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

889 篇 会议
11 篇 期刊文献

馆藏范围

900 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

487 篇 工学
- 369 篇 计算机科学与技术...
- 348 篇 电气工程
- 212 篇 信息与通信工程
- 92 篇 软件工程
- 21 篇 控制科学与工程
- 14 篇 电子科学与技术（可...
- 12 篇 生物工程
- 11 篇 生物医学工程（可授...
- 9 篇 机械工程
- 8 篇 光学工程
- 6 篇 土木工程
- 6 篇 网络空间安全
- 5 篇 动力工程及工程热...
- 5 篇 航空宇航科学与技...
- 4 篇 建筑学
- 3 篇 力学（可授工学、理...
- 3 篇 石油与天然气工程
- 3 篇 交通运输工程
- 2 篇 水利工程
57 篇 理学
- 36 篇 数学
- 13 篇 物理学
- 13 篇 生物学
- 10 篇 统计学（可授理学、...
35 篇 管理学
- 31 篇 管理科学与工程(可...
- 12 篇 工商管理
- 7 篇 图书情报与档案管...
11 篇 教育学
- 11 篇 教育学
5 篇 法学
- 5 篇 社会学
4 篇 医学
- 3 篇 基础医学(可授医学...
2 篇 经济学
- 2 篇 应用经济学
1 篇 军事学

主题

112 篇 computer network...
73 篇 wireless sensor ...
50 篇 wireless network...
40 篇 throughput
39 篇 bandwidth
38 篇 telecommunicatio...
33 篇 protocols
31 篇 computer science
31 篇 neural networks
31 篇 delay
29 篇 routing
29 篇 computer archite...
28 篇 routing protocol...
27 篇 ad hoc networks
27 篇 quality of servi...
26 篇 costs
24 篇 ip networks
23 篇 traffic control
23 篇 network topology
21 篇 conferences

机构

5 篇 department of co...
4 篇 univ hong kong d...
4 篇 xidian univ stat...
4 篇 tsinghua univ de...
4 篇 institute of com...
4 篇 graduate school ...
4 篇 univ texas austi...
3 篇 univ sci & techn...
3 篇 univ calif river...
3 篇 univ politecnica...
3 篇 tsinghua univ de...
3 篇 univ sci & techn...
3 篇 univ wisconsin m...
3 篇 school of comput...
3 篇 univ calif los a...
3 篇 iit dept comp sc...
3 篇 politecnico di t...
3 篇 tsinghua nationa...
3 篇 tsinghua univ in...
3 篇 imdea networks i...

作者

4 篇 steinmetz ralf
4 篇 ralf steinmetz
3 篇 muntean gabriel-...
3 篇 li xin
3 篇 jayasumana anura...
3 篇 boukerche azzedi...
3 篇 li yong
3 篇 hollick matthias
3 篇 matthias hollick
3 篇 farid naït-abdes...
3 篇 wan peng-jun
3 篇 li xiaoming
3 篇 azzedine boukerc...
3 篇 hossam hassanein
3 篇 leonardi emilio
3 篇 wang xinbing
3 篇 libman lavy
3 篇 anura p. jayasum...
3 篇 wei yang
3 篇 lavy libman

语言

895 篇 英文
5 篇 其他

检索条件"任意字段=IEEE 34th Conference on Local Computer Networks"

共 900 条记录，以下是11-20 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：

Contrastive Graph Convolutional networks with Degree-specific Augmentation 34

Contrastive Graph Convolutional Networks with Degree-specifi...

