检索结果-内蒙古大学图书馆

Wireless Coded Computation With Error Detection

IEEE TRANSACTIONS ON COMMUNICATIONS 2024年第3期72卷 1273-1289页

作者： Fang, Borui Chen, Li Chen, Yunfei You, Changsheng Chen, Xiaohui Wang, Weidong Univ Sci & Technol China Dept Elect Engn & Informat Sci Hefei 230027 Anhui Peoples R China Univ Durham Dept Engn Durham DH1 3LE England Southern Univ Sci & Technol SUSTech Dept Elect & Elect Engn Shenzhen 518055 Peoples R China

In wireless networks with distributed computing, the computational performance is limited by stragglers. To mitigate the stragglers' effect, coded computation is adopted through computational redundancy. Moreover, in wireless transmission, transmission errors may occur due to noise, channel fading and so on. Existing works design coded computation and error detection separately. However, this leads to frequent encoding and inefficient allocation. In this paper, we propose a joint computation and transmission coding (JCTC) scheme to design coded computation and error detection jointly. The coded computation is based on Luby transform (LT) code and linear error-detecting codes are applied for the re-transmission mechanism. To achieve the low dynamic encoding, two-layer encoding is adopted. Then, the performances of JCTC scheme are analyzed in terms of latency and computation reliability. Finally, in order to achieve efficient task and redundancy allocation, the wireless LT coded computation with error detection (WLTCC-ED) algorithm is given from both iterative and low-complexity perspectives respectively. Through theoretical analysis and numerical simulation, it shows that our proposed JCTC scheme has significant advantages over separate designs.

关键词： Coded computation distributed computing error detection transmission errors wireless networks

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning With Adaptive Batchnorm for Healthcare

引用

IEEE TRANSACTIONS ON BIG DATA 2024年第6期10卷 915-925页

作者： Lu, Wang Wang, Jindong Chen, Yiqiang Qin, Xin Xu, Renjun Dimitriadis, Dimitrios Qin, Tao Univ Chinese Acad Sci Beijing 101408 Peoples R China Chinese Acad Sci Inst Comp Technol Beijing 100045 Peoples R China Microsoft Res Asia Beijing 100080 Peoples R China Chinese Acad Sci Pengcheng Lab Inst Comp Technol Shenzhen 518066 Peoples R China Zhejiang Univ Hangzhou 310027 Peoples R China Microsoft Res Redmond WA 98052 USA

There is a growing interest in applying machine learning techniques to healthcare. Recently, federated learning (FL) is gaining popularity since it allows researchers to train powerful models without compromising data privacy and security. However, the performance of existing FL approaches often deteriorates when encountering non-iid situations where there exist distribution gaps among clients, and few previous efforts focus on personalization in healthcare. In this article, we propose FedAP to tackle domain shifts and then obtain personalized models for local clients. FedAP learns the similarity between clients based on the statistics of the batch normalization layers while preserving the specificity of each client with different local batch normalization. Comprehensive experiments on five healthcare benchmarks demonstrate that FedAP achieves better accuracy compared to state-of-the-art methods (e.g., 10%+ accuracy improvement for PAMAP2) with faster convergence speed.

关键词： Medical services Collaborative work Data models Adaptation models Computational modeling Machine learning Data privacy distributed computing federated learning personalization batch normalization healthcare

来源：评论

学校读者我要写书评

暂无评论

Vaccination Against Backdoor Attacks on Federated Learning Systems

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2025年第7期55卷 4434-4443页

作者： Sundar, Agnideven Palanisamy Li, Feng Zou, Xukai Gao, Tianchong Hosler, Ryan Purdue Univ Indianapolis Dept Comp Sci Indianapolis IN 46202 USA Purdue Univ Indianapolis Dept Comp & Informat Technol Indianapolis IN 46202 USA Indiana Univ Indianapolis Dept Comp Sci Indianapolis IN 46202 USA Southeast Univ Sch Cyberspace Secur Nanjing 210096 Jiangsu Peoples R China

Federated Learning (FL) enhances model performance for participants with limited data but is highly vulnerable to backdoor attacks. Unlike Byzantine attacks, backdoor attacks infiltrate local models undetected, causing selective misclassification under specific conditions. Existing defenses rely entirely on a trusted central server, raising concerns if the server fails or acts maliciously. This article introduces a novel vaccination-based technique, empowering clients to defend their models independently with minimal computation and no communication overhead. Our approach is effective even when only a subset of benign clients adopt the protocol, offering a practical, client-centric solution to enhance FL security. Experimental results demonstrate that our method reduces the attack success rate (ASR) to as low as 4.17%, compared to over 47% for state-of-the-art defenses like FoolsGold, while maintaining a high main task accuracy of 82.94%, closely matching the baseline accuracy of 83.21%. Furthermore, even when the proportion of malicious participants exceeds 60%, the backdoor trigger is not part of the vaccine trigger or only one client follows the vaccination protocol, the ASR remains below 7.8%.

