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101-110 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：

Enhancing Implicit Discourse Relation Classification by Perceiving External Semantics and Convolving Internal Semantics

Enhancing Implicit Discourse Relation Classification by Perc...

引用

International conference on Tools for Artificial Intelligence (ICTAI)

作者： Zujun Dou Yu Hong Yu Sun Xiao Li Guodong Zhou Computer Science and Technology Soochow University Suzhou China

Implicit discourse relation classification refers to a task of automatically determining relationships between arguments. It has been widely proven that, in a neural classification architecture, decoding discourse relations heavily relies on the reliable semantic representations of arguments. In addition, our previous survey shows that, for a target argument, the external semantic information hidden in the accompanying argument benefits the encoding of the target, either wholly or partially. Moreover, dependency structure appears as the crucial feature for synthesizing word senses of the entire words in arguments. Accordingly, we propose a novel method to enhance the current representation learning of pairwise arguments, which takes into consideration both external semantic information and internal dependency structure. In particular, we inject external semantic information into the Long-Short Term Memory (LSTM) unit of Recurrent Neural Network (RNN) through the input and forget gates. Different from the existing one-off interactive learning models, our method allows the neuronal memory of internal argument semantics to be affected by external information at each encoding step. On the basis, we apply the parser-based Graph Convolutional networks (GCN) over the semantic presentations of words, so as to accumulate the closely-related semantic information in terms of dependency structures. We conduct experiments on Penn Discourse TreeBank Corpus of version 2.0 (PDTB 2.0). the test results illustrate that the proposed method enhances the baseline significantly, and it obtains comparable performance compared to the state of the art.

关键词： Representation learning Recurrent neural networks Semantics Knowledge graphs Logic gates Encoding Decoding

来源：评论

学校读者我要写书评

暂无评论

A Federated Multi-Server Knowledge Graph Embedding Framework For Link Prediction

A Federated Multi-Server Knowledge Graph Embedding Framework...

引用

International conference on Tools for Artificial Intelligence (ICTAI)

作者： Ce Hu Baisong Liu Xueyuan Zhang Zhiye Wang Chennan Lin Linze Luo Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China

the federated framework is actively applied in knowledge graph fusion research to obtain a complete knowledge graph without exposing data privacy. It can help local clients learn the knowledge graph embeddings in other clients without revealing data privacy. However, current federated-based knowledge graph embedding frameworks cannot exploit both entity and relation embeddings and may not prevent partial triples from being reconstructed. this paper proposes a novel framework named Federated Multi-server knowledge graph embedding (FedM), which creatively utilizes uploaded entity and relation embeddings while preventing privacy leakage. Expressly, we first set up two central servers for entity and relation embeddings to aggregate and share client-uploaded embeddings. Secondly, we design a knowledge graph secure aggregation algorithm to address the potential privacy concerns in FedM. We conduct comparative experiments on an empirical dataset (divided into three federated datasets) with four commonly-used knowledge graph embedding methods to evaluate the performance of our proposed framework. In addition, our proposed FedM framework is generally superior to the latest baseline frameworks on both privacy preservation and link prediction tasks.

关键词： Training Privacy Data privacy Aggregates Knowledge graphs Servers Security

来源：评论

学校读者我要写书评

暂无评论

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on Adaptive Perturbation on Federated Graph Learning 25

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on ...

引用

34th ACM Web conference, WWW 2025

作者： Li, Ken Shi, Bin Wei, Jiazhe Dong, Bo School of Computer Science and Technology Xi’an Jiaotong University Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an China School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an China School of Distance Education Xi’an Jiaotong University Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an China

