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

8,440 篇 会议
50 篇 期刊文献
29 册 图书

馆藏范围

8,519 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,427 篇 工学
- 3,376 篇 计算机科学与技术...
- 2,256 篇 软件工程
- 1,099 篇 信息与通信工程
- 819 篇 控制科学与工程
- 769 篇 电气工程
- 357 篇 生物工程
- 334 篇 电子科学与技术（可...
- 255 篇 机械工程
- 251 篇 动力工程及工程热...
- 195 篇 生物医学工程（可授...
- 185 篇 网络空间安全
- 178 篇 仪器科学与技术
- 148 篇 交通运输工程
- 140 篇 安全科学与工程
- 139 篇 光学工程
- 115 篇 化学工程与技术
2,204 篇 理学
- 1,653 篇 数学
- 392 篇 生物学
- 367 篇 统计学（可授理学、...
- 331 篇 物理学
- 305 篇 系统科学
- 118 篇 化学
1,107 篇 管理学
- 804 篇 管理科学与工程(可...
- 366 篇 图书情报与档案管...
- 335 篇 工商管理
174 篇 医学
- 151 篇 临床医学
- 145 篇 基础医学(可授医学...
146 篇 法学
- 121 篇 社会学
132 篇 文学
- 128 篇 新闻传播学
114 篇 经济学
- 112 篇 应用经济学
58 篇 教育学
43 篇 农学
16 篇 军事学
9 篇 艺术学

主题

1,133 篇 convergence
442 篇 cloud computing
413 篇 optimization
343 篇 computational mo...
293 篇 genetic algorith...
230 篇 information tech...
200 篇 algorithm design...
198 篇 particle swarm o...
195 篇 neural networks
182 篇 resource managem...
178 篇 servers
175 篇 training
170 篇 internet of thin...
162 篇 computer archite...
143 篇 real-time system...
143 篇 mobile computing
141 篇 wireless sensor ...
137 篇 educational inst...
136 篇 costs
129 篇 deep learning

机构

37 篇 university of ch...
28 篇 state key labora...
25 篇 college of compu...
25 篇 chitkara univers...
22 篇 amrita vishwa vi...
18 篇 beijing key labo...
17 篇 school of comput...
15 篇 university of sc...
15 篇 shenyang institu...
15 篇 college of compu...
15 篇 school of inform...
14 篇 school of comput...
14 篇 department of co...
14 篇 college of infor...
13 篇 faculty of infor...
13 篇 college of compu...
13 篇 national univers...
13 篇 institute of com...
12 篇 communication un...
12 篇 state key labora...

作者

40 篇 jeong jongpil
23 篇 kim dong-seong
20 篇 lee jae-min
19 篇 yang yang
14 篇 wang hui
14 篇 pan jeng-shyang
13 篇 wang lei
12 篇 zhiwei ye
12 篇 dong-seong kim
11 篇 sampedro gabriel...
11 篇 peeta basa pati
11 篇 younghan kim
11 篇 jongpil jeong
10 篇 jongwon kim
10 篇 rajagopal shinu ...
10 篇 lee jae min
9 篇 jie yang
9 篇 li li
9 篇 liu yang
9 篇 jae-min lee

语言

8,349 篇 英文
143 篇 其他
38 篇 中文
1 篇 法文

检索条件"任意字段=International Conference on Computing and Convergence Technology"

共 8519 条记录，以下是311-320 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：

Personalized Federated Learning for Fast convergence and Local Adaption: A Double Gradient Descent Method 25

Personalized Federated Learning for Fast Convergence and Loc...

引用

25th IEEE international conferences on High Performance computing and Communications, 9th international conference on Data Science and Systems, 21st IEEE international conference on Smart City and 9th IEEE international conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Li, Zhidu He, Songyang Li, Xu Xue, Meiting School of Communication and Information Engineering Chongqing University of Posts and Telecommunications China College of Physical Education Chongqing University of Posts and Telecommunications China School of Cyberspace Hangzhou Dianzi University China

ISBN: (纸本)9798350330014

Federated learning (FL) has emerged as a promising paradigm for privacy-preserving collaborative learning, enabling multiple devices to jointly train a global model without sharing their raw data. However, the statistical heterogeneity of client data in FL often results in slow convergence rates and poor performance of local models. In this paper, we propose a novel personalized federated learning method called Personalized Federated Learning with Double Descent (pFeD3) to mitigate the impact of data heterogeneity. Our approach decouples the up-dates of personalized models from the main FL process, allowing for personalized solutions tailored to each client. Moreover, we introduce a similarity penalty term to accelerate the convergence of the global model, providing generalization information for personalized models. We prove that pFeD3 achieves sublinear convergence rates under general non-convex settings for both personalized models and the global model. Through extensive experiments on real-world datasets, we demonstrate that pFeD3 significantly outperforms various baseline FL methods in terms of convergence speed and accuracy. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

AutoCaps-Zero: Searching for Hardware-Efficient Squash Function in Capsule Networks

AutoCaps-Zero: Searching for Hardware-Efficient Squash Funct...

