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

1,417 篇 会议
44 册 图书
28 篇 期刊文献

馆藏范围

1,489 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

972 篇 工学
- 891 篇 计算机科学与技术...
- 487 篇 软件工程
- 377 篇 信息与通信工程
- 114 篇 电气工程
- 89 篇 控制科学与工程
- 39 篇 电子科学与技术（可...
- 31 篇 生物工程
- 28 篇 动力工程及工程热...
- 21 篇 机械工程
- 20 篇 仪器科学与技术
- 19 篇 生物医学工程（可授...
- 18 篇 网络空间安全
- 16 篇 环境科学与工程（可...
- 15 篇 建筑学
- 10 篇 安全科学与工程
- 8 篇 化学工程与技术
218 篇 管理学
- 164 篇 管理科学与工程(可...
- 78 篇 工商管理
- 75 篇 图书情报与档案管...
203 篇 理学
- 124 篇 数学
- 43 篇 系统科学
- 34 篇 生物学
- 25 篇 统计学（可授理学、...
- 24 篇 物理学
- 11 篇 化学
18 篇 法学
- 14 篇 社会学
10 篇 经济学
- 10 篇 应用经济学
10 篇 医学
- 10 篇 临床医学
- 8 篇 基础医学(可授医学...
9 篇 教育学
- 9 篇 教育学
2 篇 军事学
1 篇 农学

主题

112 篇 distributed comp...
92 篇 distributed comp...
55 篇 computer science
55 篇 cloud computing
50 篇 application soft...
48 篇 peer to peer com...
44 篇 computer network...
41 篇 computer archite...
41 篇 mobile computing
40 篇 conferences
40 篇 costs
40 篇 middleware
35 篇 protocols
33 篇 quality of servi...
33 篇 computational mo...
30 篇 software enginee...
30 篇 bandwidth
29 篇 internet
29 篇 hardware
28 篇 resource managem...

机构

6 篇 college of compu...
5 篇 seikei universit...
5 篇 ibm thomas j. wa...
5 篇 inria rennes
5 篇 3-30-1 wajiro-hi...
4 篇 nanyang technol ...
4 篇 universidad carl...
4 篇 tokyo denki univ...
4 篇 rissho universit...
4 篇 school of electr...
3 篇 college of compu...
3 篇 school of big da...
3 篇 department of co...
3 篇 zhejiang univers...
3 篇 department of co...
3 篇 school of cybers...
3 篇 ohio state univ ...
3 篇 university of pi...
3 篇 tennessee tech u...
3 篇 rwth aachen univ...

作者

8 篇 michael alexande...
6 篇 stephen l. scott
6 篇 barolli leonard
6 篇 mario cannataro
6 篇 takizawa makoto
4 篇 xhafa fatos
4 篇 alexandru costan
4 篇 liu yh
4 篇 emmanuel jeannot
4 篇 shibata yoshitak...
4 篇 marco danelutto
4 篇 uehara minoru
4 篇 mikkilineni rao
4 篇 r. guerraoui
4 篇 beniamino martin...
4 篇 josef weidendorf...
4 篇 durresi arjan
3 篇 li zengxiang
3 篇 alfredo cuzzocre...
3 篇 m. takizawa

语言

1,481 篇 英文
5 篇 其他
2 篇 俄文
1 篇 中文

检索条件"任意字段=Proceedings - 24th International Conference on Distributed Computing Systems Workshops"

共 1489 条记录，以下是171-180 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：

Optimal Trajectory Planning and Task Assignment for UAV-assisted Fog computing

Optimal Trajectory Planning and Task Assignment for UAV-assi...

引用

IEEE international conference on High Performance computing and Communications (HPCC)

作者： Shuaijun Liu Jiaying Yin Zishu Zeng Jingjin Wu Department of Statistics and Data Science BNU-HKBU United International College Zhuhai China Li Ka Shing Faculty of Medicine The University of Hong Kong Pokfulam Hong Kong SAR China School of Engineering The Hong Kong University of Science and Technology Kowloon Hong Kong SAR China Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science

Fog computing is an emerging distributed computing model for the realization of the Internet of things (IoT). It extends computing and caching functions to the edge of wireless networks. Unmanned Aerial Vehicles (UAVs) provide effective support for fog computing, as UAVs can not only act as a relay between mobile users and physically remote edge devices to avoid costly long-range wireless communications, but also are equipped with computing facilities that can take over certain tasks. In this paper, we aim to optimize the energy efficiency of a fog computing system assisted by a single UAV, by planning the trajectories of the UAV and assigning computing tasks to different devices including the UAV itself. We propose two algorithms based on the classical Ant Colony and Particle Swarm Optimization techniques, and solve the problem by continuous convex approximation. Different from most existing studies where the trajectories are assumed to be straight lines, we account for the effect of obstacles, such as buildings, and deliberately avoid them during the trajectory planning phase. We demonstrate, through extensive simulation experiments, that our proposed approach can achieve significantly better energy efficiency compared to existing benchmark algorithms.