ISBN: (纸本)9798400712746

Federated Graph Learning (FedGL) is an emerging Federated Learning (FL) framework that learns the graph data from various clients to train better Graph Neural networks(GNNs) model. Owing to concerns regarding the security of such framework, numerous studies have attempted to execute backdoor attacks on FedGL, with a particular focus on distributed backdoor attacks. However, all existing methods posting distributed backdoor attack on FedGL only focus on injecting distributed backdoor triggers into the training data of each malicious client, which will cause model performance degradation on original task and is not always effective when confronted with robust federated learning defense algorithms, leading to low success rate of attack. What’s more, the backdoor signals introduced by the malicious clients may be smoothed out by other clean signals from the honest clients, which potentially undermining the performance of the attack. To address the above significant shortcomings, we propose a non-intrusive graph distributed backdoor attack(NI-GDBA) that does not require backdoor triggers to be injected in the training data. Our attack trains an adaptive perturbation trigger generator model for each malicious client to learn the natural backdoor from the GNN model downloading from the server with the malicious client’s local data. In contrast to traditional distributed backdoor attacks on FedGL via trigger injection in training data, our attack on different datasets such as Molecules and Bioinformatics have higher attack success rate, stronger persistence and stealth, and has no negative impact on the performance of the global GNN model. We also explore the robustness of NI-GDBA under different defense strategies, and based on our extensive experimental studies, we show that our attack method is robust to current federated learning defense methods, thus it is necessary to consider non-intrusive distributed backdoor attacks on FedGL as a novel threat that requires custom d

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Dual Autoencoder Enhanced Subgraph Pattern Mining for Cognitive Diagnosis

Dual Autoencoder Enhanced Subgraph Pattern Mining for Cognit...

引用

International conference on Tools for Artificial Intelligence (ICTAI)

作者： Haodong Meng Changzhi Chen Hongyu Yi Xiaofeng He School of Computer Science and Technology East China Normal University Shanghai China Born to Learn Education Technology Chengdu China Shanghai Key Laboratory of Trustworthy Computing Shanghai China

In adaptive learning, Cognitive diagnosis aims to discover students' knowledge state on different knowledge con-cepts and predict their future performance. Most previous methods consider more on students' own answering history and rarely model the the impact brought by students with similar answering behaviors explicitly. this collaborative information among students is helpful for students who lack sufficient historical logs. In this paper, we propose a new cognitive diagnosis method called Dual Autoencoder Enhanced Subgraph Pattern Mining(DASPM) for Cognitive Diagnosis, which incorporates collaborative information among students into the cognitive di-agnosis process to obtain more accurate predictions. Specifically, we use a graph neural network to capture collaborative pattern on the student-exercise bipartite graph. In order to filter out the interference of irrelevant information, we design a sub graph extraction algorithm that separates local parts around the target student-exercise pair from global graph based on the correlation between exercises. In addition, we utilize a dual autoencoder module to encode students and exercises to enhance the initial representation of nodes in the sub graph. Extensive experiments on multiple datasets show the effectiveness of our proposed method.

关键词： Correlation Collaboration Learning (artificial intelligence) Interference Predictive models Prediction algorithms Information filters

来源：评论

学校读者我要写书评

暂无评论

Bayesian Optimized Supervised Learning for Short-Term Net Load Forecasting in Distribution Grids with Net-Metering

Bayesian Optimized Supervised Learning for Short-Term Net Lo...

引用

Australasian Universities Power Engineering conference, AUPEC

作者： Abdul Haseeb Shahid Nawaz Khan Naveed Arshad Muhammad Waseem Md. Rabiul Islam Md. Jahangir Hossain Shuvra Prokash Biswas Department of Computer Science Lahore University of Management Sciences Lahore Pakistan Department of Electronic Engineering Maynooth University Kildare Ireland School of Electrical Computer and Telecom Engineering University of Wollongong Keiraville NSW Australia School of Electrical and Data Engineering University of Technology Sydney Ultimo NSW Australia Faculty of Engineering and Information Sciences University of Wollongong Wollongong NSW Australia