引用

2024 IEEE international conference on Communications, computing, Cybersecurity and Informatics, CCCI 2024

作者： Kang, Jieui Kwon, Sooyoung Kim, Hyojin Sim, Jaehyeong Ewha Womans University Dept of Artificial Intelligence Convergence Seoul Korea Republic of Ewha Womans University Dept of Computer Science & Engineering Seoul Korea Republic of

ISBN: (纸本)9798350349832

Capsule networks (CapsNets) offer distinct advantages over conventional convolutional neural networks (CNNs) by introducing the concept of a capsule. Specifically, this innovation achieves both rotational invariance and spatial awareness, making CapsNets a powerful tool in the field of machine learning. However, this breakthrough comes with an increased level of computational complexity. In our comprehensive experimental analysis of CapsNets, we meticulously inspected its various components and identified the squash function as the main computational bottleneck. To address this challenge, In this paper, we adapts the principles of neural architecture search (NAS) and introduces AutoCaps-Zero, a framework that automatically searches the hardware-efficient squash function to reduce model inference time. Meanwhile, CapsNet models incorporating the searched squash function have exhibited excellent performance across datasets of various sizes, while retaining robust features that make them resistant to adversarial attacks. Besides, these models maintain high performance even on challenging datasets like multiMNIST. Particularly, our experimental results demonstrate that the squash function searched by AutoCaps-Zero reduces the execution time of the squash function itself by approximately 68 %. Consequently, deploying the searched squash function on our benchmark models can reduce the end-To-end graphic processing unit (GPU) inference time by up to 34%. Overall, with the searched function, the CapsNet code will be released. © 2024 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Research on a Prototype System of Spatial Big Data Approximation Query for Smart City based on Cloud computing 2

Research on a Prototype System of Spatial Big Data Approxima...

引用

2nd IEEE international conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Zhang, Weishan Leng, Tao Sun, Hongyan Public Security Academy of Sichuan Police College Sichuan Luzhou China Department of Computer Science and Technology Sichuan Police College Sichuan Luzhou China School of Educational Technology Southwest Medical University Sichuan Luzhou China

ISBN: (纸本)9798331504960

Smart city spatial query is a data structure that arranges spatial objects in a certain order based on their location and shape, or a certain spatial relationship between spatial objects. It aims to quickly filter spatial objects that are unrelated to specific spatial operations and is an important indicator for ensuring efficient search and display of spatial data. Its performance directly affects the overall performance of geographic information systems and spatial databases. At present, various spatial approximation query algorithms have been optimized, but there are still significant limitations. This article empirically tests the relationship between smart cities and high-quality development of the circulation industry based on the spatial DID model. The trajectory data is divided into sub trajectories using a trajectory data partitioning method based on optimized minimum boundary rectangle MBR to improve the approximation effect of trajectory data. The results show that the optimal convergence speed of our method is 50 times, and the convergence accuracy is the highest, with a maximum value of 1.5160, a minimum value of 1.6623, and an average value of 1.54471. When the data volume is 3.0, the running time of the method in this article is 560ms. Based on cloud computing systems, the efficiency and accuracy of window queries and spatial connection queries are the highest, and the algorithm has high adaptability. © 2024 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Implementing Internet Key Exchange with Image-based Key Exchange through Socket Programming 9

Implementing Internet Key Exchange with Image-based Key Exch...

引用

9th IEEE international conference for convergence in technology, I2CT 2024

作者： Sreedeepika, M. Lekhya, N. Sri Likesh, K. Rajagopal, Shinu M. Amrita Vishwa Vidyapeetham Amrita School of Computing Dept. of Computer Science And Engineering Bengaluru India

ISBN: (纸本)9798350394474

The primary objective of our project is to execute the Internet Key Exchange (IKE) protocol, which is commonly utilized for secure key exchange in virtual private networks (VPNs) and other secure connections. Our project is divided into two parts: a server and a client, both of which are written in Python and use socket programming. In order to receive an encrypted symmetric key, the server first creates anRivest, Shamir, Adleman (RSA) key pair, then delivers the client its public key. The symmetric key is contained into an image file and encrypted with the server's public key. A symmetric key is created on the client side, encrypted using the public key of the server, and hidden inside an image. After then, the server receives this encrypted key image. After the server gets the picture, it uses the decrypted symmetric key to decode another picture, which concludes the key exchange procedure. This creative strategy not only makes use of IKE's advantages but also investigates a novel technique for key exchange using picture hiding. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

GeoFed: A Geography-Aware Federated Learning Approach for Vehicular Visual Crowdsensing 59

GeoFed: A Geography-Aware Federated Learning Approach for Ve...