关键词： Trajectory planning Computational modeling Wireless networks Autonomous aerial vehicles Energy efficiency Trajectory Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Bayesian Approach for Fault Diagnosis in an Irrigation Canal 24

A Bayesian Approach for Fault Diagnosis in an Irrigation Can...

引用

24th international conference on System theory, Control and computing (ICSTCC)

作者： Lami, Youness Lefevre, Laurent Lagreze, Andre Genon-Catalot, Denis Univ Grenoble Alpes Grenoble INP LCIS F-26000 Valence France

ISBN: (纸本)9781728198095

In this paper, we present a fault diagnosis approach based on a probabilistic model, more specifically a Bayesian one, while relying on a distributed Multi-Agent systems paradigm. First, a networked control water system benchmark is introduced, then a Bayesian approach for fault diagnosis is provided where inference and time dependencies between operating modes of systems are tackled. It is suggested that a Multi-Agent System, where entities interact and cooperate in a distributed architecture while expressing subjective knowledge of the system, is relevant regarding fault handling and offers more flexibility in the implementation and data collection.

关键词： Fault Detection and Diagnosis Water systems Probabilistic Models Bayesian Methods distributed Approaches Multi-Agent systems

来源：评论

学校读者我要写书评

暂无评论

the Influence-Maximizing Node Selection Algorithm Based on Local Isolated Centrality in Large-scale networks Implemented by distributed Graph computing

The Influence-Maximizing Node Selection Algorithm Based on L...

引用

IEEE international conference on High Performance computing and Communications (HPCC)

作者： Piaoyang Chen Rong Lei Mingsen Deng School of Information Guizhou University of Finance and Economics Guiyang China

Identifying influence-maximizing (IM) nodes is an effective strategy for designing efficient communication networks or contain the spreading of information for rumors and epidemics with limited budgets. With the growing of the sizes of the social networks, finding solutions to the problem of intfuence − maximizing vertices becomes more and more challenging. Tra-ditionally, the number of users finally affected was the focus. However, the information diffusion speed was becoming a bottle-neck of IM problems. In this paper, we proposed a locality-aware vertex selection strategy based on local isolation centrality (LIC), while the information diffusion experiments used the Independent Cascade (IC) model. the computing scheme was implemented by a distributed graph computing framework. the superiority of the LIC algorithm was confirmed by evaluated on three real-world datasets. It was indistinguishable from algorithms such as K-shell, H-index, degree centrality (DC), local centrality (LC), and VoteRank at the diffusion cascade scale. But it showed better superiority in diffusion speed. More importantly, by comparing LIC with the VoteRank algorithm, which was the closest algorithm on diffusion speed to that of LIC, the huge advantage of the LIC algorithm in terms of time cost was found. We believe that the locality-aware LIC algorithm was more suitable for the influence-maximization problem in very large-scale social networks.

关键词： Epidemics Costs Social networking (online) Computational modeling Communication networks Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Hybrid Parameter Update: Alleviating Imbalance Impacts for distributed Deep Learning

Hybrid Parameter Update: Alleviating Imbalance Impacts for D...

引用

IEEE international conference on High Performance computing and Communications (HPCC)

作者： Hongliang Li Dong Xu Zhewen Xu Xiang Li College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Changchun China

Nowadays, data parallelism has been widely applied to train large datasets on distributed deep learning clusters, but it has suffered from costly global parameter updates at batch barriers. Performance imbalance among worker instances, introduced by uneven workload partitioning or biased resource allocation, can cause straggly workers, which can lead to severe impacts on both training speed and result accuracy. this paper studies the issue focusing on the tradeoff between training speed and result accuracy. We propose Cooperate Grouping Parallel (CGP), a hybrid parameter update solution that allows the flexibility of both synchronous and asynchronous update schemes. We introduce a novel Cooperate Worker Grouping Problem (CWGP) that seeks a task grouping configuration that leads to maximum model accuracy and holds customized training speed guarantees. We propose an evolution-based Pareto local searching algorithm to compute efficient worker grouping configurations. Comprehensive evaluation results are presented to demonstrate the effectiveness of CGP under both persistent and fluctuant imbalances. the proposed method alleviates the imbalance impacts without introducing extra adjustment over-heads.

