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731-740 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：

Owl: Differential-Based Side-Channel Leakage Detection for CUDA Applications

Owl: Differential-Based Side-Channel Leakage Detection for C...

引用

international conference on Dependable Systems and networks (DSN)

作者： Yu Zhao Wenjie Xue Weijie Chen Weizhong Qiang Deqing Zou Hai Jin National Engineering Research Center for Big Data Technology and System Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Jinyinhu Laboratory Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350341058

ISBN: (纸本)9798350341065

Over the past decade, various methods for detecting side-channel leakage have been proposed and proven to be effective against CPU side-channel attacks. These methods are valuable in assisting developers to identify and patch side-channel vulnerabilities. Nevertheless, recent research has revealed the feasibility of exploiting side-channel vulnerabilities to steal sensitive information from GPU applications, which are beyond the reach of previous side-channel detection methods. Therefore, in this paper, we conduct an in-depth examination of various GPU features and present Owl, a novel side-channel detection tool targeting CUDA applications on NVIDIA GPUs. Owl is designed to detect and locate side-channel leakage in various types of CUDA applications. When tracking the execution of CUDA applications, we design a hierarchical tracing scheme and extend the A-DCFG (Attributed Dynamic Control Flow Graph) to address the massively parallel execution in CUDA, ensuring Owl's detection scalability. After completing the initial assessment and filtering, we conduct statistical tests on the differences in program traces to determine whether they are indeed caused by input variations, subsequently facilitating the positioning of side-channel leaks. We evaluate Owl's capability to detect side-channel leaks by testing it on Libgpucrypto, PyTorch, and nvJPEG. Meanwhile, we verify that our solution effectively handles a large number of threads. Owl has successfully identified hundreds of leaks within these applications. To the best of our knowledge, we are the first to implement side-channel leakage detection for general CUDA applications.

关键词： Target tracking Statistical analysis Filtering Scalability Graphics processing units Side-channel attacks Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Key technology research of distribution automation system based on cloud architecture 9

Key technology research of distribution automation system ba...

引用

9th China international conference on Electricity Distribution, CICED 2021

作者： Su, Biaolong Wu, Huichao Zhang, Yiran Zhou, Yanghao NARI Group Corporation State Grid Electric Power Research Institute China

ISBN: (纸本)9781728192291

China's economic development has higher requirements for the power supply capability and reliability of distribution network. At present, the management scope of distribution automation system cannot cover the whole distribution network and many regional electric companies cannot manage the operation state of distribution network through the existing distribution automation system, which restricts the development of distribution network construction. It is necessary to develop a new system construction scheme to cope with the different data capacity and function requirements of distribution networks in different cities. This paper proposes a technical scheme of main station of distribution automation system based on cloud architecture in aspects of system architecture, elastic data processing, safe access of distribution terminals and optimal operation control. With the distributed collaboration between core cloud and regional cloud as well as data fragmentation parallel processing technology, the problem of massive access and application of distribution network will be solved. © 2021 IEEE.

关键词： Cloud computing architecture

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

A Global Opinion-influencing Consensus Model based on the DeGroot

A Global Opinion-influencing Consensus Model based on the De...

引用

IEEE international Symposium on parallel and distributed Processing with Applications and IEEE international conference on Ubiquitous computing and Communications (ISPA/IUCC)

作者： Yuntian Zhang Xiaoliang Chen Zexia Huang Xianyong Li Yajun Du School of Computer and Software Engineering Xihua University Chengdu China College of Science Xihua University Chengdu China

Social networks have become an important platform for transmitting and sharing information due to the rapid development of online social networks. Opinion dynamics have been examined through the consensus-reaching process (CRP) in social networks, which aims to model the evolution of opinions in social networks so that agents can reach a consensus. Many researchers have solved the CRP problem by improving the DeGroot model, which models divide agents into two categories, leaders and followers, and change the network structure or the values of the agents’ opinions to bring the network to a consensus. However, all of them require the construction of leaders who can influence the entire network. Consensus cannot be achieved without the leaders. This paper proposes a global opinion-influencing consensus model (GOCM) to solve the CRP problem. A network agent refers not only to the opinion of its neighbors but also to the average opinion of the entire network. The numerical analysis indicates that our proposed GOCM can significantly accelerate the achievement of an expected consensus.

关键词： Analytical models Social networking (online) Numerical analysis Computational modeling Ubiquitous computing Numerical models

来源：评论

学校读者我要写书评

暂无评论

SCGraph: Accelerating Sample-based GNN Training by Staged Caching of Features on GPUs

SCGraph: Accelerating Sample-based GNN Training by Staged Ca...

