and feature-based prior knowledge of services. To address this problem, this paper proposes a Web service classification method based on graph neural network knowledge distillation. In this method, firstly, it employs Word2Vec to extract the semantic feature vector from service descriptions, and then builds the service relationship network based on the shared tag annotation relationship of service. Secondly, a graph neural network knowledge distillation framework for Web service classification consisting of a teacher model and a student model is designed. The teacher model extracts the knowledge of GNN model, and the student model obtains the structure-based and feature-based prior knowledge of the service relationship network from teacher model by neighbor feature aggregation and feature transformation. Finally, GNN models (GCN, GAT, SAGE, APPNP, SGC, and GCNII) as teacher models for accuracy comparison are used in the experiment. From the experiment result, the classification accuracy of the student model is 11.64%23.10% higher than that of the teacher model. © 2022 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Overview of Blockchain Privacy Protection 8

Overview of Blockchain Privacy Protection

引用

8th IEEE International Conference on Big Data Security on Cloud, 8th IEEE International Conference on High Performance and Smart computing, and 8th IEEE International Conference on Intelligent Data and Security, BigDataSecurity/HPSC/IDS 2022

作者： Yang, Ce Chen, Juan Zeng, Bin Liao, Lei School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China College of Computer Science and Electronic Engineering Hunan University Changsha China Hunan YouDao Information Technology Co. Ltd. Changsha China Hunan Vocational College of Art Changsha China

ISBN: (纸本)9781665480697

In recent years, blockchain technology has attracted extensive attention in academia and industry by virtue of its unique advantages such as decentralization, tamper proof, openness and traceability. The combination of blockchain and data protection has always been the focus of scholars. This paper first analyzes the system structure and characteristics of the blockchain itself, and introduces the development process of the blockchain. Secondly, it analyzes the privacy threats faced by data protection in the blockchain, and introduces the relevant blockchain privacy protection technologies. Finally, it discusses how to combine blockchain and other technologies to enhance privacy protection. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Bilinear Graph Neural Network-Enhanced Web services Classification 23

Bilinear Graph Neural Network-Enhanced Web Services Classifi...

引用

23rd IEEE International Conference on High Performance computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Zhang, Lulu Cao, Buqing Peng, Mi Qing, Yueying Kang, Guosheng Liu, Jianxun Fletcher, Kenneth K. School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory of Service Computing and New Software Service Technology Xiangtan China University of Massachusetts Boston Department of Computer Science Boston United States

ISBN: (纸本)9781665494571

With the growing number of Web services, classifying Web services accurately and efficiently has become a challenging problem. Effective service classification is conducive to improving the quality of service discovery and the efficiency of service composition. Existing graph neural network methods represent the target service node by a weighted sum of the features of the neighbor service nodes, and have achieved remarkable results in service classification. However, these methods ignore the impact of possible interactions between neighbor service nodes on the target service node. To address this problem, we propose a Web services classification method based on bilinear graph neural network. Our proposed method can model the bilinear interactions between neighbor service nodes and effectively improve the accuracy of service classification. First, our proposed model uses the Word2Vec model to extract the latent semantic vectors from service description documents. We then construct the service relationship network according to tags and shared annotation relationships of Web services. Next, a bilinear aggregator is used to model the pairwise interactions between neighbor service nodes, highlighting the local common attributes. Finally, the bilinear aggregator is combined with the weighted sum aggregator to construct a bilinear graph neural network, which can learn more comprehensive representations of services. The experimental results on the real dataset from ProgrammableWeb show that the classification accuracy of the proposed method is greatly improved compared with DeepWalk, Node2Vec, GCN, and GAT. © 2021 IEEE.

关键词： Smart cities Annotations Mashups Semantics Quality of service Feature extraction Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

AMSC: Adaptive Multi-channel Graph Convolutional Network-Enhanced Web services Classification 23

AMSC: Adaptive Multi-channel Graph Convolutional Network-Enh...

引用

作者： Qing, Yueying Cao, Buqing Peng, Mi Zhang, Lulu Kang, Guosheng Liu, Jianxun Fletcher, Kenneth K. School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory of Service Computing and New Software Service Technology Xiangtan China University of Massachusetts Boston Department of Computer Science Boston United States

ISBN: (纸本)9781665494571

With the development of service Oriented Architecture (SOA), the number of Web services on the Internet is also growing rapidly. Classifying Web services accurately and efficiently is helpful to improve the quality of services discovery and promote the efficiency of service composition. However, existing deep learning-based Web services classification methods, such as graph convolutional networks (GCNs), are incapable of adaptively learning the correlation between service topology structure and service node features concurrently, resulting in unsatisfactory classification performance. To address this problem, this paper proposes an adaptive multi-channel GCN-enhanced Web services classification method. In this method, we first extract specific and shared embedding, in the Web API node isomorphic network, from the node features, topology, and combination of Web service nodes. Then, an attention mechanism is used to learn the importance weight of each embedding. By doing this, we adaptively integrate these weights to ensure the consistency and difference of each learned embedding. Finally, experimental results on real datasets from Programmable Web show that compared with LINE, Node2vec, Deep-walk, GCN, and GAT, the method proposed in this paper has an average improvement in accuracy of 19.81%, 19.35%, 19.16%, 11.56%, and 7.75% respectively. © 2021 IEEE.

关键词： Correlation Adaptive systems Network topology Smart cities Quality of service Feature extraction Topology

来源：评论

学校读者我要写书评

暂无评论

Container-based data-intensive application scheduling in hybrid cloud-edge collaborative environment

Container-based data-intensive application scheduling in hyb...