引用

34th ieee International conference on Tools with Artificial Intelligence (ICTAI)

作者： Cheng, Jiahou Yan, Hui Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9798350397444

In recent years, Graph Convolutional networks (GCNs) have achieved tremendous success on semi-supervised tasks by effectively gathering local features for nodes. However, we find that the classification performance of nodes with different degrees on GCNs varies greatly: a considerable number of low-degree nodes perform poorly due to a lack of information, while high-degree nodes receive more noise due to their large receptive fields, resulting in suboptimal performance. Graph Convolutional Network (GCN) is widely used as an encoder in graph contrastive learning models, yet a large number of low-degree nodes are generated during crucial graph augmentation, resulting in suboptimal performance. To this end, we propose a novel graph contrastive representation learning method with degree-specific augmentation, which incorporates various priors for topological and semantic aspects of the graph. Specifically, on the topological level, we design a degree-specific augmentation scheme to expand the receptive field of low-degree nodes and reduce the noise received by high-degree nodes. On the node attribute level, we comprehensively consider node degree and feature variance to force the model to recognize the underlying semantic information. We jointly utilize supervised and unsupervised contrastive losses to improve model performance. Compared with other advanced methods, the experimental results on various real datasets strongly verify the effectiveness of our method.

关键词： Contrastive learning Graph Convolutional networks Degree-specific Augmentation

来源：评论

学校读者我要写书评

暂无评论

A novel fuzzy-based MOPSO algorithm for identifying clusters from complex networks 34

A novel fuzzy-based MOPSO algorithm for identifying clusters...

引用

34th ieee International conference on Tools with Artificial Intelligence (ICTAI)

作者： Yang, Yue Su, Xiaorui Zhao, Bowei He, Yizhou Hu, Lun Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan 430070 Peoples R China Chinese Acad Sci Xinjiang Tech Inst Phys & Chem Urumqi 830000 Peoples R China

ISBN: (纸本)9798350397444

Many complicated systems can be modeled as complex networks, and a variety of graph clustering algorithms have been proposed to perform accurate clustering analysis for better understanding system behaviors. However, most of them suffer the disadvantage of slow convergence. In this paper, we incorporate multi-objective particle swarm optimization (MOPSO) into a well-established fuzzy clustering algorithm, i.e., FCAN, and propose an improved Fuzzy-based Graph Clustering Algorithm, namely IMFCAN, which retains all the benefits gained with FCAN while achieving significantly fast convergence rate. Specially, IMFCAN enhances the ability of handling the imbalance observed in the distribution of fuzzy membership of nodes by introducing an instance-frequency-weighted regularization (IR) scheme. After that, IMFCAN develops an effective solution to reach a consensus optimization among them by balancing global exploration and local exploitation abilities of particles. Experimental results on four practical datasets demonstrate that IMFCAN performs better than several state-of-the-art clustering algorithm in terms of accuracy and convergence. Hence, IMFCAN is a promising algorithm for addressing the clustering analysis of complex networks.

关键词： Complex network graph clustering fuzzy membership multi-objective particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Multitask Learning Neural networks for Pandemic Prediction with Public Stance Enhancement 34

Multitask Learning Neural Networks for Pandemic Prediction w...

引用

34th ieee International conference on Tools with Artificial Intelligence (ICTAI)

作者： Zhang, Zhong Xie, Feng Zhao, Xuechen Zhou, Bin Chen, Jian Tian, Lei Natl Univ Def Technol Sch Comp Changsha Peoples R China Natl Univ Def Technol Key Lab Software Engn Complex Syst Changsha Peoples R China

ISBN: (纸本)9798350397444

State and local governments have imposed health policies to contain the spread of COVID-19 since it had a serious impact on human daily life. However, the public stance on these measures may be time-varying. It is likely to escalate the infection in the area where the public is negative or resistant. To take advantage of the correlation between public stance on health policies and the COVID-19 statistics, we propose a novel framework, Multitask Learning Neural networks for Pandemic Prediction with Public Stance Enhancement (MP3), which is composed of three modules: (1) Stance awareness module to make stance detection on health policies from users' tweets in social media and convert them into a stance time series. (2) Temporal feature extraction module that applies Convolution Neural Network and Recurrent Neural Network to extract and fuse local patterns and long-term correlations from COVID-19 statistics. Moreover, a Stance Latency-aware Attention is proposed to capture dynamic social effects and fuse them with temporal features. (3) Multitask prediction module to adopt Graph Convolution Network to model the spread of pandemic and employ multi-task learning to simultaneously predict COVID-19 statistics and the trend of public stance on health policies. the proposed framework outperforms state-of-the-art baselines on both confirmed cases and deaths prediction tasks.

