检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

6,705 篇 会议
116 册 图书
70 篇 期刊文献

馆藏范围

6,891 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,560 篇 工学
- 3,366 篇 计算机科学与技术...
- 1,736 篇 软件工程
- 1,054 篇 信息与通信工程
- 673 篇 电气工程
- 228 篇 控制科学与工程
- 179 篇 电子科学与技术（可...
- 143 篇 机械工程
- 97 篇 动力工程及工程热...
- 97 篇 生物工程
- 94 篇 测绘科学与技术
- 42 篇 生物医学工程（可授...
- 40 篇 仪器科学与技术
- 39 篇 光学工程
- 34 篇 建筑学
- 29 篇 土木工程
- 28 篇 网络空间安全
- 27 篇 安全科学与工程
771 篇 理学
- 568 篇 数学
- 112 篇 生物学
- 102 篇 统计学（可授理学、...
- 100 篇 物理学
- 75 篇 系统科学
- 37 篇 化学
511 篇 管理学
- 383 篇 管理科学与工程(可...
- 197 篇 工商管理
- 155 篇 图书情报与档案管...
82 篇 医学
- 80 篇 临床医学
- 25 篇 基础医学(可授医学...
42 篇 经济学
- 42 篇 应用经济学
35 篇 法学
- 25 篇 社会学
12 篇 农学
10 篇 文学
8 篇 教育学
8 篇 军事学
1 篇 艺术学

主题

898 篇 distributed comp...
802 篇 computer network...
513 篇 concurrent compu...
450 篇 wireless sensor ...
377 篇 parallel process...
354 篇 computer science
352 篇 routing
344 篇 neural networks
341 篇 computational mo...
304 篇 computer archite...
260 篇 application soft...
255 篇 network topology
253 篇 peer to peer com...
253 篇 protocols
244 篇 bandwidth
235 篇 grid computing
232 篇 software enginee...
189 篇 costs
177 篇 intelligent netw...
176 篇 artificial intel...

机构

28 篇 institute of com...
24 篇 shandong provinc...
20 篇 key laboratory o...
15 篇 shandong fundame...
14 篇 department of co...
13 篇 university of ch...
12 篇 department of co...
11 篇 department of co...
11 篇 department of co...
11 篇 institute of com...
11 篇 national laborat...
11 篇 beijing universi...
10 篇 college of compu...
10 篇 institute of inf...
10 篇 school of cyber ...
10 篇 department of co...
10 篇 school of comput...
9 篇 shandong enginee...
9 篇 department of co...
9 篇 school of comput...

作者

16 篇 jiannong cao
15 篇 m. takizawa
15 篇 li dongsheng
15 篇 shen hong
15 篇 hong shen
14 篇 shietung peng
14 篇 eyas el-qawasmeh
13 篇 lemin li
13 篇 rothermel kurt
12 篇 hai jin
11 篇 dongsheng li
11 篇 wei zhang
10 篇 koibuchi michihi...
10 篇 jack dongarra
10 篇 t. enokido
10 篇 wang yang
10 篇 stephen l. scott
10 篇 j. duato
10 篇 m. ould-khaoua
9 篇 duerr frank

语言

6,711 篇 英文
168 篇 其他
17 篇 中文

检索条件"任意字段=IASTED International Conference on Parallel and Distributed Computing and Networks"

共 6891 条记录，以下是451-460 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

High-Performance computing for Efficient Transaction Processing: A Comparative Study of parallel and Sequential Execution using SQLite

High-Performance Computing for Efficient Transaction Process...

引用

IoT Based Control networks and Intelligent Systems (ICICNIS), international conference on

作者： C.V.Roshan Balaji Shaman. KR V.Pritham Raj N.Nithish Kumar Kumaran K School of Computer Science and Engineering Vellore Institute of Technology Chennai campus India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

High-performance computing (HPC) has become an essential tool for improving the efficiency and scalability of transaction processing systems, especially as data volumes continue to grow in fields like finance, e-commerce, and blockchain. This paper presents a comparative study of parallel and sequential transaction processing methods using an SQLite database. Specifically, the research investigates the impact of HPC techniques on transaction throughput, processing speed, and efficiency by simulating 1,000 user transactions. The study employs Python's multiprocessing module to simulate parallel execution, contrasting it with traditional sequential execution. Key performance indicators, including execution time, transaction success rate, and system efficiency, were analyzed to determine the advantages of parallel processing in a transaction-heavy environment. Our results reveal that parallel execution significantly reduces processing time, boosts throughput, and increases overall system efficiency compared to sequential processing. Additionally, the study discusses how parallel processing techniques can address common bottlenecks in transaction-heavy applications and provide solutions for improving the performance of large-scale, data-intensive systems. The findings demonstrate the potential for using HPC to optimize database operations, particularly in systems where high-volume transaction processing is a critical requirement. Future work will explore advanced parallelization strategies, fault tolerance mechanisms, and integrations with distributed databases and blockchain systems. This research contributes to the growing body of knowledge on optimizing transaction processing in high-performance computing environments, with potential applications across various sectors, including financial services, e-commerce, and blockchain technology.

