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

1,606 篇 会议
1,074 篇 期刊文献
3 册 图书

馆藏范围

2,683 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,750 篇 工学
- 897 篇 计算机科学与技术...
- 816 篇 软件工程
- 461 篇 控制科学与工程
- 293 篇 机械工程
- 258 篇 信息与通信工程
- 187 篇 电气工程
- 164 篇 电子科学与技术（可...
- 153 篇 仪器科学与技术
- 132 篇 生物工程
- 119 篇 交通运输工程
- 114 篇 光学工程
- 99 篇 材料科学与工程（可...
- 95 篇 化学工程与技术
- 71 篇 生物医学工程（可授...
- 68 篇 动力工程及工程热...
- 64 篇 航空宇航科学与技...
- 58 篇 土木工程
- 56 篇 力学（可授工学、理...
- 53 篇 安全科学与工程
- 41 篇 建筑学
904 篇 理学
- 467 篇 数学
- 273 篇 物理学
- 168 篇 统计学（可授理学、...
- 136 篇 生物学
- 136 篇 系统科学
- 80 篇 化学
421 篇 管理学
- 297 篇 管理科学与工程(可...
- 130 篇 图书情报与档案管...
- 90 篇 工商管理
49 篇 法学
- 44 篇 社会学
49 篇 医学
40 篇 经济学
24 篇 艺术学
23 篇 农学
13 篇 文学
9 篇 军事学
6 篇 教育学
2 篇 哲学
1 篇 历史学

主题

141 篇 laboratories
131 篇 intelligent syst...
80 篇 feature extracti...
58 篇 computer science
57 篇 support vector m...
50 篇 training
49 篇 control systems
48 篇 automation
47 篇 neural networks
39 篇 semantics
38 篇 data mining
38 篇 robustness
37 篇 machine learning
36 篇 algorithm design...
32 篇 object detection
32 篇 deep learning
32 篇 sun
32 篇 image segmentati...
32 篇 optimization
31 篇 accuracy

机构

182 篇 state key labora...
117 篇 state key labora...
79 篇 state key labora...
78 篇 school of automa...
65 篇 state key labora...
63 篇 qingdao academy ...
56 篇 intelligent tran...
54 篇 state key labora...
53 篇 school of artifi...
52 篇 university of ch...
48 篇 state key labora...
48 篇 department of co...
42 篇 department of co...
42 篇 beijing engineer...
39 篇 state key labora...
36 篇 state key labora...
36 篇 state key labora...
35 篇 state key labora...
35 篇 state key labora...
34 篇 institutes for r...

作者

62 篇 fuchun sun
61 篇 gang xiong
47 篇 fei-yue wang
45 篇 changshui zhang
38 篇 zhidong deng
37 篇 zhen shen
37 篇 zhu xiaoyan
36 篇 xiong gang
36 篇 xiaoqing ding
35 篇 ma shaoping
35 篇 xu hua
35 篇 huaping liu
35 篇 wang fei-yue
34 篇 zhang min
33 篇 zhang bo
33 篇 bo zhang
32 篇 sun maosong
32 篇 liu yiqun
31 篇 zengqi sun
30 篇 peifa jia

语言

2,538 篇 英文
77 篇 中文
69 篇 其他

检索条件"机构=State Key Laboratory of Intelligent Technology& Systems"

共 2683 条记录，以下是2591-2600 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：

Conceiving,Analyzing,Modeling,Verifying and Developing——The Clews of Modeling Open Software Architectures of Robot Controllers

Conceiving,Analyzing,Modeling,Verifying and Developing——Th...

引用

2001 International Conferences on Info-tech and Info-net

作者： Hua Xu Peifa Jia Yannan Zhao State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and TechnologyTsingHua University

Openness is one of the features of modern robot *** many modeling technologies about how to model and develop open robot controllers have been discussed,the focus is always on some detail problems in some *** the relative complete modeling clews have never been *** this paper,an initial modeling clew is *** corresponding contents including basic conceptions,modeling methods,requirement analysis,testing strategies are discussed in details.

