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

2,217 篇 会议
1,434 篇 期刊文献
1 册 图书

馆藏范围

3,652 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,306 篇 工学
- 1,470 篇 计算机科学与技术...
- 1,222 篇 软件工程
- 590 篇 信息与通信工程
- 377 篇 电子科学与技术（可...
- 313 篇 电气工程
- 274 篇 控制科学与工程
- 191 篇 生物工程
- 181 篇 机械工程
- 169 篇 光学工程
- 127 篇 生物医学工程（可授...
- 121 篇 化学工程与技术
- 114 篇 仪器科学与技术
- 82 篇 动力工程及工程热...
- 67 篇 材料科学与工程（可...
- 56 篇 网络空间安全
- 51 篇 建筑学
- 45 篇 土木工程
1,394 篇 理学
- 892 篇 数学
- 402 篇 物理学
- 225 篇 生物学
- 216 篇 统计学（可授理学、...
- 131 篇 化学
- 124 篇 系统科学
565 篇 管理学
- 299 篇 管理科学与工程(可...
- 283 篇 图书情报与档案管...
- 100 篇 工商管理
93 篇 医学
- 77 篇 临床医学
- 63 篇 基础医学(可授医学...
- 42 篇 药学(可授医学、理...
58 篇 法学
- 45 篇 社会学
48 篇 农学
33 篇 经济学
21 篇 教育学
11 篇 军事学
9 篇 哲学
9 篇 艺术学
8 篇 文学

主题

138 篇 feature extracti...
104 篇 semantics
86 篇 training
78 篇 laboratories
68 篇 information proc...
65 篇 computational mo...
64 篇 image segmentati...
55 篇 optimization
54 篇 data mining
53 篇 computers
50 篇 face recognition
49 篇 signal processin...
48 篇 visualization
47 篇 accuracy
47 篇 robustness
46 篇 signal processin...
43 篇 deep learning
42 篇 support vector m...
42 篇 humans
40 篇 bandwidth

机构

431 篇 key laboratory o...
219 篇 university of ch...
210 篇 key laboratory o...
101 篇 key laboratory o...
83 篇 key laboratory o...
63 篇 peng cheng labor...
62 篇 school of comput...
61 篇 key laboratory o...
61 篇 college of compu...
53 篇 anhui university...
53 篇 college of mathe...
53 篇 key laboratory o...
47 篇 key laboratory o...
46 篇 hunan provincial...
45 篇 the key laborato...
43 篇 key laboratory o...
43 篇 graduate univers...
41 篇 school of comput...
41 篇 college of infor...
39 篇 chinese academy ...

作者

90 篇 zhongzhi shi
86 篇 huang zhixiang
85 篇 shi zhongzhi
74 篇 li yingsong
73 篇 xilin chen
72 篇 shiguang shan
69 篇 zhixiang huang
62 篇 liu qun
61 篇 huang qingming
57 篇 yingsong li
56 篇 xianliang wu
52 篇 shi minjia
41 篇 wu xianliang
41 篇 xu qianqian
39 篇 wu xian-liang
38 篇 feng yang
36 篇 he qing
34 篇 luo bin
33 篇 bin luo
32 篇 wen gao

语言

3,444 篇 英文
116 篇 其他
99 篇 中文

检索条件"机构=The Key Laboratory of Intelligent Computing and Signal Processing"

共 3652 条记录，以下是3621-3630 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：

Neural field model for perceptual learning

Neural field model for perceptual learning

引用

IEEE International Conference on Cognitive Informatics

作者： Zhongzhi Shi Youping Huang Jian Zhang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China

ISBN: (纸本)0769521908

Perceptual learning happens at the perceptual level. We combine holism and reductionism to research perception learning. Based on information geometry the paper presents a neural field model which is used to understand the transformation mechanism, dynamical behavior, capability and limitation of neural network models, by the study of globally topological and geometrical structure on parameter spaces of neural networks. We discuss neural field representation, fractal learning principle, topology approximation correction learning and the dualistic correction learning algorithm. Finally the paper gives conclusions and points out future research topics.