关键词： epidemic prediction social media mining stance detection time series

来源：评论

学校读者我要写书评

暂无评论

Using Semeru Cloud Compiler to Enhance Cloud-Native Java Application Performance 34

Using Semeru Cloud Compiler to Enhance Cloud-Native Java App...

引用

34th Annual International conference on Collaborative Advances in Software and Computing, CASCON 2024

作者： Liu, Ryan Shinde, Shreya Tahvildari, Ladan Stoodley, Mark Sundaresan, Vijay Pirvu, Marius University of Waterloo Dept. of Electrical and Computer Engineering Canada IBM Canada

ISBN: (纸本)9798331504830

Java-based applications rely on just-in-time (JIT) compilation to convert bytecode into machine code at run-time to improve throughput. However, JIT compilation is achieved at the cost of additional CPU cycles and memory. In the context of modern cloud, where applications have limited computing resources due to containerization, JIT compilation may potentially become a pain-point. the Semeru Cloud Compiler (SCC) is a promising solution that offloads JIT compilation to a remote cloud compiler to reduce the local overhead of JIT compilation in containers. In this paper, we outline novel research directions to further leverage the advantages of remote cloud compilation by extending the SCC to achieve two goals: (i) reduce application start-up time and (ii) improve JIT compilation decision making. To reduce application start-up time, the proposed enhancement is to extract unused or unlikely to be used Java class files from container images. the SCC can still provide the extracted class files to the client JVM if any turn out to be needed. Our preliminary experiments show that this approach can potentially reduce container image sizes by up to 22.1% and start-up times by up to 9.2% for certain applications. To reduce JIT compilation overhead, the proposed enhancement is to perform dynamic analysis of the Java application using the additional resources on the server-side. In turn, the remote JIT compilation can make more informed decisions regarding which methods to compile and optimizations to apply. We are also developing a novel visualization tool designed to help JIT compiler developers identify pain points in current JIT compilation heuristics. Specifically, we have measured that up to 18.9% of JIT compilations for certain applications may be sub-optimal due to later method inlining, and we are investigating how the SCC could help to avoid these potentially wasted compile-time computations by using information learned from other JVM clients. © 2024 ieee.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

Synchronization of Fractional-Order Quaternion-Valued Coupled Neural networks via Hybrid Control Approach 34

Synchronization of Fractional-Order Quaternion-Valued Couple...

引用

34th Chinese Control and Decision conference (CCDC)

作者： Zheng, Bibo Wang, Zhanshan Wang, Shuran Northeastern Univ Sch Informat Sci & Engn Shenyang 110004 Peoples R China

ISBN: (纸本)9781665478960

Without separating the fractional-order quaternion-valued coupled neural networks (FQVCNNs) into four real-valued systems, synchronization for FQVCNNs is investigated in this paper. Firstly, a hybrid control approach including internal drive and external control is considered. To be specific, based on local information of the nodes' dynamics, edge-based fractional-order adaptive technique for coupling weights and adaptive feedback controllers are simultaneously applied to synchronize the FQVCNNs to the desired trajectory. Particularly, some new analytical approaches for fractional-order adaptive schemes, including the method of contradiction, the Mean Value theorem are developed to establish synchronization criteria of the network system. Finally, a numerical simulation is provided to illustrate the validity of theoretical results.