关键词： Control systems Robotics Robot Controller Software Engineering

来源：评论

学校读者我要写书评

暂无评论

Kernel MSE algorithm: a unified framework for KFD, LS-SVM and KRR

Kernel MSE algorithm: a unified framework for KFD, LS-SVM an...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jianhua Xu Xuegong Zhang Yanda Li Department of Automation State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China

ISBN: (纸本)0780370449

We generalize the conventional minimum squared error (MSE) method to yield a new nonlinear learning machine by using the kernel idea and adding different regularization terms. We name it kernel minimum squared error (KMSE) algorithm, which can deal with linear and nonlinear classification and regression problems. With proper choices of the output coding schemes and regularization terms, we prove that KMSE is identical to the kernel Fisher discriminant (KFD) except for an unimportant scale factor, and it is directly equivalent to the least square version for support vector machine (LS-SVM). For continuous real output values, we find that KMSE is the kernel ridge regression (KRR) with a bias. Therefore KMSE can act as a general framework that includes KFD, LS-SVM and KRR as its particular cases. In addition, we simplify the formula to estimate the projecting direction of KFD. Experiments on artificial and real world data sets in numerical computation aspects demonstrate that KMSE is a class of powerful kernel learning machines.

关键词： Kernel Machine learning Least squares methods Support vector machines Automation intelligent systems Learning systems Support vector machine classification Least squares approximation Bayesian methods

来源：评论

学校读者我要写书评

暂无评论

Large margin kernel pocket algorithm

Large margin kernel pocket algorithm

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jianhua Xu Xuegong Zhang Yanda Li Department of Autmation State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China

ISBN: (纸本)0780370449

Two attractive advantages of SVM are the ideas of kernels and of large margin. As a linear learning machine, the original pocket algorithm can handle both linearly and nonlinearly separable problems. In order to improve its classification ability and control its generalization, we generalize the original pocket algorithm by using kernels and adding a margin criterion, and propose its kernel and large margin version, which can be referred to as large margin kernel pocket algorithm (LMKPA). The objective is to maximize both the number of correctly classified samples and the distance between the separating hyperplane and those correctly classified samples closest to the hyperplane, in the feature space realized with the kernels. This new algorithm only utilizes an iterative procedure to implement kernel idea and large margin simultaneously. For the linearly separable problems, LMKPA can find a solution that is not only without error, but also almost equivalent to that of SVM with the large-margin goal. For linearly nonseparable problems, its performance is also very close to that of SVM. Experiments in numeral computation aspects show that the performance of LMKPA is close to that of SVM but the algorithm is much simpler.

关键词： Kernel Support vector machines Support vector machine classification Iterative algorithms Machine learning Machine learning algorithms intelligent systems Learning systems Robustness Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Editing support vector machines

Editing support vector machines

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Haixin Ke Xuegong Zhang Department of Automation State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing China

ISBN: (纸本)0780370449

A support vector machine constructs an optimal hyperplane from a small set of samples near the boundary. This makes it sensitive to these specific samples and tends to result in machines either too complex with poor generalization ability or too imprecise with high training error, depending on the kernel parameters. In this paper, we present an improved version of the method, called editing support vector machine (ESVM), which removes some samples near the boundary from the training set. Experiments show that for cases that the two classes are overlapped, ESVM can get better generalizing ability, and ESVM is also more robust with noises.

关键词： Support vector machines Kernel Automation intelligent systems Machine intelligence Noise robustness Risk management Error analysis Nearest neighbor searches

来源：评论

学校读者我要写书评

暂无评论

A novel algorithm of adaptive background estimation

A novel algorithm of adaptive background estimation

引用

IEEE International Conference on Image Processing

作者： Da-shan Gao Jie Zhou Le-ping Xin State Key Laboratory of Intelligent Technology and Systems Department of Automation Tsinghua University Beijing China

ISBN: (纸本)0780367251

We propose an adaptive background estimation algorithm for an outdoor video surveillance system. In order to enhance the ability of adaptation to illumination changes and variant noise in long-term running, an improved Kalman filtering model based on the local-region is discussed to dynamically estimate a background image, in which the parameters are predicted by a recursive-least-square adaptive filter. The experimental results on real-world video show that the algorithm can perform robustly and effectively.

