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

717 篇 会议
387 篇 期刊文献
4 册 图书

馆藏范围

1,108 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

757 篇 工学
- 446 篇 计算机科学与技术...
- 423 篇 软件工程
- 223 篇 控制科学与工程
- 127 篇 信息与通信工程
- 116 篇 机械工程
- 106 篇 生物工程
- 73 篇 环境科学与工程（可...
- 67 篇 生物医学工程（可授...
- 59 篇 电气工程
- 57 篇 光学工程
- 49 篇 仪器科学与技术
- 49 篇 化学工程与技术
- 41 篇 电子科学与技术（可...
- 34 篇 交通运输工程
- 28 篇 材料科学与工程（可...
- 26 篇 安全科学与工程
- 24 篇 动力工程及工程热...
- 20 篇 土木工程
374 篇 理学
- 178 篇 数学
- 110 篇 生物学
- 80 篇 物理学
- 53 篇 系统科学
- 48 篇 统计学（可授理学、...
- 40 篇 化学
- 19 篇 大气科学
216 篇 管理学
- 159 篇 管理科学与工程(可...
- 60 篇 图书情报与档案管...
- 28 篇 工商管理
37 篇 医学
- 30 篇 临床医学
- 24 篇 基础医学(可授医学...
16 篇 法学
13 篇 经济学
9 篇 农学
6 篇 教育学
1 篇 文学
1 篇 军事学
1 篇 艺术学

主题

48 篇 feature extracti...
34 篇 training
28 篇 deep learning
28 篇 predictive model...
26 篇 neural networks
24 篇 visualization
24 篇 semantics
20 篇 reinforcement le...
19 篇 convolution
16 篇 three-dimensiona...
16 篇 mathematical mod...
15 篇 object detection
15 篇 forecasting
14 篇 adaptive dynamic...
14 篇 robots
14 篇 adaptation model...
14 篇 wastewater treat...
13 篇 computational mo...
13 篇 accuracy
13 篇 optimal control

机构

282 篇 faculty of infor...
258 篇 beijing key labo...
101 篇 beijing key labo...
81 篇 university of ch...
52 篇 engineering rese...
51 篇 school of artifi...
34 篇 beijing laborato...
30 篇 beijing universi...
27 篇 beijing key labo...
26 篇 guangdong engine...
23 篇 beijing laborato...
22 篇 college of elect...
22 篇 beijing institut...
21 篇 beijing laborato...
19 篇 key laboratory o...
19 篇 beijing key labo...
17 篇 beijing engineer...
17 篇 shenzhen institu...
17 篇 beijing universi...
16 篇 school of intern...

作者

59 篇 junfei qiao
48 篇 xiaoli li
39 篇 qiao junfei
35 篇 kang wang
32 篇 ding wang
32 篇 gang xiong
30 篇 han honggui
30 篇 jia kebin
28 篇 honggui han
27 篇 jian tang
23 篇 zuo guoyu
22 篇 zhen shen
21 篇 xiong gang
21 篇 kebin jia
21 篇 yang li
21 篇 feng jinchao
20 篇 xiaogang ruan
20 篇 guoyu zuo
19 篇 wu xinyu
18 篇 songmin jia

语言

1,031 篇 英文
61 篇 其他
17 篇 中文

检索条件"机构=Beijing Key Laboratory of Computing Intelligence and Intelligent System"

共 1108 条记录，以下是821-830 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：

Prediction of PM2.5 Concentration Based on CEEMD-LSTM Model

Prediction of PM2.5 Concentration Based on CEEMD-LSTM Model

引用

第三十八届中国控制会议

作者： Jiangeng Li Jianing Shen Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

At present, there are serious air pollution problems in most cities in China. As one of the main atmospheric pollutants, PM has caused serious harm to peopled health. In order to improve the accuracy of PM 2.5 concentration prediction, this paper proposes a new hybrid model based on com plementary ensemble empirical mode decomposition（CEEMD） and Long Short-Term Mem ory（LSTM） to predict daily PM 2.5 concentration. The daily PM concentration and meteorological data from January 2010 to December 2014 released by the US Embassy are selected as experim ental data. Compared with extreme learning machine（ELM）, Support Vector Regression（SVR） and Long Short-Term Memory（LSTM）, the CEEM D-LSTM m odel shows a higher prediction ability.