关键词： Training Deep learning Computational modeling Focusing distributed databases Parallel processing Resource management

来源：评论

学校读者我要写书评

暂无评论

AI Surrogate Model for distributed computing Workloads 24

AI Surrogate Model for Distributed Computing Workloads

引用

proceedings of the SC '24 workshops of the international conference on High Performance computing, Network, Storage, and Analysis

作者： David K. Park Yihui Ren Ozgur O. Kilic Tatiana Korchuganova Sairam Sri Vatsavai Joseph Boudreau Tasnuva Chowdhury Shengyu Feng Raees Khan Jaehyung Kim Scott Klasky Tadashi Maeno Paul Nilsson Verena Ingrid Martinez Outschoorn Norbert Podhorszki Frederic Suter Wei Yang Yiming Yang Shinjae Yoo Alexei Klimentov Adolfy Hoisie Brookhaven National Laboratory Upton NY USA University of Pittsburgh Pittsburgh PA USA Carnegie Mellon University Pittsburgh PA USA Oak Ridge National Laboratory Oak Ridge TN USA University of Massachusetts Amherst MA USA SLAC National Accelerator Laboratory Menlo Park CA USA

ISBN: (纸本)9798350355543

Large-scale international scientific collaborations, such as ATLAS, Belle II, CMS, and DUNE, generate vast volumes of data. these experiments necessitate substantial computational power for varied tasks, including structured data processing, Monte Carlo simulations, and end-user analysis. Centralized workflow and data management systems are employed to handle these demands, but current decision-making processes for data placement and payload allocation are often heuristic and disjointed. this optimization challenge potentially could be addressed using contemporary machine learning methods, such as reinforcement learning, which, in turn, require access to extensive data and an interactive environment. Instead, we propose a generative surrogate modeling approach to address the lack of training data and concerns about privacy preservation. We have collected and processed real-world job submission records, totaling more than two million jobs through 150 days, and applied four generative models for tabular data---TVAE, CTAGGAN+, SMOTE, and TabDDPM---to these datasets, thoroughly evaluating their performance. Along with measuring the discrepancy among feature-wise distributions separately, we also evaluate pair-wise feature correlations, distance to closest record, and responses to pre-trained models. Our experiments indicate that SMOTE and TabDDPM can generate similar tabular data, almost indistinguishable from the ground truth. Yet, as a non-learning method, SMOTE ranks the lowest in privacy preservation. As a result, we conclude that the probabilistic-diffusion-model-based TabDDPM is the most suitable generative model for managing job record data.

关键词： AI-based Performance Modeling

来源：评论

学校读者我要写书评

暂无评论

ReSLB: Load Balanced Workflow for distributed Deep Learning Mass Spectrometry Database

ReSLB: Load Balanced Workflow for Distributed Deep Learning ...

引用

IEEE international conference on High Performance computing and Communications (HPCC)

作者： Li Mocheng Liu Yang Ou Yang Chen Zhiguang Xiao Nong Chen Tao Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China School of Computer Sun Yat-sen University Guangzhou China State Key Laboratory of Proteomics Beijing Proteome Research Center National Center for Protein Sciences(Beijing) Beijing Institute of Lifeomics Beijing China

the proteomics data analysis pipeline based on the shotgun method requires efficient data processing methods. the parallel algorithm of mass spectrometry database search faces the problems of rapidly expanding database size but low scalability. the heterogeneous database search algorithm based on deep learning is an effective way to solve this problem. Still, the deep learning-based distributed parallel database search algorithm is lacking. this paper analyzes the database searching computational load using a neural network and designs ReSLB, a workflow for the restricted search of mass spectrometry data based on GPU cluster and neural network scoring algorithm. this work aims to ensure the high scalability of future deep learning-based mass spectrometry distributed databases. In the performance estimation of 256 GPUs, the load imbalance of less than 30% and the parallel efficiency of 60% are achieved. Compared with state-of-the-art, the time cost is reduced by 75%, and the parallel efficiency from 1 to 256 GPUs is 3.6x higher than that.

关键词： Deep learning Scalability Neural networks Data preprocessing distributed databases Graphics processing units Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Aware: Adaptive distributed Training with Computation, Communication and Position Awareness for Deep Learning Model

Aware: Adaptive Distributed Training with Computation, Commu...

引用

IEEE international conference on High Performance computing and Communications (HPCC)