关键词： Quaternion-valued coupled neural network Fractional-order Synchronization and Adaptive strategy

来源：评论

学校读者我要写书评

暂无评论

Object-Contextual Representations for PointNet 34

Object-Contextual Representations for PointNet

引用

34th Chinese Control and Decision conference (CCDC)

作者： Dong, Jinyang Wang, Wenwu Zhu, Lei Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430080 Peoples R China

ISBN: (纸本)9781665478960

the classical network PointNet has achieved good results in classification and part segmentation for point clouds, but poor semantic segmentation results it gets with ignoring the context information of the point clouds in large scenes. In this paper, we present a simple approach, called object-contextual representations, characterizing a point by exploiting the representation of the corresponding object class. Firstly, object regions under the supervision of the ground truth are got by learning. Secondly, we compute the object region representation by aggregating the representations of the points lying in the object region. Last, the relation between each point and each object region are computed, and the representation of each point is augmented with the object-contextual representation, which is a weighted aggregation of all the object region representations. Furthermore, we adopt APNB module which leverages a pyramid sampling module into the non-local block to largely reduce the computation and memory consumption without sacrificing the performance. We believe that this method has strong versatility, and can also improve the performance with other popular networks.

关键词： semantic segmentation non-local block pyramid sampling

来源：评论

学校读者我要写书评

暂无评论

MI Classification based on locally Linear Embedding and One-dimensional Simplified Convolutional Neural Network 34

MI Classification based on Locally Linear Embedding and One-...

引用

34th Chinese Control and Decision conference (CCDC)

作者： Xu, Lei Wei, Li Xu, Youyun Nanjing Univ Posts & Telecommun Natl Engn Res Ctr Commun Networking Nanjing 210003 Peoples R China

ISBN: (纸本)9781665478960

Motor imagery (MI) electroencephalogram (EEG) signals are extensively used in brain-computer interface (BCI) systems, and it is considered as a promising cognitive tool for the rehabilitation of movement disorders. Due to the limited dataset of MI, the complex neural networks fed by the MI data are prone to overfitting. However, the feature extraction capability of simple neural networks is limited. therefore, this paper combines the locally linear embedding (LLE) of unsupervised learning and one-dimensional simplified neural network (1DSCNN). locally linear embedding is used for dimensionality reduction of MI signals. then the features are sent to the 1DSCNN for MI classification. Using dataset III from BCI competition II, the experimental results show that the proposed method achieves accuracy as high as 98.21%. Compared with other algorithms, it can improve the recognition rate of EEG by 6-13% on average in BCI competition IV dataset 2b, with shorter training time.

关键词： Brain computer Interface Motor Imagery locally Linear Embedding and Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

EG-KGR: A Knowledge Graph Reasoning Model Based on Enhanced Graph Sample and Aggregate Inductive Learning Algorithm 34

EG-KGR: A Knowledge Graph Reasoning Model Based on Enhanced ...

引用

34th ieee International conference on Tools with Artificial Intelligence (ICTAI)

作者： Wu, Yuejia Zhou, Jian-tao Inner Mongolia Univ Coll Comp Sci Hohhot Peoples R China Minist Educ Mongolian Engn Res Ctr Ecol Big Data Natl & Local Joint Engn Res Ctr Intelligent Infor Hohhot Peoples R China Inner Mongolia Engn Lab Cloud Comp & Serv Softwar Hohhot Peoples R China Inner Mongolia Key Lab Social Comp & Data Proc Hohhot Peoples R China Inner Mongolia Key Lab Discipline Inspect & Super Hohhot Peoples R China Inner Mongolia Engn Lab Big Data Anal Technol Hohhot Peoples R China