关键词： PM2.5 hybrid model ELM LSSVM CEEM D-LSTM

来源：评论

学校读者我要写书评

暂无评论

Simple and Efficient Smoke Segmentation Based on Fully Convolutional Network

Simple and Efficient Smoke Segmentation Based on Fully Convo...

引用

2019 2nd International Conference on Informatics, Control and Automation (ICA 2019)

作者： Mao-shen LIU Xiao-tian XIE Ke GU Jun-fei QIAO Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

In this paper,a shallow fully convolutional network for image smoke segmentation is designed to solve the real-time monitoring of smoke emitted by the flare *** algorithm can quickly and effectively distinguish the smoke area in the image,which can determine the actions of the flare stack control system to improve combustion *** main difficulty in segmenting the smoke in the flare stack image is the variegated texture and shape of the smoke and the varying brightness,color and other disturbances of the *** to the above problems,we only use one layer of convolution to extract large numbers of low level features such as texture and color,and further utilize two special convolutional layers,separable convolution and 1×1 convolution,to map the final segmentation *** experiments on different data sets,our algorithm has the best accuracy and efficiency.

关键词： Fully convolutional network Smoke segmentation Flare stack smoke

来源：评论

学校读者我要写书评

暂无评论

Phase Partition and Monitoring of Batch Process Based on FOM-KECA

Phase Partition and Monitoring of Batch Process Based on FOM...

引用

第30届中国过程控制会议（CPCC 2019）

作者： Zhang Xiangyu Chang Peng Li Zey WangPu Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

Batch processes often have multiple operation phases, meanwhile the process variables have complex nonlinear relationships and process data often does not satisfy the Gaussian *** these lead to the performance degradation or even failure of traditional statistical process monitoring *** response to these problems, a phase partition method is proposed, Firstly, the number of clusters is automatically determined by fast search and find of density peaks algorithm, then, the principle component load matrix is clustered by a warped K-means(WKM) algorithm to generate ordered phase division results;Secondly, in each sub-phase, in order to obtain non-Gaussian information of process data while coping with the nonlinear relationship between process variables, a FOM-KECA modeling method which is a combination of Forth Order Moment(FOM) and Kernel Entropy Component Analysis(KECA) algorithm is ***, the validity of the proposed method is verified by penicillin fermentation simulation platform and a application in Escherichia coli fermentation preparation process.

关键词： Batch process Fault monitoring Phase Partition Kernel Entropy Component Analysis

来源：评论

学校读者我要写书评

暂无评论

Fault monitoring and Diagnosis of Process Industry Based on Fourth Order Moment and Singular value decomposition

Fault monitoring and Diagnosis of Process Industry Based on ...

引用

第30届中国过程控制会议（CPCC 2019）

作者： Chang Peng Qiao Junfei Ding Chunhao Lu Ruiwei Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

Principal Component Analysis(PCA) and Partial Least Squares(PLS) are frequently prescribed for process industry monitoring, but their application in industrial sites is greatly limited for they cannot process data with non-Gaussian ***, Independent Component Analysis(ICA) has emerged as powerful modeling method for non-Gaussian process ***, the ICA-based modeling method will cause double loss of data information in feature *** is first because when PCA algorithm is used to whiten the original data, the smaller principal component is ***, when selecting independent components, some smaller independent components will be discarded according to the evaluation *** above two data feature extraction methods may discard useful information for fault monitoring, which will inevitably lead to inaccurate fault *** solve this problem, a fault monitoring and diagnosis method based on Fourth Order Moment(FOM) analysis and Singular Value Decomposition(SVD) is ***, the fourth-order moments of each process variable are constructed ***, the data space of the fourth-order moments is decomposed by singular value decomposition to establish the global monitoring ***, the contribution diagram is drawn and the fault diagnosis is carried out based on the global monitoring *** proposed method is applied to Tennessee Eastman(TE) simulation platform, and its effectiveness and feasibility are verified by comparing with PCA and ICA.