引用

59th Annual IEEE international conference on Communications (IEEE ICC)

作者： Hao, Xinli Zhang, Wenjun Liu, Xiaoli Zhu, Chao Tarkoma, Sasu Beijing Inst Technol Beijing Peoples R China Univ Helsinki Helsinki Finland

ISBN: (纸本)9781728190549

Internet of Things (IoT) technology enables enhanced connectivity and information sharing among various devices and platforms. In the context of vehicular crowdsensing, this connectivity has opened up new way to collect environmental data via Vehicle-based Visual Crowdsensing. However, the heterogeneity of data sources and the presence of vehicle outliers pose challenges of ensuring the reliability and accuracy of the machine learning (ML) models. We propose GeoFed, a geography-aware federated learning (FL) approach for vehicular visual crowdsensing. Here, geographically similar vehicular fog nodes (VFNs) collaborate to train a cluster model unlike the traditional FL approaches where vehicles participate to train a model. To further improve GeoFed's performance, we employ the deep Q-Network (DQN) algorithm to intelligently determine the participation of vehicles in the FL process. Through extensive experiments on our own collected real-world dataset, we find that our proposed GeoFed not only outperforms the state-of-art FedAvg with higher F1 score (1.18 x) and mAP (1.14 x), but also achieves a faster convergence rate with less loss (80%).

关键词： Federated Learning Visual-based Crowdsensing Vehicular Fog computing

来源：评论

学校读者我要写书评

暂无评论

Comparative Study on Synthetic and Natural Error Analysis with BART & MarianMT 9

Comparative Study on Synthetic and Natural Error Analysis wi...

引用

9th IEEE international conference for convergence in technology, I2CT 2024

作者： Rohit, R. Gandheesh, S.A. Sannala, Gayatri Sanjana Pati, Peeta Basa Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science & Engineering Bengaluru India

ISBN: (纸本)9798350394474

Text is essential for communication, information sharing, knowledge acquisition, and analysis. It shapes public opinion, supports education, and drives online content, making it crucial in various domains. While there are various language models utilized for text analysis and text correction, there is little to no survey conducted on these model's behavior and limitations. This work deals with studying BART and MarianMT language models behavior to an input dataset consisting of two types of errors, Synthetic and Natural. Synthetic errors are efficient to create and test, whereas Natural errors are more common and close to real world occurring errors. The models were trained and tested with the generated data, the results highlighted that BART exhibited consistent outputs towards both Synthetic and Natural errors and hence revealing a break-even point at the vicinity of 26% Synthetic error introduction. Conversely, the performance of MarianMT was comparatively diminished for Synthetic errors in contrast to Natural errors. These findings provide valuable insights into the behavior and capabilities of the models. © 2024 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Opportunistic Task Offloading in UAV-assisted Mobile Edge computing: A Deep Reinforcement Learning Approach 14

Opportunistic Task Offloading in UAV-assisted Mobile Edge Co...

引用

14th international conference on Information and Communication technology convergence, ICTC 2023

作者： Song, Taewon Soonchunhyang University Department of Internet of Things Asan Korea Republic of

ISBN: (纸本)9798350313277

Mobile edge computing (MEC) aims to extend cloud services to the network edge to reduce network traffic and latency for 5G mobile networks. Unmanned aerial vehicles (UAVs) are being used as assisted edge clouds for large-scale sparsely-distributed user equipment, due to their flexible deployment, wide coverage, and reliable wireless communication. In this paper, we propose a deep Q learning-based opportunistic task offloading algorithm for UAV-assisted mobile edge computing. To this end, we formulate a Markov decision process (MDP) model in which the UAV can choose whether to offload tasks to the cloud server or process them on the local MEC server. Extensive simulations show that our task offloading algorithm outperforms both offload-only and local-only algorithms, ensuring satisfactory service quality for 5G services. © 2023 IEEE.

关键词： 5G mobile networks deep reinforcement learning DQN mobile edge computing task offloading

来源：评论

学校读者我要写书评

暂无评论

MCHeRA: An Efficient Multi Cloud Heuristic Resource Allocation using Grey Wolf Optimization 5

MCHeRA: An Efficient Multi Cloud Heuristic Resource Allocati...