关键词： Vaccines Data models Training Sensitivity Training data Servers Protocols Computational modeling Federated learning Inspection Adversarial machine learning backdoor attacks distributed computing federated learning

来源：评论

学校读者我要写书评

暂无评论

Productivity, Portability, Performance, and Reproducibility: Data-Centric Python

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2025年第5期36卷 804-820页

作者： Ziogas, Alexandros Nikolaos Schneider, Timo Ben-Nun, Tal Calotoiu, Alexandru De Matteis, Tiziano de Fine Licht, Johannes Lavarini, Luca Hoefler, Torsten Swiss Fed Inst Technol Dept Informat Technol & Elect Engn CH-8092 Zurich Switzerland Swiss Fed Inst Technol Dept Comp Sci CH-8092 Zurich Switzerland Lawrence Livermore Natl Lab Ctr Appl Sci Comp Livermore CA 94550 USA Vrije Univ Amsterdam Dept Comp Sci NL-1081 HV Amsterdam Netherlands NextSilicon CH-8005 Zurich Switzerland 1plusX CH-8005 Zurich Switzerland

Python has become the de facto language for scientific computing. Programming in Python is highly productive, mainly due to its rich science-oriented software ecosystem built around the NumPy module. As a result, the demand for Python support in High-Performance computing (HPC) has skyrocketed. However, the Python language itself does not necessarily offer high performance. This work presents a workflow that retains Python's high productivity while achieving portable performance across different architectures. The workflow's key features are HPC-oriented language extensions and a set of automatic optimizations powered by a data-centric intermediate representation. We show performance results and scaling across CPU, GPU, FPGA, and the Piz Daint supercomputer (up to 23,328 cores), with 2.47x and 3.75x speedups over previous-best solutions, first-ever Xilinx and Intel FPGA results of annotated Python, and up to 93.16% scaling efficiency on 512 nodes. Our benchmarks were reproduced in the Student Cluster Competition (SCC) during the Supercomputing Conference (SC) 2022. We present and discuss the student teams' results.

关键词： Productivity Codes Semantics Computer architecture Supercomputers Software Field programmable gate arrays Optimization Python Computer languages high-performance computing dataflow computing parallel programming distributed computing distributed computing

来源：评论

学校读者我要写书评

暂无评论

Optimized Multi-Modular Services: Empowering Earth Observation Data Processing

引用

INFORMATICA 2024年第2期35卷 363-378页

作者： Lalayan, Arthur Astsatryan, Hrachya Poghosyan, Suren Giuliani, Gregory Inst Informat & Automat Problems Yerevan Armenia Inst Environm Sci Geneva Switzerland

The significance of earth observation data spans diverse fields and domains, driving the need for efficient management. Nevertheless, the exponential increase in data volume brings new challenges that complicate processing and storing data. This article proposes an optimized multimodular service for earth observation data management in response to these challenges. The suggested approach focuses on choosing the optimal configurations for the storage and processing layers to improve the performance and cost-effectiveness of managing data. By employing the recommended optimized strategies, earth observation data can be managed more effectively, resulting in fast data processing and reduced costs.

关键词： Earth observation distributed computing performance optimization

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Aided Anonymous Traceable and Revocable Access Control Scheme With Dynamic Policy Updating for the Cloud IoT

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第1期11卷 526-542页

作者： Zhang, Leyou Li, Xinmin Wu, Qing Rezaeibagha, Fatemeh Xidian Univ Sch Math & Stat Xian 710126 Peoples R China Xian Univ Posts & Commun Sch Automat Xian 710121 Peoples R China Murdoch Univ Discipline Informat Technol Math & Stat Perth WA 6150 Australia

The Internet of Things has been applied in various fields of industry, which has promoted the intelligent development of the industry and improved efficiency in industrial production. The devices involved in the IoT have generated useful and sensitive data over time and upload the data to the cloud to realize real-time data sharing. To ensure the confidentiality of data, many systems use attribute-based encryption primitive to encrypt data. However, there are still some security and privacy problems in this mode, such as the lack of identification of malicious users who leaked private keys, performance bottleneck caused by excessive reliance on a single central authority (CA), and vulnerability because a single CA holds the private keys of all users in the system. In this article, white-box tracking is used to identify malicious users. The alliance chain is introduced to support multiauthority environments, where the consensus nodes are managed by different authorities and assist CA in generating partial private keys. To protect users' privacy, users remain anonymous at all times during their interactions with blockchain consensus. The security analysis and simulation results show that the proposed scheme outperformed other comparable schemes, indicating that it is a preferable scheme.