关键词： Process monitoring Fault Diagnosis Forth Order Moment Singular Value Decomposition

来源：评论

学校读者我要写书评

暂无评论

Dioxin Emission Concentration Forecasting Approach Based on Latent Feature Extraction and Selection for Municipal Solid Waste Incineration

Dioxin Emission Concentration Forecasting Approach Based on ...

引用

第三十八届中国控制会议

作者： Jian Tang Zihao Guo Junfei Qiao Zhe Xu Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

As one of the prohibit by-products of municipal solid waste incineration(MSWI) process, dioxin(DXN) is difficult to be on-line measured in terms of its multi-component characteristic and complexity production mechanism. Normally, DXN emission concentration is detected by using two steps, which are online flue gas acquirement with special instruments in the factory and off-line flue gas analysis with expensive instruments in the laboratory. In this paper, a new DXN emission concentration forecasting approach based on latent feature extraction and selection for the practical MSWI process is proposed. At first, latent features of the high dimensional process variables are extracted based on principal component analysis(PCA). Then, by using mutual information(MI) and pre-set feature selection ratio, these latent features are estimated and selected. At last, these selected latent features are fed into least-square support machine vector(LS-SVM) model with super-parameter adaptive selection strategy. Simulation results based on the practical DXN emission data of an industrial MSWI process of China show effectiveness of the proposed approach.

关键词： Municipal solid waste incineration(MSWI) dioxins(DXN) Latent feature selection Mutual information(MI) Least square-support vector machine(LS-SVM) Super-parameter adaptive selection

来源：评论

学校读者我要写书评

暂无评论

Implementation and Application of Video Distribution Technology Based on OpenGL

Implementation and Application of Video Distribution Technol...

引用

第二届先进电子材料、计算机与材料工程国际学术会议（AEMCME 2019）

作者： Jiangeng Li Minjie Fan Guangsheng Wang Rihui Sun Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

The panoramic video contains a wealth of information that vividly reproduces the surrounding scene. However, the larger video information puts forward higher requirements for data transmission, interactivity and real-time. All the video information directly shows that the phenomenon of stagnation and black screen is easy to occur, and the user's traffic is greatly consumed, so that the payment cost of the terminal is large. In a traditional live video broadcast, the information displayed by the client is information with a fixed perspective. The client has no right to select the information, but only displays the obtained information. In order to solve the above problems, this paper has improved the traditional live broadcast mode. In this new live broadcast mode, the host side synthesizes the collected surrounding scene into a super wide-angle video. Then with the OpenG L technology, the host side performs the texture mapping, projection and other steps on the panoramic video. The host then distributes the video to the client. As a result, the client not only gets undistorted video, but also interacts with the server in real time. This approach greatly enhances the visual experience of the client.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A multi-task learning convolutional neural network for object pose estimation

A multi-task learning convolutional neural network for objec...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Wang, Yurui Jin, Shaokun Ou, Yongsheng Shenzhen Institutes of Advanced Technology CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Beijing China University of Chinese Academy of Sciences Beijing China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

ISBN: (纸本)9781728163215

Estimating 6D poses of objects from RGB images is very crucial for robots to interact with the surrounding environment and to cooperate with humans. It is a challenging problem due to the various shapes of objects, the occlusions among objects, as well as the complexity of the scene. In this study, we present a new multi-task convolutional neural network for 6D object pose estimation, which also learns the object region in the image to further improve the estimation result. A weighted loss computed from the training samples is adopted to guarantee that the components of the estimated pose are equally accurate. Additionally, we sythesize new virtual data based on the existing training data so as to overcome the possible adverse situation caused by insufficiency of training data. Experiments on the YCB-video dataset are undertaken to validate the effectiveness of the proposed method. © 2019 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An In-Motion Initial Alignment Algorithm for SINS Using Lie Group Matrix Kalman Filter

An In-Motion Initial Alignment Algorithm for SINS Using Lie ...