关键词： High performance computing Scalability Key performance indicator Process control parallel processing Throughput Blockchains Electronic commerce Resource management Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed 29

1-bit LAMB: Communication Efficient Large-Scale Large-Batch ...

引用

29th Annual IEEE international conference on High Performance computing, Data, and Analytics (HiPC)

作者： Li, Conglong Awan, Ammar Ahmad Tang, Hanlin Rajbhandari, Samyam He, Yuxiong Microsoft Redmond WA 98052 USA Univ Rochester Rochester NY 14627 USA

ISBN: (纸本)9781665494236

To train large machine learning models (like BERT and GPT-3) on hundreds of GPUs, communication has become a significant bottleneck, especially on commodity systems with limited-bandwidth TCP networks. On one side, large batch-size optimization such as the LAMB algorithm was proposed to reduce the frequency of communication. On the other side, communication compression algorithms such as 1-bit Adam help to reduce the volume of each communication. However, we find that simply using one of the techniques is not sufficient to solve the communication challenge, especially under low network bandwidth. Motivated by this we aim to combine the power of large-batch optimization and communication compression but we find that existing compression strategies cannot be directly applied to LAMB due to its unique adaptive layerwise learning rates. To this end, we design a new communication-efficient optimization algorithm, 1-bit LAMB, which introduces a novel way to support adaptive layerwise learning rates under compression. In addition to the algorithm and corresponding theoretical analysis, we propose three novel system implementations in order to achieve actual wall clock speedup: a momentum fusion mechanism to reduce the number of communications, a momentum scaling technique to reduce compression error, and a NCCL-based compressed communication backend to improve both usability and performance. For the BERT-Large pre-training task with batch sizes from 8K to 64K, our evaluations on up to 256 GPUs demonstrate that our optimized implementation of 1-bit LAMB is able to achieve up to 4.6x communication volume reduction, up to 2.8x end-to-end time-wise speedup, and the same sample-wise convergence speed (and same fine-tuning task accuracy) compared to uncompressed LAMB. Furthermore, 1-bit LAMB achieves the same accuracy as LAMB on computer vision tasks like ImageNet and CIFAR100.

关键词： communication compression distributed deep learning language model pre training natural language processing optimization

来源：评论

学校读者我要写书评

暂无评论

AgEBO-Tabular: Joint Neural Architecture and Hyperparameter Search with Autotuned Data-parallel Training for Tabular Data 21

AgEBO-Tabular: Joint Neural Architecture and Hyperparameter ...

引用

international conference for High Performance computing, Networking, Storage and Analysis (SC21)

作者： Egele, Romain Balaprakash, Prasanna Guyon, Isabelle Vishwanath, Venkatram Xia, Fangfang Stevens, Rick Liu, Zhengying Ecole Polytech Palaiseau France Argonne Natl Lab Lemont IL USA Univ Paris Saclay CNRS INRIA LISN Paris France

ISBN: (纸本)9781450384421

Developing high performing predictive models for large tabular data sets is a challenging task. Neural architecture. search (NAS) is an AutoML approach that generates and evaluates multiple neural networks with different architectures concurrently to automatically discover an high performing model. A key issue in NAS, particularly for large data sets, is the large computation time required to evaluate each generated architecture. While data-parallel training has the potential to address this issue, a straightforward approach can result in significant loss of accuracy. To that end, we develop AgEBO-Tabular, which combines Aging Evolution (AE) to search over neural architectures and asynchronous Bayegan optimization (BO) to search over hyperparanieters to adapt data -parallel training. We evaluate the efficacy of our approach on two large predictive modeling tabular data sets froni the Exascale computing ProjectCANcer distributed Learning Environment (ECP-CANDLE).

关键词： neural networks neural architecture search data-parallelism

来源：评论

学校读者我要写书评

暂无评论

PIOD: An Efficient parallel Iterative Algorithm for Solving Over-determined Equations

PIOD: An Efficient Parallel Iterative Algorithm for Solving ...

