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

8,477 篇 会议
50 篇 期刊文献
29 册 图书

馆藏范围

8,556 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,457 篇 工学
- 3,403 篇 计算机科学与技术...
- 2,281 篇 软件工程
- 1,104 篇 信息与通信工程
- 824 篇 控制科学与工程
- 770 篇 电气工程
- 357 篇 生物工程
- 335 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...
- 187 篇 网络空间安全
- 178 篇 仪器科学与技术
- 149 篇 交通运输工程
- 142 篇 安全科学与工程
- 139 篇 光学工程
- 115 篇 化学工程与技术
2,217 篇 理学
- 1,664 篇 数学
- 392 篇 生物学
- 371 篇 统计学（可授理学、...
- 333 篇 物理学
- 306 篇 系统科学
- 118 篇 化学
1,115 篇 管理学
- 808 篇 管理科学与工程(可...
- 371 篇 图书情报与档案管...
- 339 篇 工商管理
176 篇 医学
- 153 篇 临床医学
- 147 篇 基础医学(可授医学...
147 篇 法学
- 121 篇 社会学
132 篇 文学
- 128 篇 新闻传播学
115 篇 经济学
- 113 篇 应用经济学
59 篇 教育学
44 篇 农学
16 篇 军事学
9 篇 艺术学

主题

1,134 篇 convergence
441 篇 cloud computing
412 篇 optimization
343 篇 computational mo...
294 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...
145 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...
29 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
24 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

8,239 篇 英文
290 篇 其他
40 篇 中文
1 篇 法文

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

共 8556 条记录，以下是1041-1050 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：

DMSA: Dynamic Multi-Scale Unsupervised Semantic Segmentation Based On Adaptive Affinity 48

DMSA: Dynamic Multi-Scale Unsupervised Semantic Segmentation...

引用

48th IEEE international conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Yang, Kun Lu, Jun Heilongjiang University College of Computer Science and Technology Harbin150080 China Jiaxiang Industrial Technology Research Institute of Hlju Jining China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (纸本)9781728163277

The proposed method in this paper proposes an end-to-end unsupervised semantic segmentation architecture DMSA based on four loss functions. The framework uses Atrous Spatial Pyramid Pooling (ASPP) module to enhance feature extraction. At the same time, a dynamic dilation strategy is designed to better capture multi-scale context information. Secondly, a Pixel-Adaptive Refinement (PAR) module is introduced, which can adaptively refine the initial pseudo labels after feature fusion to obtain high quality pseudo labels. Experiments show that the proposed DSMA framework is superior to the existing methods on the saliency dataset. On the COCO 80 dataset, the MIoU is improved by 2.0, and the accuracy is improved by 5.39. On the Pascal VOC 2012 Augmented dataset, the MIoU is improved by 4.9, and the accuracy is improved by 3.4. In addition, the convergence speed of the model is also greatly improved after the introduction of the PAR module. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Projection Onto Convex Sets Approach to Solve Homogeneous Self Dual Model of Portfolio Optimization

Projection Onto Convex Sets Approach to Solve Homogeneous Se...

引用

2023 international conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, ICAMIMIA 2023

作者： Subchan, Subchan Yamashita, Makoto Hidayatullah, Alvian Alif Safarina, Sena Yunus, Mahmud Institut Teknologi Sepuluh Nopember Department of Mathematics Surabaya Indonesia Tokyo Institute of Technology Dept. of Mathematical and Computing Science Tokyo Japan

ISBN: (纸本)9798350309225

A portfolio optimization problem is a convex optimization problem that involves a linear objective function with quadratic constraints. One method for solving portfolio optimization problems is to convert the QCLP (quadratically constrained linear programming) model into a homogeneous self-dual (HSD) model. The homogeneous self-dual (HSD) model is a combination of primal and dual problems from conic programming and is based on determining a point from the intersection of two convex sets, a convex cone and a subspace. The projection onto convex sets (POCS) and averaged projection can be employed to determine the solution of the HSD model. In this paper, POCS is applied to solve QCLP on portfolio optimization. The resulting solution is the convergence value of the sequence constructed in the POCS method. From the sequence constructed in the POCS methods, we can see whether the QCLP problem in portfolio optimization has a solution or not. © 2023 IEEE.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

Pareto Set Representation Learning with Application to Multi-criteria Order Optimization

Pareto Set Representation Learning with Application to Multi...