引用

IEEE international conference on Big Data and Cloud computing (BdCloud)

作者： Yuqi He Zhiquan Lai Zhejiang Ran Lizhi Zhang Dongsheng Li National Key Laboratory of Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha China

Graph neural networks (GNNs) have been becoming important tools for processing structured graph data and successfully applied to multiple graph-based application scenarios. The existing GNN systems adopt sample-based training on large-scale graphs over multiple GPUs. Although they support large-scale graph training, large data loading overhead of transferring vertex features between CPUs and GPUs is still a bottleneck. In this work, we propose SCGraph, a method that supports GPU high-speed feature caching. SCGraph classifies the graph vertices sorted by out-degrees. For high out-degree vertices, SCGraph sets grading caches via different GPUs to increase the overall cache content through NVLink high-speed data transmission between them. For low out-degree vertices, SCGraph expands training vertices' neighborhood in advance to regenerate cache. We evaluate SCGraph against two state-of-the-art industrial GNN frameworks, i.e., DGL and PaGraph on various benchmarks. Experimental results show that SCGraph improves the cache hit rate over GPUs up to 23.6%, and achieves up to 1.71x performance speedup over the state-of-the-art baselines while the convergence almost constant.

关键词： Training Memory management Loading Graphics processing units Benchmark testing Graph neural networks Data communication

来源：评论

学校读者我要写书评

暂无评论

RIFFLE: A distributed Network Operating System with Re-configurability for Multiple Domains

RIFFLE: A Distributed Network Operating System with Re-confi...

引用

IEEE international Symposium on parallel and distributed Processing with Applications and IEEE international conference on Ubiquitous computing and Communications (ISPA/IUCC)

作者： Boyang Zhou Chunming Wu Shuangxi Chen Zhen Li Hong Fan Zhejiang Lab Intelligent Networks Institute Hangzhou China School of Intelligent Science and Technology Hangzhou Institute for Advanced Study UCAS Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China Jiaxing Key Laboratory of Industrial Internet Jiaxing China Research Center for Intelligent Technology Standardization Zhejiang Lab Hangzhou China Department of Electrical Engineering Shanghai University of Electric Power Shanghai China

The distributed network control in software-defined networking is greatly challenged by the design demands of evolving a running distributed control plane (DCP), and by the complexity of handling the control state dynamics. In this paper, we propose RIFFLE to address the problem using a distributed network operating system approach. RIFFLE enables the evolvability of control states of DCP deployed on a global scale. RIFFLE handles spatial and temporal dynamics that occur when updating and migrating the distributed control states, which overcomes the critical barrier to the evolvability. It fills the gap by enabling temporal reconfigurability in DCP. Moreover, RIFFLE reduces the complexities of building and maintaining network control services in DCP by enabling componentization and abstracting the underlying network dynamics. We evaluated the prototype RIFFLE through experiments running in PlanetLab. The results show that the prototype scales well for 135 nodes. We also validate that RIFFLE ensures the continuity and low content request delay for the supported the information-centric network supported during cache update periods owing to the enabled evolvability.

关键词： Runtime Roads Decentralized control Information-centric networking Prototypes Ubiquitous computing Dynamic scheduling

来源：评论

学校读者我要写书评

暂无评论

A Low-rate DDoS Strategy for Unknown Bottleneck Link Characteristics

A Low-rate DDoS Strategy for Unknown Bottleneck Link Charact...

引用

19th IEEE international conference on Pervasive computing and Communications (IEEE PerCom)

作者： Takahashi, Yuta Inamura, Hiroshi Nakamura, Yoshitaka Future Univ Hakodate Grad Sch Syst Informat Sci Hakodate Hokkaido Japan Future Univ Hakodate Sch Syst Informat Sci Hakodate Hokkaido Japan

ISBN: (纸本)9781665404242

Low-rate distributed Denial of Service (LDDoS) attacks degrade the quality of TCP links with low average traffic by exploiting vulnerabilities in the TCP/IP protocol and routing queue management mechanisms. The ideal transmission rate of the attack pulse in the most classical RTO-based LDDoS attacks (aka: Shrew attacks) is greater than or equal to the bandwidth of the target bottleneck link, and it is assumed that the attacker is able to set a suitably large transmission rate. However, the attacker does not always know the bandwidth of the target bottleneck link in real-world attack scenarios. In this paper, we propose a strategy for executing a low-rate shrew DDoS attack against a bottleneck link of unknown bandwidth and buffer size under a scenario targeting a residential network. The proposed attack strategy degrades downstream traffic from a specific service to the target network to the desired quality while keeping the attack traffic stealthy by exploratively increasing the pulse rate while estimating the attack effect by building bot nodes in the residential network.

关键词： Low-rate DDoS (LDDoS) attacks Sophisticated attacks strategy Residential networks Botnet

来源：评论

学校读者我要写书评

暂无评论

Investigating Scope of Energy Efficient Routing in Adhoc Network

Investigating Scope of Energy Efficient Routing in Adhoc Net...