引用

international conference on parallel and distributed Systems (ICPADS)

作者： Min Tian Zhenguo Wei Yanlong Li Wei Du Lei Xiao Chaoshuai Xu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan Key Laboratory of High Performance Computing Jinan Institute of Supercomputing Technology

The solution of over-determined equations plays a very important role in fields such as data fitting, signal processing, and machine learning. It is of great significance in predicting natural phenomena, optimizing engineering design, and other fields. However, there is currently no efficient method to solve over-determined equations, either being not accurate enough or consuming a lot of time. In this article, we propose a parallel iterative method for solving over-determined equations, called the PIOD algorithm. By using a sub-convergence condition to terminate the iterative calculation, we have developed a task partitioning strategy for the algorithm and implemented parallelization of the solution of over-determined equations on a distributed memory system. Our proposed algorithm achieves an average speedup of 152 ×times compared to the open-source Eigen solver. Additionally, it also achieves a parallel efficiency of over 30%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Fault Warning Technology of Optical Network Based on Recurrent Neural Network

Research on Fault Warning Technology of Optical Network Base...

引用

Information Science, parallel and distributed Systems (ISPDS), international conference on

作者： Ganhong Cai Yinfa Zhang Xiaoyun Kuang Lu Zeng College of Information and Communication National University of Defense Technology Wuhan China Team 14 Unit 75842 of PLA Guangzhou China

ISBN: (数字)9798350352719

ISBN: (纸本)9798350352726

With the rapid development of cyber information system construction, optical networks, as a crucial component of the cyber information infrastructure, carry an increasing amount of data information and directly determine the performance of the network information system. The occurrence of faults in optical networks can severely impact various information transmissions; hence, fault warning and analysis are essential to ensure the stable and reliable operation of optical networks. Traditional fault warning and analysis of optical networks mainly rely on expert experience and network management system alarms, which have limitations such as long training cycles for backbone personnel, poor fault tolerance of network management systems, and long cycles for knowledge base construction. These limitations make it difficult to provide early warnings before faults occur in optical transmission networks, and the implementation of intelligent operation and maintenance of optical networks is challenging. Therefore, warning of optical network performance helps to accurately detect hidden dangers and determine fault causes before faults occur in optical transmission networks, and to prepare spare boards, fiber cores, and backbone forces in advance, minimizing repair time and achieving "zero" fault perception for users. This paper proposes an optical network fault warning model based on recurrent neural networks to achieve high-accuracy and intelligent response for optical network fault warnings.

关键词： Training Optical fibers Recurrent neural networks Optical computing Optical fiber networks Predictive models Maintenance engineering

来源：评论

学校读者我要写书评

暂无评论

Fourth international conference on Computer Technology, Information Engineering, and Electron Materials, CTIEEM 2024

Fourth International Conference on Computer Technology, Info...

引用

4th international conference on Computer Technology, Information Engineering, and Electron Materials, CTIEEM 2024

ISBN: (纸本)9781510689299

The proceedings contain 74 papers. The topics discussed include: research on fault analysis of EOS services based on OTN networks;elderly fall detection based on skeleton data using OpenPose;research on high slope deformation prediction model based on MEEMD-ARIMA;parallel computing method for base station radiation prediction range based on 3D triangulation mesh;research and application of wireless rechargeable sensor networks;design and simulation of FIR filter based on Modelsim-platform;early abnormal warning for fuel dispensers driven by data;U-Net network with fused attention mechanism for traffic flow prediction;design and optimization of a high-precision distributed wireless sensor network for dynamic seismic wave data acquisition;and research on cyber security attack and defense strategy simulation in a virtual network environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

2PGraph: Accelerating GNN Training over Large Graphs on GPU Clusters

2PGraph: Accelerating GNN Training over Large Graphs on GPU ...

引用

IEEE international conference on Cluster computing (Cluster)

作者： Zhang, Lizhi Lai, Zhiquan Li, Shengwei Tang, Yu Liu, Feng Li, Dongsheng Natl Univ Def Technol Natl Lab Parallel & Distributed Proc PDL Comp Coll Changsha Peoples R China

ISBN: (纸本)9781728196664

Graph neural networks (GNNs) have been emerging as powerful learning tools for unstructured data and successfully applied to many graph-based application domains. Sampling-based graph training is commonly used in existing GNN training frameworks to handle large-scale graphs. However, this type of approach is restricted by the problems of long memory accessing latency, neighborhood explosion during mini-batch sampling, and inefficient loading of vertex features from CPU to GPU. In this paper, we propose 2PGraph, a system that supports high-speed locality-aware mini-batch sampling and GNN layer-aware feature caching. 2PGraph significantly reduces sampling time by vertex-cluster sampling, which improves the locality of vertex access and limits the range of neighborhood expansion. To further reduce the sampling time in a distributed environment, we renumber the vertex numbers in subgraphs after graph partition, which improves the data locality of each partition. 2PGraph also avoids abundant data transfer between CPU and GPU through the feature data caching on available GPU resources with a hit rate of 100 %. Furthermore, 2PGraph develops a GNN layer-aware feature caching policy during data parallel training and achieves better cache efficiency and memory utilization. We evaluate 2PGraph against two state-of-the-art industrial GNN frameworks, i.e., PyG and DGL, on a diverse array of benchmarks. Experimental results show that 2PGraph reduces up to 90 % mini-batch sampling and 99 % data loading time, and achieves up to 8.7 x performance speedup over the state-of-the-art baselines on an 8-GPU cluster.

