检索结果-内蒙古大学图书馆

35th Chinese Control and Decision Conference (CCDC)

作者： Mu, Yashuang Liu, Tian Li, Jiayan Hou, Kai Zhang, Lei Wang, Jiangyong Henan Univ Technol Sch Artificial Intelligence & Big Data Zhengzhou 450001 Peoples R China Henan Univ Technol Coll Informat Sci & Engn Zhengzhou 450001 Peoples R China

ISBN: (纸本)9798350334722

The clustering problems are one of the fundamental data analysis tasks in machine learning and data mining. However, many traditional clustering methods cannot directly deal with large-scale data sets as the restriction of memory. In this paper, we develop a simple distributed fuzzy c-means clustering method via the technique of Map-Reduce for large-scale data sets. First, a distributed data dividing method is designed to randomly partition the original data set to several data blocks. Then, we establish a data center determining method through applying fuzzy c-means clustering algorithm in the framework of Map-Reduce. Finally, a distributed clustering method is proposed according to the distance of between each sample and the nearest center. The experimental studies verify the feasibility in clustering accuracy and the parallelism in clustering time.

关键词： Clustering analysis distributed computing Map-Reduce Fuzzy c-means

来源：评论

学校读者我要写书评

暂无评论

IBing: An Efficient Interleaved Bidirectional Ring All-Reduce Algorithm for Gradient Synchronization

引用

ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION 2025年第1期22卷 1-23页

作者： Zong, Ruixing Zhang, Jiapeng Tang, Zhuo Li, Kenli Hunan Univ Coll Comp Sci & Elect Engn Changsha Hunan Peoples R China Hunan Univ Changsha Hunan Peoples R China

Ring all-reduce is currently the most commonly used collective communication technique in the fields of data parallel and distributed computing. It consists of three phases: communication establishment, data transmission, and data processing at each step. However, this method may suffer from increased communication latency as the number of computation nodes increases, excessive communication steps and data processing procedures can lead to insufficient bandwidth utilization. To address this issue, this article proposes an Interleaved Bidirectional Ring (IBing) all-reduce method, which uses specially crafted communication operations to improve communication efficiency by reducing the effects of both communication establishment and data processing time. IBing reduces the number of communication steps by half compared to the Ring all-reduce. The results of extensive experiments indicate that the proposed IBing design can reduce total communication consumption by an average of 8.49% and up to 49.73%.

关键词： distributed computing data parallel ring all-reduce

来源：评论

学校读者我要写书评

暂无评论

High-fidelity Graphics for Dynamically Generated Environments using distributed computing 6

High-fidelity Graphics for Dynamically Generated Environment...

引用

6th International Conference on Games and Virtual Worlds for Serious Applications (VS-GAMES)

作者： Bugeja, Keith Debattista, Kurt Spina, Sandro Chalmers, Alan Univ Warwick WMG Coventry W Midlands England

ISBN: (纸本)9781479940561

In many serious games and applications, increasing visual fidelity enhances immersion. While physically-based renderers can produce highly realistic imagery by correctly simulating light propagation, these are impractical in the context of interactive applications due to lengthy computations. For real-time applications, several rasterisation-based techniques have been developed to augment the visual realism in a scene, such as the inclusion of shadows and ambient occlusion. These techniques however, come at the cost of additional compute resources from GPUs. This paper describes a novel technique which takes advantage of the distributed computational resources available at peers participating in a serious game to precompute the light distribution in the virtual environment. This additional information is then included within the vertex geometry of the scene and used at no extra costs whilst rendering. Experimental evaluation shows that the rendered virtual environments are much more realistic and more closely match reference imagery generated by physically-based renderers.

关键词： augmented reality distributed processing graphics processing units light propagation rendering (computer graphics) serious games (computing) GPU ambient occlusion distributed computational resources distributed computing dynamically generated environments high-fidelity graphics interactive applications physically-based renderers rasterisation-based techniques realistic imagery serious games shadow occlusion vertex geometry virtual environment visual fidelity Games Geometry Light sources Lighting Rendering (computer graphics) Virtual environments Visualization Virtual environments LIGHT PROPAGATION distributed computing distributed processing LIGHT SOURCES augmented reality Graphics Processing Unit Visualization Lighting geometry Rendering (computer graphics) Game theory Renderers

来源：评论

学校读者我要写书评

暂无评论

The Concept of Green Cloud Infrastructure Based on distributed computing and Hardware Accelerator within FPGA as a Service 12

The Concept of Green Cloud Infrastructure Based on Distribut...

引用

Proceedings of IEEE East West Design and Test Symposium ( EWDTS 2014)

作者： Yanovskaya, O. Yanovsky, M. Kharchenko, V. Natl Aerosp Univ Kharkov Ukraine Ctr Safety Infrastruct Oriented Res & Anal Kharkov Ukraine

ISBN: (纸本)9781479976300

The article focuses on the energy efficiency issue and the negative impact on the environment of Cloud computing based on data centers infrastructure. A modernization of Cloud architecture in terms of Green computing is proposed, using FPGA hardware accelerators and distributed peer-to-peer networks. Customer and FPGA as a Service (FAAS) interaction scenarios are discussed. A distributed peer-to-peer Cloud architecture is suggested. The energy efficiency analysis of the proposed architectures shows its advantages.

