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

98 篇 会议
57 篇 期刊文献

馆藏范围

155 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

94 篇 理学
- 41 篇 数学
- 32 篇 物理学
- 17 篇 生物学
- 16 篇 化学
- 10 篇 统计学（可授理学、...
- 3 篇 大气科学
- 3 篇 系统科学
88 篇 工学
- 49 篇 计算机科学与技术...
- 40 篇 软件工程
- 18 篇 信息与通信工程
- 16 篇 化学工程与技术
- 14 篇 生物工程
- 9 篇 电气工程
- 9 篇 控制科学与工程
- 8 篇 力学（可授工学、理...
- 8 篇 电子科学与技术（可...
- 6 篇 光学工程
- 6 篇 材料科学与工程（可...
- 5 篇 土木工程
- 5 篇 农业工程
- 5 篇 安全科学与工程
- 4 篇 网络空间安全
- 3 篇 水利工程
- 3 篇 石油与天然气工程
- 3 篇 交通运输工程
- 3 篇 环境科学与工程（可...
21 篇 管理学
- 12 篇 图书情报与档案管...
- 10 篇 管理科学与工程(可...
5 篇 医学
- 3 篇 基础医学(可授医学...
3 篇 经济学
- 3 篇 应用经济学
3 篇 农学
1 篇 法学

主题

5 篇 image enhancemen...
4 篇 object detection
4 篇 pseudovector
4 篇 feature extracti...
3 篇 convolution
2 篇 channel state in...
2 篇 simulation
2 篇 signal processin...
2 篇 curl
2 篇 rain
2 篇 correlation
2 篇 antennas
2 篇 scalar
2 篇 classification (...
2 篇 accuracy
2 篇 computer vision
2 篇 measurement
2 篇 nonlinear
2 篇 training
2 篇 convolutional ne...

机构

47 篇 school of inform...
25 篇 key laboratory o...
18 篇 key laboratory o...
11 篇 school of mathem...
11 篇 key laboratory o...
10 篇 key laboratory o...
10 篇 school of mathem...
9 篇 key laboratory o...
8 篇 zhejiang ocean u...
8 篇 key laboratory o...
8 篇 key laboratory o...
7 篇 school of inform...
7 篇 zhejiang ocean u...
6 篇 zhejiang ocean u...
6 篇 school of mathem...
5 篇 school of mathem...
4 篇 tianfu college o...
4 篇 school of inform...
3 篇 college of infor...
3 篇 key laboratory o...

作者

17 篇 gu shenming
13 篇 wang chao
11 篇 yang chuansheng
10 篇 shenming gu
8 篇 chao wang
8 篇 chen hongming
7 篇 peng li
6 篇 yang yueting
6 篇 xue-ping cheng
6 篇 yang kun
6 篇 anhui tan
6 篇 ye qihong
5 篇 chuansheng yang
5 篇 tan anhui
5 篇 ding jianjun
5 篇 kun yang
5 篇 xiao-ping qin
5 篇 hongming chen
5 篇 wang na-er
5 篇 yueting yang

语言

153 篇 英文
1 篇 其他
1 篇 中文

检索条件"机构=Key Laboratory of Oceanographic Big Data Mining-& Application of Zhejiang Province"

共 155 条记录，以下是61-70 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

Gaussian process multi-label classification based on multi-view similarity fusion 22

Gaussian process multi-label classification based on multi-v...

引用

Proceedings of the 2022 4th International Conference on Robotics, Intelligent Control and Artificial Intelligence

作者： Hui Xiang Shenming Gu School of Information Engineering Zhejiang Ocean University China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University China

ISBN: (纸本)9781450398343

Multi-view multi-label learning serves as a vital framework for learning from objects with diverse representations and rich semantics. The Gaussian process (GP), as an efficient and flexible Bayesian nonparametric model, the GP has effectively solved various tasks in machine learning. However, the Gaussian process has rarely been directly applied to multi-view multi-label learning scenarios. Therefore, in this paper, we propose a new multi-view multi-label learning method (mvml-DSimGP) based on the Gaussian pass latent variable model (GPLVM), which consists of similar non-parametric mapping function learning, rule constraint learning and label learning. Similarity nonparametric study mapping function for multiple-views data analysis, it studied the view within the similarity and latent mapping function between the parameters. On the basis of the similarity of nonparametric function learning, regular constraints are introduced, and put forward multi-label learning. Instances with similar label information are encouraged to have similar output representations in the embedded space, making it sufficient discernment in the embedded space. Numerous experiments on real-world datasets clearly show that mvml-DSimGP has good performance compared to other general multi-view multi-label learning methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature Enhancement Composition Model for Heavy Rain Removal on Single Image

Feature Enhancement Composition Model for Heavy Rain Removal...