ISBN: (纸本)9798350397444

Knowledge Graph is an important research field that involves the storage and management of knowledge, but the incompleteness and sparsity of Knowledge Graphs hinder their application in many fields. Knowledge Graph Reasoning aims to alleviate this problem by completing missing paths or identifying wrong paths between entities. Graph Convolution Network (GCN) based methods are one of the state-of-the-art approaches to this work. However, it is difficult to directly generalize to unknown nodes and utilizes valid information from the local neighborhood which results in poor flexibility and extensibility and will loss of important information. this paper presents EG-KGR, a plug-and-play knowledge reasoning model based on enhanced graph sampling and aggregate inductive learning algorithm to relieve the above problems and enhance existing GCN-based methods. Specifically, EG-KGR supports incremental characteristics, uses inductive learning to replace transductive learning, and designs random sampling and local information sampling optimization methods to improve the model's generalization ability, prediction accuracy, and running speed. Extensive experimental results show that our EG-KGR can achieve optimal results.

关键词： Knowledge Graph Knowledge Graph Reasoning Graph Convolution networks Inductive Learning

来源：评论

学校读者我要写书评

暂无评论

Exploiting Invariance in Training Deep Neural networks 36

Exploiting Invariance in Training Deep Neural Networks

引用

36th AAAI conference on Artificial Intelligence / 34th conference on Innovative Applications of Artificial Intelligence / 12th Symposium on Educational Advances in Artificial Intelligence

作者： Ye, Chengxi Zhou, Xiong McKinney, Tristan Liu, Yanfeng Zhou, Qinggang Zhdanov, Fedor Amazon Web Serv Seattle WA 98121 USA

ISBN: (纸本)9781577358763

Inspired by two basic mechanisms in animal visual systems,we introduce a feature transform technique that imposes invariance properties in the training of deep neural *** resulting algorithm requires less parameter tuning, trains well with an initial learning rate 1.0, and easily generalizes to different tasks. We enforce scale invariance with local statistics in the data to align similar samples at diverse scales. To accelerate convergence, we enforce a GL(n)-invariance property with global statistics extracted from a batch such that the gradient descent solution should remain invariant under basis change. Profiling analysis shows our proposed modifications takes similar to 5% of the computations of the underlying convolution layer. Tested on convolutional networks and transformer networks, our proposed technique requires fewer iterations to train, surpasses all baselines by a large margin, seamlessly works on both small and large batch size training, and applies to different computer vision and language tasks.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Clustering Algorithm for Correlation Quickest Hub Discovery Mixing Time Evolution and Random Matrix theory 34

A Clustering Algorithm for Correlation Quickest Hub Discover...

引用

34th ieee International conference on Tools with Artificial Intelligence (ICTAI)

作者： Rodriguez Dominguez, Alejandro Stynes, David Miralta Finance Bank SA Barcelona Spain Munster Technol Univ Munster Ireland

ISBN: (纸本)9798350397444

We present a geometric version of Quickest Change Detection (QCD) and Quickest Hub Discovery (QHD) tests in correlation structures that allows us to include and combine new information with distance metrics. the topic falls within the scope of sequential, nonparametric, high-dimensional QCD and QHD, from which state-of-the-art settings developed global and local summary statistics from asymptotic Random Matrix theory (RMT) to detect changes in random matrix law. these settings work only for uncorrelated pre-change variables. With our geometric version of the tests via clustering, we can test the hypothesis that we can improve state-of-the-art settings for QHD, by combining QCD and QHD simultaneously, as well as including information about pre-change time-evolution in correlations. We can work with correlated pre-change variables and test if the time-evolution of correlation improves performance. We prove test consistency and design test hypothesis based on clustering performance. We apply this solution to financial time series correlations. Future developments on this topic are highly relevant in finance for Risk Management, Portfolio Management, and Market Shocks Forecasting which can save billions of dollars for the global economy. We introduce the Diversification Measure Distribution (DMD) for modeling the time-evolution of correlations as a function of individual variables which consists of a Dirichlet-Multinomial distribution from a distance matrix of rolling correlations with a threshold. Finally, we are able to verify all these hypotheses.

关键词： Clustering Correlation Distribution functions Financial Graphs and networks Quickest change detection Quickest hub discovery Risk management Sequential analysis

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90页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：