ISBN: (数字)9798350377941

ISBN: (纸本)9798350377958

As power systems evolve into more intelligent, flexible, and interactive networks with a higher penetration of Renewable Energy Sources (RES) on the demand side, net load forecasting has become a cost-effective and essential technique for planning, stability, and reliability of modern power grids. this study explores both direct and indirect methodologies for short-term net load forecasting (STNLF) in distribution grids considering solar net-metering using deep learning (DL) and machine learning (ML) techniques. the proposed models begin with feature engineering and filtering using Pearson Correlation and Mutual Information (MI) indices, followed by developing a forecasting models employing a Bayesian Optimized Long Short-Term Memory (BO-LSTM) network and Bayesian Optimized Random Forest (BO-RF). the model’s effectiveness was validated using historical net load data from the Lahore Electric Supply Company (LESCO) spanning January 2022 to January 2024, as LESCO has the highest number of net-metering customers among all Distribution Companies (DISCOS) in Pakistan. Results demonstrate the BO-RF model’s capability to deliver accurate and robust STNLF, achieving a Mean Absolute Percentage Error (MAPE) of $\mathbf{3. 5 6 \%}$ for the test data and $\mathbf{2. 2 1 \%}$ for the train data. this study also compares the efficiency of indirect and direct methods for STNLF, demonstrating that the indirect method generally performs better than direct method in distribution grids.

关键词： Radio frequency Correlation Load forecasting Predictive models Power system stability Data models Bayes methods Forecasting Long short term memory Load modeling

来源：评论

学校读者我要写书评

暂无评论

Self-Adaptive Layer: An Application of Function Approximation theory to Enhance Convergence Efficiency in Neural networks 34

Self-Adaptive Layer: An Application of Function Approximatio...

引用

34th International conference on Information Networking (ICOIN)

作者： Chan, Ka-Hou Im, Sio-Kei Ke, Wei Macao Polytech Inst Sch Appl Sci Macau Peoples R China Macao Polytech Inst Macau Peoples R China

ISBN: (纸本)9781728141985

Neural networks provide a general architecture to model complex nonlinear systems, but the source data are often mixed with a lot of noise and interference information. One way to offer a smoother alternative for addressing this issue in training is to increase the neural or layer size. In this paper, a new self-adaptive layer is developed to overcome the problems of neural networks so as to achieve faster convergence and avoid local minimum. We incorporate function approximation theory into the layer element arrangement, so that the training process and the network approximation properties can be investigated via linear algebra, where the precision of adaptation can be controlled by the order of polynomials being used. Experimental results show that our proposed layer leads to significantly faster performance in convergence. As a result, this new layer greatly enhances the training accuracy. Moreover, the design and implementation can be easily deployed in most current systems.

关键词： Function Approximation Orthogonal Polynomial Self-Adaptive Neural Network

来源：评论

学校读者我要写书评

暂无评论

Convolutional Transformer with Similarity-based Boundary Prediction for Action Segmentation

Convolutional Transformer with Similarity-based Boundary Pre...

引用

International conference on Tools for Artificial Intelligence (ICTAI)

作者： Dazhao Du Bing Su Yu Li Zhongang Qi Lingyu Si Ying Shan Institute of Software Chinese Academy of Science University of Chinese Academy of Sciences Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods International Digital Economy Academy Tencent PCG ARC Lab

Action classification has made great progress, but segmenting and recognizing actions from long videos remains a challenging problem. Recently, Transformer-based models with strong sequence modeling ability have succeeded in many se-quence modeling tasks. However, the lack of inductive bias and the difficulty of handling long video sequences limit the application of the Transformer in the action segmentation task. In order to explore the potential of the Transformer in this task, we replace some specific linear layers in the vanilla Transformer with dilated temporal convolution, and a sparse attention mechanism is utilized to reduce the time and space complexities to process long video sequences. Besides, directly using frame-wise classification loss to train the model will cause that frames at boundaries of actions are treated equally with those in the middle of actions, and the learned features are not sensitive to boundaries. We propose a new local log-context attention module to predict whether each frame is at the beginning, middle, or end of an action. Since boundary frames are similar to their neighboring frames of different classes, our similarity-based boundary prediction helps learn more discriminative features. Extensive experiments on three datasets show the effectiveness of our method.

关键词： Convolution Video sequences Predictive models Transformers Complexity theory Convolutional neural networks Task analysis

来源：评论

学校读者我要写书评

暂无评论

Base Station Operation Based on Affinity Propagation in Cellular networks 34

Base Station Operation Based on Affinity Propagation in Cell...

