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

3,054 篇 期刊文献
2,638 篇 会议
4 册 图书

馆藏范围

5,696 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,722 篇 工学
- 2,390 篇 计算机科学与技术...
- 1,946 篇 软件工程
- 852 篇 信息与通信工程
- 471 篇 控制科学与工程
- 445 篇 电气工程
- 443 篇 生物工程
- 326 篇 电子科学与技术（可...
- 299 篇 化学工程与技术
- 258 篇 生物医学工程（可授...
- 252 篇 机械工程
- 229 篇 光学工程
- 180 篇 材料科学与工程（可...
- 166 篇 动力工程及工程热...
- 163 篇 交通运输工程
- 145 篇 仪器科学与技术
- 142 篇 建筑学
- 135 篇 土木工程
2,074 篇 理学
- 1,018 篇 数学
- 534 篇 物理学
- 525 篇 生物学
- 334 篇 统计学（可授理学、...
- 308 篇 化学
- 148 篇 系统科学
1,054 篇 管理学
- 621 篇 管理科学与工程(可...
- 482 篇 图书情报与档案管...
- 223 篇 工商管理
299 篇 医学
- 243 篇 临床医学
- 162 篇 基础医学(可授医学...
174 篇 法学
- 141 篇 社会学
150 篇 农学
112 篇 经济学
- 112 篇 应用经济学
42 篇 教育学
16 篇 文学
13 篇 军事学
7 篇 艺术学
1 篇 历史学

主题

176 篇 semantics
149 篇 feature extracti...
140 篇 deep learning
133 篇 training
92 篇 computational mo...
82 篇 data models
78 篇 machine learning
74 篇 convolution
70 篇 data mining
69 篇 predictive model...
62 篇 neural networks
61 篇 accuracy
56 篇 object detection
55 篇 visualization
52 篇 big data
52 篇 graph neural net...
50 篇 optimization
49 篇 task analysis
48 篇 contrastive lear...
48 篇 forecasting

机构

165 篇 school of inform...
147 篇 key laboratory o...
132 篇 school of econom...
97 篇 state key labora...
94 篇 school of comput...
79 篇 fujian provincia...
76 篇 henan key labora...
73 篇 college of big d...
73 篇 school of comput...
73 篇 research center ...
72 篇 school of comput...
69 篇 guangdong key la...
69 篇 university of ch...
60 篇 hubei key labora...
53 篇 shandong provinc...
53 篇 shenzhen researc...
51 篇 key laboratory o...
50 篇 school of inform...
49 篇 national enginee...
48 篇 peng cheng labor...

作者

45 篇 shi yong
41 篇 zhang rui
40 篇 yong shi
40 篇 chen hong
38 篇 chang kuo-chi
37 篇 wu xindong
37 篇 pan jeng-shyang
33 篇 liu yang
33 篇 wang meng
32 篇 xue xingsi
32 篇 du xiaoyong
32 篇 zhang jing
31 篇 liu jun
30 篇 li cuiping
29 篇 wen ji-rong
29 篇 huang qingming
28 篇 chu kai-chun
28 篇 xindong wu
25 篇 hong chen
24 篇 niyato dusit

语言

5,182 篇 英文
404 篇 其他
121 篇 中文
3 篇 德文
3 篇 法文

检索条件"机构=Key Laboratory of Knowledge Engineering with Big Data"

共 5696 条记录，以下是961-970 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：

Side-Information Aided Adaptive Fusion Algorithm for Multiuser Detection in Grant-Free Non-Orthogonal Multiple Access Networks

Side-Information Aided Adaptive Fusion Algorithm for Multius...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Han Yuan Congcong Ma Kun Yang Tong Peng School of Information Engineering Zhejiang Ocean University Key Laboratory of Oceanographic Big Data Mining and Application Zhoushan Zhejiang People’s Republic of China

ISBN: (数字)9798350378412

ISBN: (纸本)9798350378429

Grant-free non-orthogonal multiple access (GFNOMA), acting as a promising technique to provide high connection density with low latency, serves multiple users simultaneously with efficient spectrum sharing and simplified resource management. The sparsity of user activity naturally exists in the uplink GF-NOMA system, which makes compressed sensing (CS) technology applied to multi-user detection (MUD). In this paper, we propose a side-information aided adaptive fusion (SIAF) algorithm to improve the MUD performance in the uplink GFNOMA system. The proposed algorithm reconstructs the signal without knowing the signal sparsity, and makes full use of the structural characteristics of the temporal correlation in the GFNOMA system to obtain accurate active user estimation. In the post-processing of the algorithm, we obtain low data error rate by fusing two conventional CS algorithms. The simulation results show that our algorithm has better MUD performance than the conventional CS algorithms.