引用

international conference on parallel distributed and Grid computing (PDGC)

作者： Vivek Veeraiah Rohit Anand Krishna Nand Mishra Dharmesh Dhabliya Supriya Sanjay Ajagekar Reshma Kanse Dept. of R & D Computer Science Adichunchanagiri University Mandya Karnataka India DSEU New Delhi India Dept. of CSE KMC Language University Lucknow Uttar Pradesh India Department of IT Vishwakarma Institute of Information Technology Pune Maharashtra India Bharati Vidyapeeth Deemed University Navi Mumbai India

ISBN: (纸本)9781665454025

Here the simulation of throughput of AODV is proposed with respect to DSDV and DSR. An Ad Hoc On-Demand Distance Vector (AODV) is a routing protocol. It has been designed for wireless and mobile ad hoc networks. The establishment of protocol has been made to destinations on demand and supports both uncast and multicast routing. Several researches are there which are made on AODV networking, are discussed here. In the environment of AODV, Destination Sequence number has been utilized in order to determine the freshness of routing information. In the research work, first of all, the setting of NSA has been made. The objective of work is to improve the throughput, end to end delivery ratio, packet delivery ratio of ADODV by providing energy efficiency. After that simulation of NS2 has been proposed over AODV network. In conventional network dropping of packets takes place. DSDV stands for Destination-Sequenced Distance-Vector Routing and DSR stands for Dynamic Source Routing. Proposed work would influence the throughput, packet dropping ratio, routing overhead and delivery ratio. Throughput of proposed work depends on the content replaced in packet and size of packet. It has been noticed that the proposed work though put would be at least 10% more as compare to Traditional transmission mechanism. Overall, the proposed work would be beneficial to provide energy efficient AODV network using NS2.

关键词： Wireless communication Routing Throughput Grid computing Energy efficiency Routing protocols AODV

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Ensure Security and Privacy While Using QR Code Scanning in Business Applications

A Novel Approach to Ensure Security and Privacy While Using ...

引用

international conference on parallel distributed and Grid computing (PDGC)

作者： Venkateswara Sarma Bhamidipati Raghavendra Sai Wvs ERP4SME Central Operations SAP Labs India Pvt. Ltd. Bangalore Karnataka India Business Networks Engineering SAP Labs India Pvt. Ltd. Bangalore Karnataka India

ISBN: (纸本)9781665454025

One of many challenges created by COVID-19 pandemic is to reduce need of contact. Quick Response (QR) codes offered a readily available solution to this challenge with offer to support contact less processes. Wide adaption of smart mobile devices like smart phones and tablets and huge number of mobile applications available in the respective application stores, which support QR code scanning acted as a catalyst in rapid adaption of QR codes to support contact less processes. Support of QR code-based processing rapidly increased during the pandemic, penetrated all processes like sales and marketing, authentication, and digital payments to name some. On one hand, this served the cause in terms of reducing contact, on other hand, factors like rapid adaption and using it in smart mobile devices, which are existing to cater to the larger purpose of human usage, scanning QR codes was not in that list to start with is bringing in the series of security issues which can arise starting from the human factor, software, misuse and hacking factors. This paper focuses on the QR code processes, differences in terms of security while using a smart device for QR codes when compared to the rugged device-based barcode scanners, the kind of security issues such process can encounter while using smart devises for QR code scanning, factors that must be considered by the applications development as well as the consumers of such functionality and the way to ensure security of consumers of such functionality.

关键词： COVID-19 Privacy Pandemics Process control QR codes Organizations Mobile handsets

来源：评论

学校读者我要写书评

暂无评论

CNN-MLP Based Prediction Model for Grading of Diabetic Retinopathy

CNN-MLP Based Prediction Model for Grading of Diabetic Retin...

引用

international conference on parallel distributed and Grid computing (PDGC)

作者： Praveen Modi Yugal Kumar Computer Science Engineering & Information Technology Jaypee University of Information Technology Waknaghat Solan Himachal Pradesh India

ISBN: (纸本)9781665454025

Diabetic Retinopathy ailment caused by the high glucose and blood pressure in the eye veins of human beings. An ophthalmologist performs the screening of eye-fundus image for diagnosis and detects the various lesions-venous beading, intraretinal micro-vascular abnormalities, Micro-aneurysms (MA), Neo-vascularization (NV), vitreous hemorrhage (VH), Cotton wool spots (CWS) etc. On the basis of detected lesions Ophthalmologists grade the DR severity into five classes-No-DR (0), Mild Non-Proliferative DR (NPDR) (1), Moderate (2), Severe (3) and Proliferative DR (4). In the medical image processing field-different neural network models and approaches to deep learning are suggested for the investigation of DR classification. This paper presents two stage model-Convolutional Neural Network (CNN) and MLP-Conv-NIN (Network-in-Network) to identify the various lesions. CNN model is used to reduce the dimensions and extract the various features of input fundus images. The relevant features are fed into MLP-Conv-NIN model which absorbs the non-linear features, to identify the various lesions present in the fundus images. Various sizes of filter variations and rectified linear unit (RELU) activation function are also applied in the proposed model to gain the more performance and analyze the responses. The performance of proposed model is analyzed using publicly available fundus image dataset-three hundred and thirty two images, by calculating accuracy, specificity, sensitivity and weighted kappa-score, which compares the score supplied in the dataset with the projected value. The proposed model achieves accuracy (87.34%), sensitivity (93.18%), specificity (75.89%), and kappa-score (0.81).

关键词： Analytical models Sensitivity Retinopathy Veins Neural networks Feature extraction Diabetes

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 << < 70 71 72 73 74 75 76 77 78 79 > >>

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：