关键词： cloud computing computer centres field programmable gate arrays peer-to-peer computing software architecture FAAS FPGA as a service FPGA hardware accelerators cloud architecture data centers infrastructure distributed computing distributed peer-to-peer networks energy efficiency green cloud infrastructure Cloud computing Computer architecture Energy consumption Field programmable gate arrays Green products Hardware Power demand Field programmable gate arrays Cloud computing distributed computing Energy efficiency Green products Peer to peer computing Power demand Computer Architecture hardware accelerator Software architecture Computer hardware energy consumption Environmental impact

来源：评论

学校读者我要写书评

暂无评论

PESC - Parallel Experience for Sequential Code

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2025年第12-14期37卷

作者： Santos, Henrique C. T. de Souza, Luciano S. de Carvalho, Jonathan H. A. Ferreira, Tiago A. E. Inst Fed Pernambuco Recife PE Brazil Univ Fed Rural Pernambuco Recife PE Brazil Univ Fed Pernambuco Recife PE Brazil

The need for computational resources grows as computational algorithms gain popularity in different sectors of the scientific community. Sequential codes need to be converted to parallel versions to optimize the use of these resources. Maintaining a local infrastructure for the execution of distributed computing, through desktop grids, for example, has been replaced in favor of cloud platforms that abstract the complexity of these local infrastructures. Unfortunately, the cost of accessing these resources could leave out various studies that could be carried by a simpler infrastructure. In this article, we present a platform for distributing computer simulations on resources available on a local network using container virtualization that abstracts the complexity needed to configure these execution environments and allows any user can benefit from this infrastructure. Simulations could be developed in any programming language (such as Python, Java, C, and R) and with specific execution needs within reach of the scientific community in a general way. We will present results obtained in running simulations that required more than 1000 runs with different initial parameters and various other experiments that benefited from using the platform.

关键词： container virtualization desktop grid distributed computing parallel programing sequential code

来源：评论

学校读者我要写书评

暂无评论

DiAD - distributed Acceleration for Datacenter FPGAs 33

DiAD - Distributed Acceleration for Datacenter FPGAs

引用

33rd International Conference on Field-Programmable Logic and Applications (FPL)

作者： Lant, Joshua Skordalakis, Emmanouil Paraskevas, Kyriakos Toms, William B. Lujan, Mikel Goodacre, John Univ Manchester Dept Comp Sci Manchester M13 9PL Lancs England

ISBN: (纸本)9798350341515

The growing demands placed upon modern compute and network resources are far exceeding the capabilities of traditional computer architectures. It is now customary for accelerators to perform the bulk of compute, and this compute is being pushed ever closer to the network. FPGA vendors have brought powerful datacenter cards to the market, combining reprogrammable FPGA fabrics with high bandwidth networking capability. However, the supporting infrastructure has yet to reach maturity, so modern and diverse workloads are not yet able to fully leverage these architectural advances. In this paper we present DiAD;a novel framework providing FPGA firmware and driver support for fully unified, distributed compute and network acceleration across a commodity Ethernet network. We present a far richer feature set and greater flexibility than other existing solutions. We show comparable networking performance from the host when compared to Xilinx's OpenNIC solution. As well as allowing for host networking through the FPGA fabric, we demonstrate reliable data transfer directly between FPGA fabrics without host intervention, and show native memory transactions sent over the network supporting pointer-chasing workloads. We achieve line rate for dataflow type communication and approach line rate for larger native memory transfers (87G).

关键词： datacenter distributed computing FPGA networks

来源：评论

学校读者我要写书评

暂无评论

Cryptography in distributed Ledger Technologies from a Layered Perspective: A State of the Art 1

引用

3rd International Conference on Digital Technologies and Applications

作者： Barj, Sara Ouaddah, Aafaf Mezrioui, Abdellatif Natl Inst Posts & Telecommun Rabat Morocco

ISBN: (数字)9783031298608

ISBN: (纸本)9783031298592;9783031298608

Cryptography is the practice of secure communication to protect data's confidentiality, integrity, and authenticity. In the context of blockchains, cryptography is used to secure transactions, protect users' privacy, and ensure the integrity and security of the network. Nevertheless, this later is subject to many attacks, such as post-quantum attacks. In this paper, we survey and extract how cryptography is used in blockchains from a layered perspective: data, Consensus, and Execution to Application layers. We summarize our findings and results using a table containing the functions of cryptographic protocols, families, functions, primitives, and schemes and how they are utilized for each studied blockchain platform. We discuss each cryptographic technique's related DCEA layer in the forecited table. Therefore, this work helps assess current cryptographic techniques used in current distributed Ledger Technologies or design and develop new hardened ones by choosing post-quantum-related cryptographic techniques for each layer.