引用

34th International conference on Information Networking (ICOIN)

作者： Takahashi, Kazunari Adachi, Koichi Univ Electrocommun Adv Wireless & Commun Res Ctr AWCC 1-5-1 Chofugaoka Chofu Tokyo Japan

ISBN: (纸本)9781728141985

Wireless communication network requires a network design that can cope with peak mobile traffic. the mobile traffic fluctuates over time. It is known that the energy consumption of base stations (BSs) accounts for a large percentage of the overall network energy consumption. Recently, small cell base stations (SBSs) are deployed at high density to cope with the increasing amount of mobile traffic. However, activating all SBSs during non-peak hours of traffic leads to a decrease in energy efficiency. BS sleep strategy has been considered to improve energy efficiency. In this paper, affinity propagation (AP) based BS sleep technology is proposed. AP does not need to determine the number of clusters in advance. the computer simulation results show that the proposed scheme can reduce the outage probability of user equipment (UE) compared to the conventional scheme.

关键词： green cellular networks energy-efficient operation base station sleep clustering affinity propagation

来源：评论

学校读者我要写书评

暂无评论

Cascaded fault model of power grid with active defense strategy

Cascaded fault model of power grid with active defense strat...

引用

Chinese Control and Decision conference, CCDC

作者： Gang Liu Yurong Song Ruqi Li School of Computer Science Nanjing University of Posts and Telecommunications Nanjing School of Automation Nanjing University of Posts and Telecommunications Nanjing Jiangsu Engineering Lab for IOT Intelligent Robots (IOT Robot) Nanjing China

ISBN: (纸本)9781665478977

With the rapid development of power system, its potential hazards are also increasing. Paying attention to grid cascading faults and building a robust smart grid have become a hot topic in current research. Based on the complex network theory system and the existing electrical betweenness model, a cascading failure model with active defense strategy has been proposed and its robustness has been analyzed. When the node is attacked and fails, the distribution principle of "the capable nodes are always busy" is adopted to distribute the failure load. that is, the larger the residual load capacity of adjacent nodes, the more load will be distributed. An active defense strategy has been proposed to artificially remove a small number of nodes with a large "removal ratio", reduce the electrical betweenness of other nodes, and prevent the propagation of cascading faults and power grid collapse. through ieee118 and ieee300 power grid system simulation, the effects of key factors such as attack mode, allocation strategy and tolerance parameters on network robustness have been studied. the experimental simulation shows that the power grid cascade failure model with active defense strategy can better inhibit the further spread of power grid cascade faults.

关键词： Analytical models Power system protection Complex networks Power grids Robustness Systems simulation Smart grids

来源：评论

学校读者我要写书评

暂无评论

A Generative Adversarial Active Learning Method for Effective Outlier Detection

A Generative Adversarial Active Learning Method for Effectiv...

引用

International conference on Tools for Artificial Intelligence (ICTAI)

作者： Mohamed Jaward Bah Ji Zhang Ting Yu Feng Xia Zhao Li Shuigeng Zhou Hongzhi Wang Big Data Intelligence Research Center Zhejiang Lab Hangzhou China University of Southern Queensland School of Sciences Toowoomba Australia Institute of Innovation Science and Sustainability Federation University Australia Ballarat Australia Zhejiang University China Fudan University School of Computer Science Shanghai China Harbin Institute of Technology Massive Data Computing Lab China

Outlier detection is an important data mining task, and developing effective methods to detect outliers is challenging in cases where there is insufficient labeled data. Manually labeling the data is labor-intensive and time-consuming. Because of a limited number of labeled samples, the classes are unbalanced, resulting in a class-imbalance problem. Existing methods fail to address these aforementioned issues holistically and fall short in generating quality outlier samples for effective outlier detection accuracy. In this paper, we propose a new solution that tackles these problems. We propose a. Generative Adversarial Active Learning method (DIR-GAAL), which generates Diverse, Informative, and Representative outlier samples through active learning, and employs the mini-max game between the generator and discriminator in a generative adversarial network. We conducted extensive experiments on several benchmark datasets to evaluate the performance of our method. When compared to other benchmark methods, our method consistently demon-strates better outlier detection accuracy without being negatively affected by the class-imbalance problem.

关键词： Learning systems Games Benchmark testing Generative adversarial networks Generators Labeling Task 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 << < 7 8 9 10 11 12 13 14 15 16 > >>

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：