关键词： Lighting Adaptive filters Vehicle detection Pixel Kalman filters Filtering Recursive estimation Change detection algorithms Video surveillance Background noise

来源：评论

学校读者我要写书评

暂无评论

A new algorithm for handwritten character recognition

A new algorithm for handwritten character recognition

引用

IEEE International Conference on Image Processing

作者： Zhu Xiaoyan Shi Yifan State Key Laboratory of Intelligent Technology & Systems Department of Computer Science & Technology Tsinghua University Beijing China

A new algorithm of handwritten character recognition based on feedback theory is proposed. We suggest this new method by adding confidence back-propagation and input modification on the neural network model, thus preprocessing and recognition are integrated closely. Convergence of the algorithm is proved. Experiments show that it greatly reduced the system's error rate and was robust to environmental noise.

关键词： Character recognition Signal processing Artificial neural networks Optical character recognition software Feature extraction Noise robustness Working environment noise Feedback loop Control systems Image recognition

来源：评论

学校读者我要写书评

暂无评论

A handwritten character recognition method with ANN feedback

A handwritten character recognition method with ANN feedback

引用

International Conference on Document Analysis and Recognition

作者： Zhu Xiaoyan Shi Yifan State Key Laboratory of Intelligent Technology & Systems Department of Computer Science Technology Tsinghua University Beijing China

In this paper, a new approach of handwritten character recognition system with Artificial Neural Network (ANN) feedback is proposed. This recognition system is based on a neural recognition network and a neural feedback network, the out put of which is used to modify the feature of the input pattern, thus preprocessing and recognition are integrated closely. Experiments show that this approach can make system performance very good and robust to environmental noise.

关键词： Character recognition Artificial neural networks Neurofeedback Signal processing Pattern recognition Feature extraction Feedback loop Noise robustness System performance Control systems

来源：评论

学校读者我要写书评

暂无评论

Support vector machine learning for image retrieval

Support vector machine learning for image retrieval

引用

IEEE International Conference on Image Processing

作者： Lei Zhang Fuzong Lin Bo Zhang State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)0780367251

A novel method of relevance feedback is presented based on support vector machine learning in the content-based image retrieval system. A SVM classifier can be learned from training data of relevance images and irrelevance images marked by users. Using the classifier, the system can retrieve more images relevant to the query in the database efficiently. Experiments were carried out on a large-size database of 9918 images. It shows that the interactive learning and retrieval process can find correct images increasingly. It also shows the generalization ability of SVM under the condition of limited training samples.

关键词： Support vector machines Machine learning Image retrieval Support vector machine classification Space technology Image databases Learning systems Content based retrieval Training data Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Vehicle license image segmentation using wavelet transform

Vehicle license image segmentation using wavelet transform

引用

International Symposium on intelligent Multimedia, Video and Speech Processing

作者： Jianlong Zhu Yannan Zhao The State Key Laboratory of Intelligent Technology and Systems Computer Science & Technology Department Tsinghua University Beijing China

ISBN: (纸本)9628576623

A novel multiscale method of vehicle license image segmentation based on wavelet transform is proposed. This analysis utilizes the local wavelet transform modulus maxima as the image edge at multiple scales, and combines the multiscale edge information. Then a template matching method is applied to segment the vehicle license image based on edge density analysis and character edge spatial feature after eliminating the long straight line noise. The approach integrates multiple scale edge information and overcomes the shortcoming of traditional single scale analysis. This advantage has special significance for the hazy image. Experimentation with about three hundred images obtained from a natural environment shows that the performance of this approach is better than the traditional method, especially for hazy images.

关键词： Vehicles Licenses Image segmentation Wavelet transforms Image edge detection Image analysis Information analysis Wavelet analysis intelligent transportation systems Image texture analysis

来源：评论

学校读者我要写书评

暂无评论

A Chinese spoken dialog system for blind men

A Chinese spoken dialog system for blind men

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Rui Guo Xiaoyan Zhu Yu Hao State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China

This paper introduces a Chinese spoken dialog system providing services for blind people through which. they can use computers. A description of the architecture of the dialog system is presented briefly and the way in which each component works is also explained. The key factor of such a dialog system is extraction of the intention of a user's utterance so as to make an appropriate response. To achieve this, a case grammar formalism was applied for semantic description and a robust spoken language parsing method based on case-frames was adopted to obtain the semantic interpretation of the input. It shows that this parsing method can tolerate errors of speech recognition and grammatical deviation of spoken language to some extent.

关键词： Natural languages Hidden Markov models Speech recognition Computer architecture Robustness Speech synthesis Knowledge management Humans intelligent systems Computer science

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269页 << < 256 257 258 259 260 261 262 263 264 265 > >>

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：