关键词： Cryptographic Protocols Privacy Data Security distributed computing Blockchain Design Improvement

来源：评论

学校读者我要写书评

暂无评论

An AIoT System for Earthquake Early Warning on Resource Constrained Devices

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第11期12卷 15101-15113页

作者： Esposito, Marco Belli, Alberto Falaschetti, Laura Palma, Lorenzo Pierleoni, Paola Univ Politecn Marche Dept Informat Engn I-60131 Ancona Italy

Seismic wave picking is an essential task the implementation of earthquake early warning (EEW) systems. While artificial intelligence picking methods show excellent accuracy, most were designed for devices with high-computational resources. At the same time, distributed approaches for Early Warning systems show promise for the implementation of viable, widespread alert systems. This article introduces a complete AIoT system for earthquake picking on resource-constrained devices. An algorithm has been developed to enable AIoT devices to switch between a detection mode, in which inferences are run on the data measured by the device, and a transmission mode, in which the device transmits alarms or other event information. To reduce inference times and input window duration, a set of deep learning pickers, called Fast PNet, derived from the PhaseNet model, were developed, achieving 74.4% inference time reduction for the shortest input model, which also showed a significant decrease in computational and power consumption. Despite a slight reduction in picking precision compared to the baseline model (from 0.09 to 0.25 s), detection performance remains high (96% precision and 98% recall). The overall system has been tested on a real event from Central Italy, displaying a 0.16-s picking error for the selected event, besides also showing its ability to reduce the amount of data to be processed for transmission to about 26.5% of the total observed input data, a great benefit compared to fully centralized EEW systems.

关键词： Computational modeling Earthquakes Data models Internet of Things Benchmark testing Accuracy Monitoring Predictive models Seismic waves Location awareness Artificial intelligence (AI) distributed computing earthquake detection earthquake early warning (EEW) Internet of Things (IoT)

来源：评论

学校读者我要写书评

暂无评论

Energy efficient task-pull scheduling using Equal Length Cellular Automata in distributed computing 4

Energy efficient task-pull scheduling using Equal Length Cel...

引用

Fourth International Conference on Emerging Applications of Information Technology

作者： Mitra, Arnab Kundu, Anirban Chattopadhyay, Matangini Adamas Inst Technol CSE Dept Kolkata 700126 India Netaji Subhash Engn Coll Dept Informat Technol Kolkata 700152 India Jadavpur Univ Sch Educ Technol Kolkata 700032 India

ISBN: (纸本)9781479942725

Energy efficient task-pull scheduling for distributed computing has been reported in this research work. Cellular Automata (CA) based scheduling algorithm has been projected in this report. We have emphasized on the usage of Equal Length Cellular Automata (ELCA) for the allocation of equal length task-pulls to maximize the employment of available processing units. We have introduced a behavioral discussion and examined the benefits of our proposed ELCA based task-pull scheduling methodology. High degree of randomness in generated equal length task-pulls and equal load distribution to available processing units have been established by experimental results. Low energy consumption for any distributed computing environment using ELCA scheduler has been successfully achieved. Efficient utilization of maximum number of available central processing units (CPUs) is achieved using proposed ELCA based scheduling.

关键词： distributed computing Job scheduling Load balancing Energy efficient scheduling Cellular Automata (CA) Equal Length Cellular Automata (ELCA)

来源：评论

学校读者我要写书评

暂无评论

Efficient distributed Approximate k-Nearest Neighbor Graph Construction by Multiway Random Division Forest 23

Efficient Distributed Approximate k-Nearest Neighbor Graph C...

引用

29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)

作者： Kim, Sang-Hong Park, Ha-Myung Kookmin Univ Seoul South Korea

ISBN: (纸本)9798400701030

k-nearest neighbor graphs, shortly k-NN graphs, are widely used in many data mining applications like recommendation, information retrieval, and similarity search. Approximate k-NN graph construction has been getting a lot of attention, and most researches focus on developing algorithms that operate efficiently and quickly on a single machine. A few pioneering studies propose distributed algorithms to increase the size of data that can be processed to billions. However, we notice that the distributed algorithms don't perform well enough due to the problems of graph fragmentation and massive data exchange. In this paper, we propose MRDF (Multiway Random Division Forest), a scalable distributed algorithm that constructs highly accurate k-NN graph from numerous high-dimensional vectors quickly. MRDF resolves the problems that the existing distributed algorithms suffer from, through coarse-grained partitioning based on tree path annotation. Experimental results on real-world datasets show that MRDF outperforms the state-of-the-art distributed algorithms with up to 7.6 times faster speed and up to 56%p better accuracy than the second best results.

关键词： k-nearest neighbor graph approximate k-NN distributed computing scalability

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：