关键词： graph neural networks pipeline parallel data parallel sampling data caching

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Preimplantation Gene Regulation in Homo Sapiens and Mus Musculus Using Multi-Layer Perceptron-Based Neural networks

Comparative Analysis of Preimplantation Gene Regulation in H...

引用

international conference on parallel distributed and Grid computing (PDGC)

作者： Akshay Jain Gurupriya Takkar Deepak Modi Priyanka Narad Abhishek Sengupta Amity Institute of Biotechnology Amity University Uttar Pradesh India Molecular and Cellular Biology Laboratory National Institute for Research In Reproductive and Child Health Mumbai India Indian Council of Medical Research New Delhi India

ISBN: (数字)9798331521349

ISBN: (纸本)9798331521356

This study investigated gene expression changes during preimplantation embryo development in Homo sapiens and Mus musculus. RNA-sequencing data from 31 human and 42 mouse samples across various developmental stages (oocyte, zygote, 2-cell, 4-cell, 8-cell, and blastocyst) were analyzed to identify differentially expressed genes (DEGs). Intraspecies comparisons revealed no shared DEGs between humans and mice. A neural network model based on a multi-layer perceptron (MLP) was employed to prioritize the top 100 genes with significant expression changes. These genes were then mapped to orthologous counterparts between species, focusing on those with over 80% sequence identity and conserved gene order. Five essential genes were chosen for every stage of preimplantation the model yielded ROC-AUCs of 0.99 and 1.00, respectively, with average cross-validation scores of 0.83 for humans and 0.81 for mice. The model yielded ROC-AUCs of 0.99 and 1.00, respectively, with average cross-validation scores of 0.83 for humans and 0.81 for mice. This comparative study gives insights into conserved gene expression mechanisms governing early mammalian development across species, increasing our knowledge of the invaluable changes in preimplantation stages.

关键词： Neural networks Genomics Focusing Stem cells Epigenetics Solids Grid computing Mice Regulation Gene expression

来源：评论

学校读者我要写书评

暂无评论

Optimization Modeling and Simulation of Motion Monitoring based on Multi layer Perceptual Neural Network

Optimization Modeling and Simulation of Motion Monitoring ba...

引用

distributed computing and Electrical Circuits and Electronics (ICDCECE), IEEE international conference on

作者： Limin Zhang Kang Shao Yingjie Li Cong Liu Weifang Engineering Vocational College Weifang China Beihang University Beijing China

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

In order to solve the problems of signal noise interference, low accuracy of motion pattern recognition, and high real-time requirements in motion monitoring, an optimization method based on MLP (multi-layer perceptron) is used to improve the accuracy and real-time performance of the motion monitoring system. First, the signal preprocessing algorithms such as wavelet transform denoising and filtering are used to ensure the quality of input data. Then, combined with the MLP model, data parallel processing strategy and model pruning technology are adopted to ensure that the motion monitoring system can run efficiently under large-scale data input. In all 20 tests, the response time and processing delay of the lightweight model have a small fluctuation range, with a response time of 97~100 milliseconds and a processing delay of 104~107 milliseconds, providing a new technical path for the field of motion monitoring.

关键词： Accuracy Noise Optimization methods Interference Real-time systems Data models Delays Time factors Monitoring Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Scheduling Algorithm Based on Cloud computing

Research on Intelligent Scheduling Algorithm Based on Cloud ...

引用

international conference on Computer Research and Development (ICCRD)

作者： Xiaofeng Yan Jie Zhao Jianchao Han Chongqing Medical and Pharmaceutical College Chongqing China

With the rapid development of the information age, computer technology and network technology are more and more mature, and the application of Internet technology is more and more extensive. On the basis of the gradual development and maturity of distributed computing, parallel computing and grid computing, cloud computing based on big data came into being. The core idea of cloud computing is to connect a large number of computing resources, storage resources and service resources through the network to form a resource pool, and then conduct unified scheduling and management of resources according to user needs. This paper mainly studies the resource scheduling method based on neural network and genetic algorithm to dynamically provide data centric computing service system for users, and maximize the reliability, customization and security of the services provided.

关键词： Cloud computing Scheduling algorithms Heuristic algorithms Neural networks parallel processing Information age Grid computing

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 42 43 44 45 46 47 48 49 50 51 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：