关键词： Solid modeling Biological neural networks Information geometry Manifolds Information processing Fractals Network topology Approximation algorithms Cognitive informatics Humans

来源：评论

学校读者我要写书评

暂无评论

MAGE: an agent-oriented software engineering environment

MAGE: an agent-oriented software engineering environment

引用

IEEE International Conference on Cognitive Informatics

作者： Zhongzhi Shi Haijun Zhang Yong Cheng Yuncheng Jiang Qiujian Sheng Zhikung Zhao Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China

ISBN: (纸本)0769521908

Agent-oriented programming is an important technology for autonomic computing and grid computing. Advances in agent technology depend on improving frameworks for building and supporting agent societies. Experience suggests that first generation multiagent systems focus only on some aspects and fall short of providing a rapid prototyping development environment for the systematic analysis, design, construction and deployment of agent-oriented applications. This paper presents MAGE, an agent-oriented programming environment, with complete tools to support agent-oriented requirement analysis, design, development and deployment. It also gives some comparison between MAGE and other multiagent platforms with particular focus on methodology. At last, this paper gives some applications on MAGE.

关键词： Software engineering Multiagent systems Application software Laboratories Grid computing Prototypes Computer industry Information processing Buildings Programming environments

来源：评论

学校读者我要写书评

暂无评论

Formal data model and algebra for resource sharing in grid

Formal data model and algebra for resource sharing in grid

引用

2nd International Workshop on Grid and Cooperative computing, GCC 2003

作者： Sheng, Qiujian Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704-28 Beijing100080 China Graduate School of the Chinese Academy of Sciences Beijing China

ISBN: (纸本)3540219935

Management of various complex resources is an important issue to be well done, in order to fulfill the potential of Grid. In this paper, we propose a formal data model and algebra for resource sharing in the Grid. In the model, domain ontology knowledge is described within knowledge schema and domain background knowledge is captured in integrity constrain rules. A query algebra is defined to manipulate the modeled resource base. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

A Multi-layers Neural Network Model based on Characteristics of Ganglions' Receptive Fields in Retina and an Algorithm for Watchfulness-keeping

A Multi-layers Neural Network Model based on Characteristics...

引用

The Third Asian Conference on Vision (ACV2004)

作者：危辉陆汝钤 Department of Computer Science Lab of Algorithm for Cognitive Model Brain Science Research Center Fudan University Shanghai 200433 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing 100080 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing 100080 China

Machine vision is an active branch of Artificial Intelligence. An important problem in this area is the balance among efficiency, accuracy and huge computing. The visual system of human can keep watchfulness to the perimeter of visual field while at same time their central attention is focused to the center of visual field for fine information processing. This mechanism of computing resource assignment could ease the demand for huge and complex hardware structure. Therefore designing computer model based on biological visual

关键词： A Multi-layers Neural Network Model based on Characteristics of Ganglions Receptive Fields in Retina and an Algorithm for Watchfulness-keeping Model

来源：评论

学校读者我要写书评

暂无评论

Amplitude spectrum-based gait recognition

Amplitude spectrum-based gait recognition

引用

International Conference on Automatic Face and Gesture Recognition

作者： Guoying Zhao Rui Chen Guoyi Liu Hua Li Graduate School of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China

ISBN: (纸本)0769521223

Gait is a biometric feature and identification of people from gait captured on video that has become a challenging problem in computer vision. A recognition method based on amplitude spectrum (Fourier spectrum) of frequency domain is proposed. Fourier spectrum reflects the frequency feature of person's pose in the current frame. After getting the period and key poses through the whole sequence according to the height of centroid and the amplitude value in frequency domain, we extract 5D features from the sequence including four amplitude values corresponding to four key poses image and the proportion of body. Finally, three measures are applied to evaluate our algorithm. Experiments result on USF dataset show that our method is insensitive to many changes condition of background, lighting, clothing, walking speed, segment noise and so on. For we implement gait recognition according to the discriminant analysis, the result to some extent is robust to the variation of viewpoint and cloth and recognition rate is satisfying.

关键词： Biometrics Face recognition Image recognition Frequency domain analysis Clothing Legged locomotion Iris Fingerprint recognition Humans Surveillance

来源：评论

学校读者我要写书评

暂无评论

An algebraic multi-class classification method

An algebraic multi-class classification method

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Qing He Zhen-Yan Liu Zhong-Zhi Shi The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China School of Software Beijing Institute of Tèchnology Beijing China

ISBN: (纸本)0780384032

An algebraic multi-class classification method AHSC, i.e., algebraic hyper surface classification, is proposed. The separating algebraic hyper surface of two-class data may be directly constructed by a single polynomial in theory, but it is too difficult to separate multi-class data by a single polynomial even though the polynomial is multivalued. AHSC can be used for classifying multi-class data by integrating a series of polynomial networks based on binary numbers, which are used for labeling the classes of samples. The problem that multi-class data cannot always be separated by a single polynomial is solved by AHSC. Moreover, using an adaptive method can choose the order of polynomial. The experimental results show that the new method can efficiently and accurately classify multi-class and high dimension data.