关键词： Multiuser detection NOMA Adaptive systems Accuracy Fuses Simulation Sensors

来源：评论

学校读者我要写书评

暂无评论

PP-Grading: Hierarchical Authorization using Polarization Pruning

PP-Grading: Hierarchical Authorization using Polarization Pr...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Yujia Zhu Ruoxi Wang Daoxun Xia School of Big Data and Computer Science Guizhou Normal University Guiyang China Key Laboratory of Information and Computing Science Guizhou Province Guizhou Normal University Guiyang China Engineering Laboratory for Applied Technology of Big Data in Education Guizhou Normal University Guiyang China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

With the popularity of neural networks, more and more service providers are providing us with convenient neural network services. In this situation, it is necessary for service providers to grant hierarchical authorization of the networks to meet the service requirements of different users. Pruning technology, as a mainstream method for modifying neural network structures, can also be applied in the hierarchical authorization of neural networks. This article uses the method of polarization pruning to decentralize and grade neural networks. Firstly, we extract the scale factors of the batch normalization(BN) layer as a measure of the importance of each channel. Then, sparse methods are used to screen for scale factors. In order to make the selected scale factors have more obvious and reasonable truncation intervals, we also use polarization methods to induce clustering of scale factors. According to different grading requirements, we prune the channels corresponding to different quantities of scale factors. The experiment proves that our method has good grading performance on different datasets and different neural networks. Moreover, good grading results can be achieved by pruning only a small portion of the channels.

关键词： Authorization Accuracy Neural networks Education Information technology

来源：评论

学校读者我要写书评

暂无评论

Structure Aware Loss for Deep Unsupervised Industrial Image Registration 24

Structure Aware Loss for Deep Unsupervised Industrial Image ...

引用

24th IEEE International Conference on data Mining Workshops, ICDMW 2024

作者： Shi, Yong Lyu, Mengjin Qi, Zhiquan Chinese Academy of Sciences Research Center on Fictitious Economy and Data Science Beijing100190 China Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management Beijing100190 China University of Nebraska at Omaha College of Information Science and Technology OmahaNE 68182 United States University of Chinese Academy of Sciences School of Computer Science and Technology Beijing100190 China University of Chinese Academy of Sciences School of Economics and Management Beijing100190 China

ISBN: (纸本)9798331530631

Image registration is extensively utilized in industrial applications. However, specific challenges inherent to these environments - such as low texture, significant displacement, and poor lighting conditions - complicate the registration process. This paper introduces a structure-aware loss module tailored to the unique characteristics of industrial images. This module promotes the network's focus on salient regions while emphasizing structural features. Additionally, it is designed as a plug-in component, facilitating integration with any loss function and homography estimation method. We develop an unsupervised registration network and create an industrial dataset to evaluate the module's effectiveness. A series of experiments demonstrate that our structure-aware module significantly enhances registration performance. © 2024 IEEE.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-dimensional Bilingual Teaching Model of Computer Courses Supported by Artificial Intelligence 17th

Research on Multi-dimensional Bilingual Teaching Model of Co...

引用

17th International Conference on Computer Science and Education, ICCSE 2022

作者： Zhao, Changhua Mi, Chunqiao Tangbo School of Computer Science and Engineering Huaihua University Hunan Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China

ISBN: (纸本)9789819924486

Aiming at the problems of the integration of computer course teaching with international teaching and engineering certification, this study designs a multi-dimensional teaching mode of computer courses through the support of Artificial Intelligence. It analyzes the teaching resources, learning services, teaching process and teaching means involved in computer course teaching. Taking the course of "Computer Introduction" as an example, this study explores the multi-dimensional bilingual teaching mode supported by Artificial Intelligence, trains computer talents who meet the ability requirements of the era of Artificial Intelligence, and provides ideas for the teaching innovation of other courses. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

The State of Charge Estimation of Lithium-ion Battery Pack Based on PSO-KELM

The State of Charge Estimation of Lithium-ion Battery Pack B...