引用

作者： Tang, Bing Luo, Jincheng Zhang, Jiaming School of Computer Science and Engineering Hunan University of Science and Technology Hunan Xiangtan China Hunan Key Laboratory for Service Computing and Novel Software Technology Hunan University of Science and Technology Hunan Xiangtan China School of Information and Communication Engineering Guangzhou Maritime University Guangdong Guangzhou China School of Information Engineering Wuhan University of Technology Hubei Wuhan China

Container virtualization technology represented by Docker has been widely used in the industry due to its advantages of lightweight, fast deployment, and easy portability. It can bring convenience to system deployment, operation, and maintenance. This article considers the implementation of AI-based IoT applications based on Docker and container technology in a cloud-edge collaborative environment. Three typical data-intensive applications, preprocessing, training, and inference in machine learning, are deployed using Docker containers. For these three types of tasks, this article proposes a container-based data-intensive application scheduling framework. Using an attribute-based data-driven method, a new scheduling approach considering multiple weighting factors is proposed, which is called DICS-OPT. The cloud nodes and edge nodes are scored and sorted uniformly. The container is scheduled to the node with the highest score, and then the task data is transmitted to the node to execute the task. NSGA-III-based genetic algorithm has been proposed to search for the optimal weighting factors. This article introduces the implementation of the prototype system and builds a cloud-edge collaborative testbed consisting of Raspberry Pis and PCs. The performance evaluation results indicates that the proposed scheduling approach outperforms existing approaches. Compared with existing approaches, DICS-OPT improves the average edge resource utilization by 10.05% to 69.04%, and saves the cloud resource cost by 16.02% to 36.68%. © 2023 John Wiley & Sons Ltd.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A Survey of Applications of Vision Transformer and its Variants

A Survey of Applications of Vision Transformer and its Varia...

引用

Intelligent Data and Security (IDS), IEEE International Conference on

作者： Chuang Wu Tingqin He Hunan Key Laboratory for Service computing and Novel Software Technology School of Computer Science and Engineering Hunan University of Science and Technology

ISBN: (数字)9798350389487

ISBN: (纸本)9798350389494

The Transformer architecture, renowned for its efficacy in natural language processing, encounters unique hur-dles when applied to computer vision. In response, the Vision Transformer (Vi $T$ ) emerges as a successful adaptation for image classification tasks. While ViT exhibits tremendous potential in revolutionizing computer vision, addressing its inherent chal-lenges and limitations stands as a critical endeavor. This compre-hensive survey meticulously scrutinizes the drawbacks associated with ViT, proposing bespoke adaptations tailored to specific applications while showcasing their remarkable performance across diverse visual tasks. Moreover, it delves into the evolution of ViT adaptations across various visual domains, elucidating four promising directions for future research and development in this dynamic field.

关键词： Surveys Computer vision Visualization Computational modeling Transformers Real-time systems Data models

来源：评论

学校读者我要写书评

暂无评论

A Multiple-Path Learning Neural Network Model for Code Completion

A Multiple-Path Learning Neural Network Model for Code Compl...

引用

2023 IEEE International Conference on Web services, ICWS 2023

作者： Liu, Yi Liu, Jianxun Zhang, Xiangping Hu, Haize Hunan University of Science and Technology Hunan Provincial Key Laboratory for Services Computing and Novel Software Technology Xiangtan411201 China Hunan University of Humanities Science and Technology School of Informationn Loudi417000 China Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan411201 China

ISBN: (纸本)9798350304855

Code completion, which can accelerate the software development process and improve the quality of software products, is an essential part of today's integrated development environments. It has become an important research topic in the field of software engineering. Recent studies have shown that the method of code completion based on the Abstract Syntax Tree (AST) learns syntactic information about the code, which helps to improve the accuracy of code completion. However, when modeling neural networks for ASTs, the sequencing operation of nodes leads to the loss of their hierarchical structure information. Meanwhile, traditional neural networks cannot predict many Out-of-Vocabulary (OoV) words in the terminal node values of AST. To alleviate the above problem, in this paper, we propose a Multiple-Path Learning neural network model for code completion (MPL) based on an AST by learning from a large-scale corpus. In this model, multiple paths such as context path, root path, and terminal node path are established to understand different code features required for node prediction and improve code representation ability. Based on the principle of program local repeatability, it also adopts a replication mechanism to copy the appropriate OoV words from the local terminal node path as the prediction result, further improving the prediction accuracy. The experimental results show that the MPL model has better performance than existing methods on the code completion task. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Blockchain Development 7th

Blockchain Development

引用

7th International Conference on Smart computing and Communication, SmartCom 2022

作者： Xie, Siqi Cai, Jiahong Zhu, Hangyu Yang, Ce Chen, Lin Xiao, Weidong School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan411201 China Guangdong Financial High-Tech Zone "Blockchain +" Fintech Research Institute Foshan528253 China School of Software Engineering Xiamen University of Technology Xiamen361024 China

ISBN: (纸本)9783031281235

In recent years, blockchain research has set off an upsurge in academia, and it is called the next generation of value Internet. Because of its decentralization, anonymity, security, immutability, traceability and other characteristics, blockchain is gradually accepted and developed by people. With the deepening of research and the integration of technologies such as deep learning, blockchain has gradually been applied to various fields such as credit reporting, government, medical care, and industrial Internet of Things, not just the initial virtual currency field. This article mainly discusses the three important stages of blockchain public chain development, namely Bitcoin, Ethereum, and meta-verse, and introduces some basic supporting technologies of blockchain, as well as the research status and future trends of blockchain. Simple Analysis. By vertically introducing the development history of the blockchain, researchers can have a more concrete understanding of the status quo of the blockchain, and provide ideas for blockchain-related research. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Smart contract

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：