引用

2024 IEEE international conference on Industrial Engineering and Engineering Management, IEEM 2024

作者： Tan, C.S. Gupta, A. Ong, Y.S. Lam, S.K. Pratama, M. Tan, P.S. Singapore Singapore School of Mechanical Sciences Indian Institute of Technology Goa India STEM University of South Australia Adelaide Australia

ISBN: (纸本)9798350386097

Multi-objective optimization seeks to arrive at a diverse set of Pareto-optimal solutions facilitating a posteriori decision-making. However, this becomes challenging for high-dimensional problems with limited compute, imposing a compromise between convergence and diversity of the final solutions. To address this curse of dimensionality, we introduce the concept of Pareto set representation learning, reducing the problem to its smallest possible dimensions while accurately capturing the Pareto-optima. A denoising autoencoder is invoked to discover a compressed latent representation of a sparsely populated Pareto set by leveraging its unique bottleneck architecture. This representation then serves as a means to create compact inverse models, mapping points from the Pareto front in objective space to the (dimensionally reduced) Pareto set in decision space. The method is empirically tested on benchmark problems and an industrial multi-site order planning problem showcasing its effectiveness in reducing the dimensionality of the Pareto set (~99.6%) while achieving significant gains (>200%) in Pareto approximation capacity. With such compact yet accurate inverse models, decision makers can readily generate high-dimensional solutions corresponding to any preferred, unexplored subregions of the objective space. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Research on Edge-Cloud Collaborative Data Sharing Method Based on Federated Learning in Internet of Vehicles 29

Research on Edge-Cloud Collaborative Data Sharing Method Bas...

引用

29th IEEE international conference on Parallel and Distributed Systems, ICPADS 2023

作者： Ren, Xiaohui Wang, Yan Zhang, Jun Han, Zhiheng Inner Mongolia University College of Computer Science Hohhot China

ISBN: (纸本)9798350330717

With the development of Internet of Vehicles(IoV) technology and the popularization of intelligent vehicles, a large amount of vehicle data is generated and accumulated. Due to the privacy and sensitivity of vehicle datas, the emergence of Federated Learning(FL) technology can effectively protect user privacy. FL allows model training without the need to share raw data, protecting vehicle user data by sharing model parameters. However, within conventional FL methodologies, vehicle users are required to undertake significant computational tasks, and communication with cloud servers demands considerable time. Inspired by edge computing, we introduce a cloud-edge-end two-tier architecture based on federated learning(CEE-FLA).This structure transfers the model aggregation process originally completed by the cloud server to the edge server to reduce the number of communications with the cloud server, thereby improving the accuracy and efficiency of data sharing. Considering that model training efficiency is affected by vehicle performance, we improve the traditional FL algorithm in CEE-FLA and adopt a K-Vehicle random scheduling strategy to minimize the impact of vehicle performance differences on model convergence and data sharing efficiency. The experimental results demonstrate that our proposed CEE-FAL offers improvements in both accuracy and efficiency compared to the traditional cloud-end single-tier. Additionally, as the number of iterations between vehicles and edge servers increases, the model's convergence speed also improves. © 2023 IEEE.

关键词： cloud-edge-end two-tier architecture data sharing edge computing Federated Learning Internet of Vehicle technology

来源：评论

学校读者我要写书评

暂无评论

Multilayer network representation learning model with structure entropy information 3

Multilayer network representation learning model with struct...

引用

3rd international conference on Artificial Intelligence, Automation, and High-Performance computing, AIAHPC 2023

作者： Wu, Yong Yan, Guanghui Luo, Hao School of Electronics and Information Engineering Lanzhou Jiaotong University Lanzhou730070 China Key Laboratory of Media Convergence Technology and Communication Lanzhou730030 China School of Information Science and Engineering Gansu University of Traditional Chinese Medicine Lanzhou730030 China

ISBN: (数字)9781510666580

ISBN: (纸本)9781510666573

Network representation learning maps network nodes to a unified vector space, which has found widespread use in various complex network analysis tasks. The resulting embedding vectors can reflect the original network's features and improve the accuracy of downstream tasks. However, current multi-layer network representation learning models have limited node sequence semantics and cannot fully capture the node's local and global structural information. To address this issue, we propose a multi-layer network representation learning model that integrates structural entropy information. Our model comprehensively considers the local and global structure of a multi-layer network, using local structure entropy and network standard structure entropy to guide the intra-layer and inter-layer migration processes, and then trains the node sequence using the skip-gram model to obtain the node vector. Experimental results on five public datasets demonstrate that our proposed model's embedding vector quality is significantly improved, with AUC scores on different datasets improving by 5% to 10% in the link prediction task. © 2023 SPIE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

An Empirical Analysis of Various Techniques of Solving Obstacles through Artificial Intelligence 4

An Empirical Analysis of Various Techniques of Solving Obsta...