引用

Chinese Control and Decision Conference, CCDC

作者： Mengyuan Chen Hongyan Ma Wei He School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China School of Electrical and Information Engineering Institute of Distributed Energy Storage Safety Big Data Beijing Key Laboratory of Intelligent of Processing for Building Big Data Beijing University of Civil Engineering and Architecture Beijing China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

Accurately estimating the State of Charge (SOC) is of great significance for ensuring the safe operation of lithium-ion batteries and preventing overcharging or discharging. However, as SOC is the internal state of the battery unit and cannot be directly measured, it is difficult to obtain accurate SOC values. To improve the estimation accuracy of SOC, this paper establishes a prediction model using Kernel Extreme Learning Machine (KELM), and uses Particle Swarm Optimization (PSO) to optimize the kernel function parameter S and regularization coefficient C of KELM and determine the optimal values, a SOC prediction method for lithium-ion batteries based on PSO-KELM is proposed. The input of the PSO-KELM model is battery voltage, current, and temperature, the output is the actual SOC value. The results show that the root mean square error (RMSE), mean absolute error (MAE), and mean percentage error (MAPE) of SOC prediction are reduced to 2.76%, 2.18%, and 6.89%, increase coefficient of determination (R 2 ) to 0.9919. The PSO-KELM model improves prediction accuracy compared to ELM and KELM models, and has good convergence and generalization properties.

关键词： Lithium-ion batteries Accuracy Extreme learning machines Estimation Predictive models Battery charge measurement data models

来源：评论

学校读者我要写书评

暂无评论

Multi-source Multi-label Feature Selection

Multi-source Multi-label Feature Selection

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiulan Yuan Xuegang Hu Peipei Li Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei City China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei City China

Feature selection for multi-source multi-label data has attracted much attention, because there are a lot of scenarios that produce multiple source data with multi-labels in the real-world applications, which aggravates the problems of dimensional disaster and the label skewness. However, most of existing multi-source feature selection methods miss the multi-label issue while existing multi-label feature selection methods can not select the optimal feature set in the multi-source environment. Motivated by this, we propose a novel feature selection method, called MSMLFS. To be specific, the Inf-FS algorithm is firstly introduced to handle multi-label feature selection for each data source, which considers the label weight in the feature selection. Secondly, the over-sampling mechanism and the inter-source feature fusion method are used to handle the label skewness of multi-label data and the feature selection in multiple sources respectively. Finally, extensive experiments conducted on synthetic and real-world multi-source multi-label data sets demonstrate that the proposed method outperforms several state-of-the-art multi-source or multi-label feature selection methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Latest Technologies on dataset Distillation: A Survey 11

Latest Technologies on Dataset Distillation: A Survey

引用

11th International Conference on Information Technology and Quantitative Management, ITQM 2024

作者： Li, Muyang Qu, Yi Shi, Yong Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China College of Information Science and Technology University of Nebraska at Omaha OmahaNE68182 United States

dataset distillation refers to the process of constructing a smaller dataset based on a larger dataset, so that the training model with the smaller dataset can obtain similar results to the larger dataset. In this paper, we first briefly review the basic methods and some recent advances in this field from the perspectives of meta-learning framework and data matching framework, including the backpropagation through time(BPTT), kernel ridge regression(KRR), decoupled techniques, gradient matching(DC), trajectory matching(MTT) and distribution matching(DM). The results of the plug-and-play approach in recent years are then presented. Finally, we discuss possible future developments from the perspectives of data distillation algorithms on large datasets, the relationship between compress ratio and information contained, more tasks and data modalities, and the use of generative models to improve the distillation results of datasets. © 2024 The Authors.