引用

Chinese Automation Congress (CAC)

作者： Fujun Pei Desen Zhu Shunan Yin Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence Intelligent System Beijing China

In this paper, an in-motion initial alignment algorithm based on Lie group matrix kalman filter is proposed. According to the Lie group's properties and the attitude optimization-based initial alignment idea, the attitude matrix is decomposed into three continuous special orthogonal matrices to separate the rotation information and motion information under the in-motion conditions. A linear system model is established based on the differential equation of Lie group, which can replace the traditional quaternion model and avoid the non-uniqueness of unit quaternion representation. Then the Lie Group Matrix Kalman Filter is proposed for estimating the initial inertial matrix directly. And the Simplified Lie Group Matrix Kalman Filter with special process noise is proposed in some specific situations. From the simulation, the alignment accuracy and stability of the two algorithms satisfies the SINS navigation requirements. These two methods have good application prospects for the in-motion initial alignment of SINS.

关键词： C# languages

来源：评论

学校读者我要写书评

暂无评论

Improved visual-inertial navigation system using self-adjusting entropy difference

Improved visual-inertial navigation system using self-adjust...

引用

Chinese Automation Congress (CAC)

作者： Fujun Pei Di Wang Haonan Song Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China

The visual-inertial navigation system of LK-Optical Flow is very sensitive to the environment of different light intensity. In this paper, an adaptive VINS, based on image entropy difference is proposed, which can adjust the emphasis of the weight in the optimization function at any time. The algorithm uses the entropy theory of continuous image to change little, constructs the weight factor of the visual estimation in the optimization function, adjusts the weight of IMU and visual online, and realizes the adaptive estimation of the position and attitude of the object. The method is applied to VINS, to overcome the problem that the poor image quality of the system leads to the degradation of system performance. Finally, the outdoor experimental results verify the performance of the proposed adaptive entropy difference VINS(EE-VINS).

关键词： Entropy Cameras Visualization Optimization Gray-scale Mathematical model Navigation

来源：评论

学校读者我要写书评

暂无评论

Identification of MSWI Furnace Temperature Model Based on Weighted Adaptive Particle Swarm optimization

Identification of MSWI Furnace Temperature Model Based on We...

引用

Chinese Automation Congress (CAC)

作者： Haijun He Jian Tang Junfei Qiao Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System University of Technology Beijing China

In order to obtain the accurate dynamic model of the furnace temperature of a solid waste incineration plant, the intelligent algorithm based on weighted adaptive particle swarm optimization algorithm is used for parameter identification. First, the transfer function model of furnace temperature is determined by burning characteristic analysis. Then, the model parameters to be identified are determined. Finally, the parameters of primary air-furnace temperature channel transfer function model are identified by weighted adaptive particle swarm optimization using preprocessed data; In the iteration process, the algorithm can obtain the optimal weight value for each iteration adaptively according to the objective function value and maximum and minimum value of the weight, which improves the identification accuracy of the algorithm. The simulation results show that the established transfer function model can fully describe the dynamic characteristics of this condition, and proves the effectiveness of the weighted adaptive particle swarm optimization algorithm, which provides a basis for subsequent multi-channel model identification of furnace temperature.

关键词： Furnaces Incineration Atmospheric modeling Temperature Heuristic algorithms Data models Solids

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111页 << < 79 80 81 82 83 84 85 86 87 88 > >>

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：