引用

4th IEEE international conference on Advance computing and Innovative Technologies in Engineering, ICACITE 2024

作者： Vaidya, Himadri Dhabliya, Dharmesh Jweeg, Muhseen Almusawi, Muntather Naser, Zamen Latef Hashem, Amjad Jawad, Ahmed Qusay Graphic Era Hill University Department of Cse India Graphic Era Deemed to Be University Uttarakhand Dehradun248007 India Information Technology Vishwakarma Institute of Information Technology Pune India Al-Farahidi University Baghdad Iraq The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq National University of Science and Technology College of Technical Engineering Dhi Qar64001 Iraq Alkunooze University College Computer Engineer Department Basra Iraq Kut University College Department of Electrical Engineering Technologies Wasit Iraq

ISBN: (纸本)9798350360165

In the space sector, artificial intelligence (AI), and especially machine learning (ML), is becoming more and more popular. These days, ML algorithms are extensively used in many different contexts, including operational control of satellite constellations, autonomous navigation, and spacecraft health monitoring. There are two main types of surveys that are now available on AI applications in space missions, each with certain drawbacks. Generally speaking, the first category is out of date since it does not include more recent advancements like Deep Learning (DL) and bioinspired AI algorithms. On the other hand, the second group tends to be too detailed and concentrates only on certain AI approaches, which can put off those who are looking for a more comprehensive knowledge, especially those with technical expertise in other subjects. In order to rectify these deficiencies, we provide a succinct summary that provides a thorough understanding of the uses and difficulties of AI in the space sector. Our study covers classical AI approaches used in several space mission disciplines, emphasizing their usefulness in real-world applications rather than going into formal methodologies. We also investigate bioinspired AI algorithms and point out possible uses for them. Beyond technical obstacles, we recognize and talk about significant legal ramifications of using AI in space projects. We expand our evaluation to include developments in Blockchain and Internet of Things (IoT) technology in the consideration of future directions. Specifically, we highlight how AI and Blockchain are convergent and pinpoint three major application fields in the space community that stand to gain a great deal from this convergence. These areas include satellite communications, spacecraft data security, and the Internet of Things in Space (IoST). Our review strives to be a useful tool for anyone interested in learning more about the complex world of artificial intelligence applications in space b

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Classification Based on Ensembling EfficientNet Using Histopathology Images 4

Lung Cancer Classification Based on Ensembling EfficientNet ...

引用

4th international conference on Intelligent Cybernetics technology and Applications, ICICyTA 2024

作者： Hidayah, Akif Rachmat Wisesty, Untari Novia School of Computing Telkom University Bandung Indonesia

ISBN: (纸本)9798331506490

Lung cancer is a leading cause of cancer-related deaths, and accurate, early diagnosis is critical for effective treatment. Histopathological analysis is a standard diagnostic approach but requires significant expertise and time. This study aims to improve lung cancer classification through an ensemble of EfficientNetV2 models (B0-B3) applied to histopathological images. EfficientNetV2 was chosen for its scalability and strong performance in image classification tasks. Data augmentation was used to enhance robustness, simulating variability in histopathological slides, while transfer learning from ImageNet pre-trained models enabled faster convergence with limited data. The models were trained on the LC25000 dataset, containing augmented images, and evaluated individually and in ensemble configurations. Grad-CAM provided interpretability, generating heatmaps that highlight model focus, aiding in understanding decision-making. Results showed that individual EfficientNetV2 models achieved near-perfect accuracy, with the ensemble approach further improving performance. Ensemble models, particularly those using hard voting, achieved up to 100% accuracy, precision, and recall, underscoring the effectiveness of combined predictions. However, the high accuracy may be partially due to the dataset's limited unique images, as repeated patterns in augmented data might inflate performance. Future work will test the ensemble on larger, more diverse datasets to validate generalizability. These findings demonstrate the potential of EfficientNetV2 ensembles in lung cancer diagnostics, paving the way for reliable, interpretable AI-based pathology tools in clinical settings. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Adaptive Compressive Sensing for Natural Images Using Schur Decomposition and Optimized Reconstruction 4

Adaptive Compressive Sensing for Natural Images Using Schur ...