关键词： Cloud computing Internet of Things Cryptography Blockchains Encryption Data privacy Privacy Anonymous traceable attribute-based encryption (ABE) distributed computing policy updating privacy protection revocable

来源：评论

学校读者我要写书评

暂无评论

Evolutionary approach for composing a thoroughly optimized ensemble of regression neural networks

引用

EGYPTIAN INFORMATICS JOURNAL 2024年 28卷

作者： Krstic, Lazar Ivanovic, Milos Simic, Visnja Stojanovic, Boban Univ Kragujevac Fac Sci 12 Radoja Domanovica St Kragujevac 34000 Serbia

The paper presents the GeNNsem (Genetic algorithm ANNs ensemble) software framework for the simultaneous optimization of individual neural networks and building their optimal ensemble. The proposed framework employs a genetic algorithm to search for suitable architectures and hyperparameters of the individual neural networks to maximize the weighted sum of accuracy and diversity in their predictions. The optimal ensemble consists of networks with low errors but diverse predictions, resulting in a more generalized model. The scalability of the proposed framework is ensured by utilizing micro-services and Kubernetes batching orchestration. GeNNsem has been evaluated on two regression benchmark problems and compared with related machine learning techniques. The proposed approach exhibited supremacy over other ensemble approaches and individual neural networks in all common regression modeling metrics. Real-world use-case experiments in the domain of hydro-informatics have further demonstrated the main advantages of GeNNsem: requires the least training sessions for individual models when optimizing an ensemble;networks in an ensemble are generally simple due to the regularization provided by a trivial initial population and custom genetic operators;execution times are reduced by two orders of magnitude as a result of parallelization.

关键词： Ensemble modeling Regression ANN Genetic algorithm distributed computing

来源：评论

学校读者我要写书评

暂无评论

Verifiable Coded Computation of Multiple Functions

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2024年 19卷 8009-8022页

作者： Kim, Wilton Kruglik, Stanislav Kiah, Han Mao Nanyang Technol Univ Sch Phys & Math Sci Singapore City 639798 Singapore

We consider the problem of evaluating distinct multivariate polynomials over several massive datasets in a distributed computing system with a single master node and multiple worker nodes. We focus on the general case when each multivariate polynomial is evaluated over its corresponding dataset and propose a generalization of the Lagrange Coded computing framework (Yu et al., 2019) to perform all computations simultaneously while providing robustness against stragglers who do not respond in time, adversarial workers who respond with wrong computation and information-theoretic security of dataset against colluding workers. Our scheme introduces a small computation overhead which results in a reduction in download cost and also offers comparable resistance to stragglers over existing solutions. On top of it, we also propose two verification schemes to detect the presence of adversaries, which leads to incorrect results, without involving additional nodes.

关键词： Polynomials Servers Costs Task analysis distributed computing Vectors Security communication efficiency verifiability privacy

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Heuristics to Schedule Task Graphs on Heterogeneous Voltage-Frequency Islands

引用

IETE JOURNAL OF RESEARCH 2024年第10期70卷 7735-7750页

作者： Jain, Anupam Singh, Jagpreet Singh, Navjot Indian Inst Informat Technol Allahabad Uttar Pradesh India Indian Inst Technol Ropar Punjab India

For energy and cost-efficient computing, many desktops and embedded computing devices these days use voltage frequency islands (VFIs) based processors. An island in VFIs consists of multiple homogeneous cores;however, multiple islands are generally heterogeneous in nature. In contrary to architectures (non-VFI) with per-core dynamic voltage frequency scaling (DVFS), in VFI, all the cores in an island run on the same voltage/frequency at the same time. The energy-aware scheduling of task graphs on VFI architectures is challenging and different from non-VFI architectures in which task-based DVFS is possible. However, in VFI scheduling, the time slot for which an island runs on a particular voltage will be decided. In this paper, we analyse 20 different scheduling heuristics for VFI architectures by varying the size of this time slot based on the workload properties and also by varying the voltage/frequency of the time slots. We also propose a heuristic OptSlotVFI to utilize all the slots optimally. The results show that the VFI scheduling heuristics are able to generate schedules which improve energy consumption up to 25% with an equivalent or shorter schedule length than the state-of-the-art approaches.

关键词： distributed computing energy-efficient heterogeneity multiprocessor parallel computing VFI-scheduling

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of Cloud Brokers for Autonomic Service Distribution

引用

IEEE ACCESS 2024年 12卷 131164-131187页

作者： Hamzah Khan, Mohd Habaebi, Mohamed Hadi Rafiqul Islam, Md. Int Islamic Univ Malaysia Dept Elect & Comp Engn Kuala Lumpur 53100 Malaysia

In recent years, cloud computing has become an essential distributed computing platform and has achieved enormous popularity. Within cloud computing, the Cloud service broker creates an abstraction layer between provider and consumer so that customers notice the cloud service providers' offered services' solitary view. The brokers of cloud service help connect the cloud's substantial resources and select the data centers of the cloud that meet the user's requirement while maximizing the entire response time and reducing cost. The landscape of autonomic cloud brokers has been reviewed in this systematic literature review study, while the PRISMA approach is used to analyze the literature. This comprehensive review of cloud brokerage mechanisms is tailored towards the autonomic distribution of services. To emphasize autonomic computing and cloud-access security brokers, the evolving paradigms of cloud service selection are detailed and critically analyzed to enhance service distribution efficiency. Further, the role of cloud brokers in load-balancing services is also highlighted in this study. A new taxonomy for the structured framework of cloud brokerage mechanisms is introduced based on functionalities, deployment models, and architecture for the autonomic service distribution. Finally, the study offers valuable insights for future research challenges and best practices in cloud security.

关键词： Cloud computing Data centers Security distributed computing Databases Load management Costs Virtual machining Cloud broker cloud service broker data center cloud computing load balancing virtual machines

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：