关键词： data assimilation

来源：评论

学校读者我要写书评

暂无评论

Resolution-Adaptive Representation Learning via Eliminating Abnormal Features for Cross-Resolution Person Re-Identification

Resolution-Adaptive Representation Learning via Eliminating ...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Xing Lu Fengshan Lai Zhixiang Cao Daoxun Xia School of Big Data and Computer Science Guizhou Normal University Guiyang China Key Laboratory of Information and Computing Science Guizhou Province Guizhou Normal University Guiyang China Engineering Laboratory for Applied Technology of Big Data in Education Guizhou Normal University Guiyang China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

Cross-resolution person re-identification(CR-ReID) seeks to overcome the challenge of retrieving and matching specific person images across cameras with varying resolutions. Numerous existing studies utilize established CNNs and ViTs models to resize captured low-resolution (LR) images and align them with high-resolution (HR) image features. However, these methods overlook the potential feature connections between LR and HR images. Consequently, CNNs or ViTs tend to highlight outliers rather than the intended characteristics in LR image attention maps. In this work, we propose the abnormal feature elimination and reconfiguration transformer (ART) network, a novel network architecture, for robust cross-resolution person re-identification tasks. Our proposed method uses a resolution feature discriminator to learn resolution invariant features and outputs feature matrices of images with different resolutions. We utilize output feature matrices to model LR and HR image interactions through cross-resolution landmark agent attention. We aim to mitigate abnormal image features and prioritize the attention on the target person by learning representations from input images of various resolutions. Extensive evaluations on three real-world datasets confirm the excellent results of our approach.

关键词： Representation learning Image resolution Pedestrians Computational modeling Subspace constraints Network architecture Transformers Hardware Information technology Identification of persons

来源：评论

学校读者我要写书评

暂无评论

GA-Net: Gated Attention Mechanism Based Global Refinement Network for Image Inpainting 29

GA-Net: Gated Attention Mechanism Based Global Refinement Ne...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Qiu, Ran Zhao, Shengrong Liang, Hu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350330717

Underwater images are often affected by problems such as light attenuation, color distortion, noise and scattering, resulting in image defects. A novel image inpainting method is proposed to intelligently predict and fill damaged areas for complete and continuous visualization of the image. First, in order to effectively solve the problem of color distortion caused by light refraction in underwater environments, the improved gated attention mechanism is used. This mechanism improves the local details by learning and weighting the important features of the image. Second, gated convolution automatically determines the degree of restoration for each pixel based on local features of the original image. It eliminates distractions such as low contrast and scattering, retaining more original detailed information. By doing so, image inpainting techniques improve the quality and visualization of underwater images. © 2023 IEEE.

关键词： Gated convolution Image inpainting Underwater images

来源：评论

学校读者我要写书评

暂无评论

Traffic optimization method at five-way intersection based on green building materials and signal processing

Traffic optimization method at five-way intersection based o...

引用

2022 International Conference on Signal Processing and Communication Security, ICSPCS 2022

作者： Liang, Zijun Zhan, Xuejuan Kong, Wei Zhao, Yuanyuan Niu, Yiran Peng, Min School of Urban Construction and Transportation Hefei University China Anhui Province Transportation Big Data Analysis and Application Engineering Laboratory China Anhui Province Ordinary University Key Laboratory of Traffic Information and Security China

ISBN: (纸本)9781510660151

With the rapid development of China's economy, the development speed and scale of transportation engineering have also expanded rapidly. But the problem of environmental pollution problems have also gradually emerged, and the use of environmental protection materials has become an inevitable trend of green transportation development. This paper puts forward the traffic optimization method at five-way intersection based on green building materials and signal processing. Firstly, the green and environment protection hot-melt reflective marking paint and color asphalt concrete pavement materials are used to construct the travel space of motor vehicles, non-motor vehicles and pedestrians at five-way intersection. Then, on this basis, the phase design method based on clipping method and the corresponding signal timing method are proposed to optimize the traffic flow travel time at five-way intersection. Finally, the evaluation and analysis is done by the VISSIM traffic simulation software, the results show that this method based on green building materials effectively defines the travel space of five-way intersection. On this premise, the traffic efficiency is further improved through signal processing optimization technology, which effectively reduces the number of conflict point at the five-way intersection and provides a basis for the research on the optimal control of deformed intersections based on green building materials and signal processing. © 2022 SPIE.

关键词： Computer software

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 << < 93 94 95 96 97 98 99 100 101 102 > >>

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：