作者： Yan Zeng Guangzheng Yi Yuyu Yin Jiyang Wu Meiting Xue Jilin Zhang Jian Wan Yunquan Zhang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China School of Cyberspace Hangzhou Dianzi University Hangzhou China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China

the accuracy of the neural networks can usually be improved by increasing the size of the dataset and the layers or operators of the network, as it has strong composability. But, it makes a challenge to train these models efficiently, due to the limited resources of a single device, such as memory, computational resource and so on. For this challenge, it has become an inevitable trend to automatically implement model parallelism across multiple devices. this paper proposes Aware, an adaptive distributed parallel training method, to search distributed parallel strategy automatically for deep learning model. It firstly proposes an operator fusion strategy with computation and communication awareness to simplify the computational graph of deep learning model. And then, it introduces position-aware graph embedding algorithm to extract the structural features of models, which can make the searched parallel strategies to transplant to other networks with similar structures. On this basis, we use reinforcement learning algorithm to search distributed parallel strategy automatically. this paper makes experiments with neural networks such as Inception V3, NMT, GNM, NasNet and ResNet, and uses CIFAR10 and PTB datasets to compare the two methods of Hierarchical and Placeto. the results show that compared with Placeto, Aware achieves up to 5% reductions in runtime. Aware achieves more than 8% reductions in runtime compared with Hierarchical. Moreover, it has better transplantation and generalization capabilities, and supports pre-training for large-scale network parallel strategy search and accelerates convergence.

关键词： Deep learning Training Adaptation models Runtime Computational modeling Neural networks Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

PRKP: A Parallel Randomized Iterative Algorithm for Solving Linear systems

PRKP: A Parallel Randomized Iterative Algorithm for Solving ...

引用

IEEE international conference on High Performance computing and Communications (HPCC)

作者： Junjie Wang Min Tian Yinglong Wang Guoping He Tao Liu School of Mathematics and Statistics Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China

this paper proposes a distributed-memory parallel randomized iterative algorithm for solving linear systems, called the parallel randomized kaczmarz projection (PRKP) algorithm. the algorithm has the property of greedy sampling, alternating projection, and lazy approximation. We derive the alternating projection process from the Randomized Kaczmarz algorithm and develop the greedy sampling and lazy approximation process to improve the convergence rate and reduce the per-process communication volume. Moreover, we develop a sampling residual estimation scheme for our proposed algorithm, which greatly reduces the extra computation cost required to obtain residuals. Our experimental results show that the proposed algorithm significantly outperforms previous parallel iterative algorithms on overdetermined linear systems, and yields up to $\mathbf{159}\times$ and $\mathbf{384}\times$ speedups on average respectively compared to the leading pipelined CG and pipelined GMRES algorithms.

关键词： Linear systems Costs Processor scheduling Estimation Approximation algorithms Scheduling Iterative algorithms

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Querying and Injection of Process Fragments in Process-Aware Information systems 24

Context-Aware Querying and Injection of Process Fragments in...

引用

24th IEEE international Enterprise distributed Object computing conference (IEEE EDOC)

作者： Kammerer, Klaus Pryss, Ruediger Reichert, Manfred Ulm Univ Inst Databases & Informat Syst Ulm Germany Univ Wurzburg Inst Clin Epidemiol & Biometry Wurzburg Germany

ISBN: (纸本)9781728164731

Cyber-physical systems (CPS) are often customized to meet customer needs and, hence, exhibit a large number of hard-/software configuration variants. Consequently, the processes deployed on a CPS need to be configured to the respective CPS variant. this includes both configuration at design time (i.e., before deploying the implemented processes on the CPS) and runtime configuration taking the current context of the CPS into account. Such runtime process configuration is by far not trivial, e.g., alternative process fragments may have to be selected at certain points during process execution of which one fragment is then dynamically applied to the process at hand. Contemporary approaches focus on the design time configuration of processes, while neglecting runtime configuration to cope with process variability. In this paper, a generic approach enabling context-aware process configuration at runtime is presented. With the Process Query Language process fragments can be flexibly selected from a process repository, and then be dynamically injected into running process instances depending on the respective contextual situations. the latter can be automatically derived from context factors, e.g., sensor data or configuration parameters of the given CPS. Altogether, the presented approach allows for a flexible configuration and late composition of process instances at runtime, as required in many application domains and scenarios.

关键词： context-awareness process injection dynamic process change

来源：评论

学校读者我要写书评

暂无评论

proceedings - 2018 IEEE 24th international conference on Embedded and Real-Time computing systems and Applications, RTCSA 2018

Proceedings - 2018 IEEE 24th International Conference on Emb...

引用

24th IEEE international conference on Embedded and Real-Time computing systems and Applications, RTCSA 2018

ISBN: (纸本)9781538677599

the proceedings contain 35 papers. the topics discussed include: DeepPicar: a low-cost deep neural network-based autonomous car;a case study of cyber-physical system design: autonomous pick-and-place robot;write-aware data allocation on heterogeneous memory architecture with minimum cost;AirTight: a resilient wireless communication protocol for mixed-criticality systems;parameterized data reduction framework of thermal sensing for gait velocity measurements;an adaptive computation framework of distributed deep learning models for Internet-of-things applications;and phase-based profiling and performance prediction with timing approximate simulators.

关键词：

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149页 << < 14 15 16 17 18 19 20 21 22 23 > >>

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：