引用

5th international conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Gandhimathi, P. Kiruthiga, S. BIndu, K.V. Shanthi, H.J. Velmurugan, V. Sangeethaa, S.N. Srm Madurai College for Engineering and Technology Pottapalayam Sivagangai District630612 India School of Computing Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science &engineering Chennai India Puduvoyal India Department: Computer Applications Hindustan Institute of Technology and Science Deemed to be University Padur India Vel Tech Rangarajan Dr Sagunlatha R&d Institute of Science and Technology Department of Electronics and Communication Engineering Avadi Chennai India Bannari Amman Institute of Technology India

ISBN: (纸本)9798350389609

Cloud computing is a cutting-edge technology that has gained immense popularity in the present era. The burgeoning demand for services has necessitated the development of a framework for efficiently allocating resources to incoming requests. This approach not only enhances the network's efficiency but also reduces costs significantly. The convergence of cloud and edge computing has emerged as a burgeoning field of study in the computing industry over the past few years. The exponential rise in the number of customers and requests for cloud data centers (CDCs) has highlighted the critical need for robust servers and energy-efficient mechanisms. As CDCs expand to meet growing demands, they face significant challenges related to energy consumption, environmental impact, and operational costs. Employing suitable algorithms for resource allocation in CDCs is crucial in order to minimize energy consumption. The objective of this research endeavor was to devise an ingenious approach for dynamically allocating resources in cloud networks by leveraging the power of the Gray Wolf Optimization algorithm. The proposed work performs Multi-Cloud Heuristic Resource Allocation (MCHeRA) using Grey Wolf Optimization (GWO) algorithm and produces 61% of computational resource utilization, 79% of CPU utilization, 64% memory utilization, 74% bandwidth utilization. The algorithm that has been put forth is meticulously assessed and contrasted with its counterparts. The outcome of the simulation manifests the remarkable efficacy of the novel MCHeRA in comparison to alternative algorithms. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Anatomization of Neural Networks based models for Semantic Analysis of Tabular dataset 9

Anatomization of Neural Networks based models for Semantic A...

引用

9th IEEE international conference for convergence in technology, I2CT 2024

作者： Bharath, B. Sai Bollineni, Jahnavi Mandala, Sandeep Preetham Ganguly, Tania Amudha, J. Shukla, Nikhil Joseph, Raj Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science And Engineering Bengaluru India Intellectyx Data Science Pvt Ltd India

ISBN: (纸本)9798350394474

The Paper focuses on analysing neural network models that are used for semantically classifying tabular customer datasets. Additionally, we propose a custom neural network architecture to analyze tabular datasets and enable the model to extract and comprehend the underlying semantics within the data. The research focuses on three distinct neural network models: CharCNN, Bi-LSTM, and CNN+Bi-LSTM. Through comprehensive evaluation based on accuracy, and confidence scores of the models' performance, we determined that Bi-LSTM proved to be the best fit for this approach and dataset. The findings suggest that the custom CHAR-CNN model can be effective in classifying tabular data and can potentially be applied on various datasets considering both computational time and accuracy. This research contributes to the advancement in the field of semantic analysis for tabular dataset, opening avenues for further research on how to handle different kinds of Tabular datasets and enhancement of semantic models in NLP. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Fast Second-order Method for Neural Networks under Small Treewidth Setting

Fast Second-order Method for Neural Networks under Small Tre...

引用

2024 IEEE international conference on Big Data, BigData 2024

作者： Li, Xiaoyu Long, Jiangxuan Song, Zhao Zhou, Tianyi Stevens Institute of Technology Department of Computer Science HobokenNJ United States South China University of Technology School of Software Engineering Guangzhou China University of California Berkeley The Simons Institute for the Theory of Computing BerkeleyCA United States University of Southern California Department of Computer Science Los AngelesCA United States

ISBN: (纸本)9798350362480

Training neural networks is a fundamental problem in theoretical machine learning. Second-order methods are rarely used in practice due to their high computational cost, even they converge much faster than first-order methods. The state-of-the-art result for the second-order method to train an over-parameterized neural network can run in O(log(1/ϵ)) iterations and each iteration has O(mnd + n3) running time, where n represent the number of data points, d is the dimension of the feature space of each data and m is the width of the neural network [Brand, Peng, Song and Weinstein ITCS 2021]. In this work, we further improve the convergence rate and the running time for each iteration to O(loglog(1/ϵ)) and O(mdτ2) respectively, where m = Ω(n4) and τ is the treewidth of the data matrix and usually very small. Our algorithm has a quadratic convergence rate, so it can be regarded as a truly second-order algorithm. To the best of our knowledge, our algorithm is the first to achieve a quadratic convergence rate for neural network training, with a per-iteration running time of O(mdτ2). © 2024 IEEE.

关键词： Trees (mathematics)

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 << < 28 29 30 31 32 33 34 35 36 37 > >>

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：