引用

4th international conference on Sustainable Expert Systems, ICSES 2024

作者： Elaveini, M. Aarthi Deepa, T. Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Electronics and Communication Engineering Ramapuram Chennai India

ISBN: (纸本)9798331540364

Compressive sensing (CS) is growing as an effective method for efficient imagine capture and recovery by harnessing the fundamental sparseness of natural images. The paper presents a unique framework for CS of live images employing Schur decomposition, a matrix decomposition approach that improves the detection and reconstruction processes. The suggested technique utilizes Schur decomposition to enhance the sensing matrix, facilitating more effective sampling by collecting essential imagine information in both spatial and frequency domains. The Schur-based sensing matrix, in contrast to conventional random sensing matrices, is designed to use the structural characteristics of real pictures, hence enhancing the precision of image reconstruction from a reduced quantity of observations. The integrated Schur decomposition with an iterative image reconstruction algorithm, incorporating Orthogonal Matching Pursuit (OMP) promotes sparsity. The combination improves the robustness of the recovery process while reducing reconstruction artifacts. Extensive simulations demonstrate that proposed Schur-based framework achieves superior performance compared to conventional CS techniques, particularly in terms of Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The proposed method improves the quality of reconstructed images and expedites the convergence of the reconstructing technique, hence reducing computational complexity. The framework is assessed over several natural imagine datasets, demonstrating substantial improvements in image quality and computing efficiency resulting in a PSNR of 37.263 dB and SSIM 0.813 for CAT image. The Schur decomposition method for CS is an effective solution for applications necessitating quick picture capture and high-quality reconstruction, including medical imaging, remote sensing, and real-time image processing systems. © 2024 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Study Containerization Technologies like Docker and Kubernetes and their Role in Modern Cloud Deployments

Study Containerization Technologies like Docker and Kubernet...

引用

international conference for convergence of technology (I2CT)

作者： Shreyas Agrawal Dhawan Singh Apex Institute of Technology Chandigarh University Mohali India University Centre for Research and Development Chandigarh University Mohali India

ISBN: (数字)9798350394474

ISBN: (纸本)9798350394481

The advent of cloud computing has reshaped the landscape of application deployment and management, ushering in an era characterized by unprecedented flexibility, scalability, and agility. In this context, containerization technologies, exemplified by Docker, and container orchestration platforms, epitomized by Kubernetes, have emerged as pivotal enablers of modern cloud deployments. These technologies promise efficient application packaging, seamless scalability, and simplified DevOps practices. However, their rapid adoption has brought forth a myriad of challenges and opportunities at the intersection of containerization and cloud computing. This research paper embarks on an exploration of containerization technologies and their role in contemporary cloud environments. It delves into the intricacies of Docker and Kubernetes, elucidating their architecture, components, and fundamental principles. Furthermore, it investigates the evolving landscape of modern cloud deployments, emphasizing the transition from traditional infrastructure to cloud-native paradigms.

关键词： Cloud computing DevOps Scalability Computer architecture Packaging Containers convergence

来源：评论

学校读者我要写书评

暂无评论

EVA: PRACTICAL SECOND-ORDER OPTIMIZATION WITH KRONECKER-VECTORIZED APPROXIMATION 11

EVA: PRACTICAL SECOND-ORDER OPTIMIZATION WITH KRONECKER-VECT...

引用

11th international conference on Learning Representations, ICLR 2023

作者： Zhang, Lin Shi, Shaohuai Bo, Li Hong Kong University of Science and Technology Hong Kong Harbin Institute of Technology Shenzhen China

Second-order optimization algorithms exhibit excellent convergence properties for training deep learning models, but often incur significant computation and memory overheads. This can result in lower training efficiency than the first-order counterparts such as stochastic gradient descent (SGD). In this work, we present a memory- and time-efficient second-order algorithm named Eva with two novel techniques: 1) we construct the second-order information with the Kronecker factorization of small stochastic vectors over a mini-batch of training data to reduce memory consumption, and 2) we derive an efficient update formula without explicitly computing the inverse of matrices using the Sherman-Morrison formula. We further provide a theoretical interpretation of Eva from a trust-region optimization point of view to understand how it works. Extensive experimental results on different models and datasets show that Eva reduces the end-to-end training time up to 2.05× and 2.42× compared to first-order SGD and second-order algorithms (K-FAC and Shampoo), respectively. © 2023 11th international conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Optimization

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 << < 101 102 103 104 105 106 107 108 109 110 > >>

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：