引用

2021 International Conference on Computer Graphics, Artificial Intelligence, and data Processing, ICCAID 2021

作者： Xu, Xufeng Wang, Quanqing Pan, Xiaomiao Pan, Qiang Yang, Yueting Wang, Chao School of Information Engineering Zhejiang Ocean University Zhejiang Zhoushan316022 China School of Mathematics and Statistics Beihua University Jilin Jilin132013 China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhejiang Zhoushan316022 China

ISBN: (数字)9781510652170

ISBN: (纸本)9781510652163

The current single image rain removal method is not ideal in the task of rain and haze removal. In this paper, based on the physical imaging mechanism under heavy rain conditions, a feature enhanced composition model, FEC-Net, is constructed by combining physical model-driven and data-driven methods. The feature maps, which contain rain streaks, atmospheric light, and transmission map information were obtained by three convolution layers. These feature maps are enhanced by the feature enhancement module. Finally, a clear image is obtained according to the formula of the atmospheric scattering model. The selective enhanced processing of key output data greatly improves the processing effect of the network. Extensive experiments show that our FEC-Net achieves better accuracy and visual improvements against state-of-the-art methods. © 2022 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Nailfold Capillary Segmentation Based on U-Net and Attention Mechanism 23

Nailfold Capillary Segmentation Based on U-Net and Attention...

引用

3rd International Conference on Bioinformatics and Intelligent Computing, BIC 2023

作者： Chen, Shupin Wei, Dan Gu, Shenming Yang, Zhangru School of Information Engineering Zhejiang Ocean University Zhoushan316022 China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhoushan316022 China Department of Radiation Oncology Shanghai Chest Hospital Shanghai Jiao Tong University No. 241 West Huaihai Road Shanghai200030 China

ISBN: (纸本)9798400700200

Microcirculation refers to the blood circulation composed of arterioles and venules, which can be used as a reference indicator for doctors to diagnose diseases. The traditional manual reading method is relatively time-consuming and labor-consuming and is not conducive to the standardization and digitization of diagnosis. A feasible way to solve this problem is to use machine learning to assist in image processing and diagnosis. In this study, we proposed a method to segment the nailfold vascular images based on the U-Net backbone network combined with the residual mechanism and the attention mechanism. The results show that: 1. Adding the CBAM attention mechanism can improve the anti-noise ability of the model. 2. Using residual blocks to replace the convolution blocks of the backbone network can improve the accuracy of models. 3. Contrast enhancement can improve the accuracy of blood vessel segmentation. The optimal method in this study is Res_CBAM_Unet and the contrast enhancement uses CLAHE (clipLimit = 2). The overall accuracy is 94.31%, the Dice score is 0.8297, the IoU score is 0.7090, the VOE score is 0.2910. The generalization ability of the proposed method is verified on the public dataset DRIVE. The results show that the accuracy of the proposed method is equivalent to the state-of-the-art methods, and it has an advantage in the sensitivity. This paper provides an effective method for nailfold capillary segmentation, which lays a foundation for the automation of diagnosis based on microcirculation images. © 2023 ACM.

关键词： Microcirculation

来源：评论

学校读者我要写书评

暂无评论

Design of a high-speed SP16T switch for a TDM radio sounder

Design of a high-speed SP16T switch for a TDM radio sounder

引用

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Xuyang Chen Kun Yang Yushuo Wang Jianjun Ding Youzhen Zhang Vidar Ringset Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhoushan China Sustainable Communication Technologies SINTEF Digital Trondheim Norway

Many radio frequency (RF) channels were frequently needed for massive MIMO systems, which significantly raised hardware prices. Therefore, the significance of RF switch has substantially expanded with the ongoing advancement of massive MIMO technology. In this paper, a 5 MHz–6 GHz SP16T RF high–speed switch design for a time-division multiplexing (TDM) radio sounder is presented, which can be further cascaded for a TDM massive MIMO channel sounder. The measured insertion loss, isolation and return Loss are frequency-dependent and vary between [-3.1, -4.6] dB, [-30, -100] dB and [-15, -60] dB, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Learning with Label-Specific Feature Selection via Local Positive and Negative Correlation

Multi-Label Learning with Label-Specific Feature Selection v...

引用

Artificial Intelligence, Networking and Information Technology (AINIT), International Seminar on

作者： Shuxin Xia School of Information Engineering Zhe Jiang Ocean University Zhoushan China Key Laboratory of Oceanographic Big Data Mining and Application Zhejiang Province School of Information Engineering Zhejiang Ocean University Zhoushan China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

High dimension data increasingly emerged in many application areas. Feature selection methods are widely studied to solve the issues, playing a crucial role in eliminating redundant or irrelevant feature. Previous feature selection algorithms seldom consider the fact that each label might be determined by its specific features, which has its own characteristics. Meanwhile, they often neglect mutual exclusion among labels, named “negative label correlations” and assume labels share global correlation in exploring label correlation. To address the above problem, we propose a novel algorithm called “Multi-label learning with label-specific feature selection via local positive and negative correlation” (LLCPN-MIFS). Multiple datasets manifest that the effectiveness of the proposed method.

关键词： Seminars Dimensionality reduction Correlation Redundancy Feature extraction Information technology Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Optimal Scale Selection in Multi-Scale Interval-Set Decision Tables

Optimal Scale Selection in Multi-Scale Interval-Set Decision...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Zhen-Huang Xie Wei-Zhi Wu Lei-Xi Wang School of Information Engineering Zhejiang Ocean University Zhoushan Zhejiang China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhoushan Zhejiang China

In traditional interval-set information systems (ISISs), each attribute is single-scale. However, processing and analyzing data at different scales is often necessary for practical applications. This paper introduces the granular information transformation into multi-scale interval-set information systems (MISISs), defines the similarity relation between objects in MISISs, and defines the rough approximation and correlation properties at different scales studied. Then, we propose the multi-scale interval-set decision table (MISDT) concept and discuss the monotonicity of scale variation of the positive region, generalized decision and positive complementarity conditional entropy. Then, we give three criteria for determining the optimal scales and discuss the relationship among the optimal scales of MISDTs. Finally, give heuristic algorithms and examples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A CEEMDAN-QPSO-BiLSTM Based Hybrid Model for Water Quality Parameter Forecasting

A CEEMDAN-QPSO-BiLSTM Based Hybrid Model for Water Quality P...

引用

Electronic Information Engineering and Computer Technology (EIECT), International Conference on

作者： Yongwen Guo Hongming Chen Juntao Huang Yilei Lin Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhoushan China College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen China

Water contamination is a major concern worldwide due to its impact on the global ecology. Accurate forecasting of water quality parameters is crucial for effective water contamination control. However, existing models face challenges in accurately predicting water quality series due to their nonlinearity and non-stationarity. Additionally, further investigation is needed to find out the performance of the Bidirectional Long Short-Term Memory network (BiLSTM) when combined with optimization of signal processing and adjustment of hyperparameters. In this article, we introduce a novel hybrid approach named CEEMDAN-QPSO-BiLSTM, which combines three techniques - Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Quantum behaved Particle Swarm optimization (QPSO), and BiLSTM - for predicting water quality parameters. To evaluate the effectiveness of this hybrid model, we developed four benchmark models, namely LSTM, BiLSTM, PSO-BiLSTM, and QPSO-BiLSTM, and compared their predictive accuracy with that of our hybrid approach. The training and testing of these models utilized actual water quality data from the Chinese National Marine Environmental Monitoring Center’s official system, specifically focusing on Dissolved Oxygen (DO), pH value, and Chemical Oxygen Demand (COD) parameters. The experimental results show that the CEEMDAN-QPSO-BiLSTM surpasses the baseline models, providing better error performance and prediction accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A survey of ship target feature extraction based on video surveillance

A survey of ship target feature extraction based on video su...

引用

2021 International Conference on Computer, Communication, Control, Automation and Robotics, CCCAR 2021

作者： Bi, Zhenbo Zhang, Shiyou Wu, Yuanhong Wang, Guangwei Qi, Changshong Information Engineering Zhejiang Ocean University Zhejiang Zhoushan316022 China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhejiang Zhoushan316022 China

Ship target feature extraction plays an important role in ship recognition and tracking based on video surveillance. However, the current feature extraction of ship targets based on video surveillance does not have a complete summary, so this article reviews these methods. This article summarizes the main ship target feature extraction methods used in ship target recognition and tracking in different application environments, including traditional artificial ship feature extraction and automated learning ship feature extraction. It focuses on the core ideas, advantages and disadvantages of the representative methods in each type of problem, and discusses the current problems in the feature extraction of ship targets and the future development of feature extraction technology. © Published under licence by IOP Publishing Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Identification of Phtato Leaf Disease Based on The TS-Resnet Deep Learing Method

Identification of Phtato Leaf Disease Based on The TS-Resnet...

引用

International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)

作者： Xiao-Yue Duan Shen-Ming Gu School of information Engineering Zhejiang Ocean University Zhoushan China Key Laboratory of Oceanographic Big Data Mining&Application of Zhejiang Province Zhejiang Ocean University Zhoushan China

At present, the incidence of potato disease is large, the disease is complex, and it is difficult to control, which seriously affects the potato yield and quality. Therefore, in order to realize the potato disease image recognition technology under small sample data, by using attention mechanism, transfer learning and data enhancement technology, the potato leaf disease image is accurately analyzed. This paper proposes a potato leaf disease recognition method based on TS-ResNet(Transform learning and SE) deep learning method. Based on the original ResNet101 model, its full connectivity layer is modified to add transfer learning and attention mechanism. In order to increase the number of potato disease part of the data set, the original graph can be flipped, horizontal flip and other operations to avoid the phenomenon of overfitting in the original model. The results of this study can provide some support for the intelligent research of potato leaf disease identification.

关键词：

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16页 << < 3 4 5 6 7 8 9 10 11 12 > >>

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：