关键词： Polynomials Machine learning Error correction codes Mathematical model Neurons Vectors Helium Information processing Computers Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Bark texture feature extraction based on statistical texture analysis

Bark texture feature extraction based on statistical texture...

引用

International Symposium on intelligent Multimedia, Video and Speech processing

作者： Yuan-Yuan Wan Ji-Xiang Du De-Shuang Huang Zheru Chi Yiu-Ming Cheung Xiao-Feng Wang Guo-Jun Zhang Intelligent Computing Laboratory Institute of Intelligent Machines Chinese Academy and Sciences Hefei Anhui China Center for Multimedia Signal Processing Hong Kong Polytechnic University Hong Kong China Department of Computer Science Hong Kong Baptist University Hong Kong China

ISBN: (纸本)0780386876

This paper quantitatively describes and discusses the usefulness of texture analysis methods for the recognition of bark. Comparative studies of bark texture feature extraction are performed for the four texture analysis methods such as the gray level run-length method (RLM), co-occurrence matrices method (COMM) and histogram method (HM) as well as auto-correlation method (ACM). Specifically, we use three classifiers of nearest neighbor (l-NN), k-nearest neighbor (k-NN) and moving median centers (MMC) hypersphere classifiers to verify the validity of the extracted bark texture features. To gain good results we added to color information that proved very efficient. Moreover, the experimental results also demonstrate that from the viewpoint of the recognition accuracy and computational complexity, the COMM method is superior to the other three methods.

关键词： Feature extraction Histograms Image texture analysis Image analysis Probability Machine intelligence signal processing Plants (biology) Entropy Multimedia computing

来源：评论

学校读者我要写书评

暂无评论

A hypersphere method for plant leaves classification

A hypersphere method for plant leaves classification

引用

International Symposium on intelligent Multimedia, Video and Speech processing

作者： Guo-Jun Zhang Xiao-Feng Wang De-Shuang Huang Zheru Chi Yiu-Ming Cheung Ji-Xiang Du Yuan-Yuan Wan Intelligent Computing Laboratory Institute of Intelligent Machines Chinese Academy and Sciences Hefei Anhui China Center for Multimedia Signal Processing Hong Kong Polytechnic University Hong Kong China Department of Computer Science Hong Kong Baptist University Hong Kong China

ISBN: (纸本)0780386876

The recognition of the tens of thousands of kinds of plants on Earth is an important and difficult task. If we use a nearest neighbour classifier to solve it, millions of training data are needed to obtain a high correct recognition rate. However, the corresponding classification process is quite time-consuming. We propose a new approach using a moving median centers hypersphere technique to recognize different plant leaves. With this new method, we can successfully decrease the classification time, and reduce the storage size without sacrificing the classification accuracy. Experimental results using real data show that this method is really efficient and effective in classifying different plant leaves.

关键词： Neural networks Training data Machine intelligence Multimedia computing Biomedical signal processing Computer science Geoscience Earth Plants (biology) Agriculture

来源：评论

学校读者我要写书评

暂无评论

Watermark extraction by magnifying noise and applying global minimum decoder

Watermark extraction by magnifying noise and applying global...

引用

International Conference on Image and Graphics (ICIG)

作者： Zhigeng Pan Li Li Mingmin Zhang D. Zhang State Key Laboratory of CAD&CG University of Zhejiang Hangzhou China Hangzhou Dianzi University Hangzhou China Multimedia Signal Processing and Department of Computing Polytechnic University Hong Kong China

For the classical watermark embedment model I = 1 + /spl alpha/W, the corresponding watermark detection has its limitation in its need of a fixed parameter for extracting watermarks. If the extraction parameter is too large, we cannot extract the watermark from the image that contains watermarks; if it is too small, the extracted watermarks may be blurred. This paper proposes a novel watermark extraction method. First, we treat the watermark information as noise for the watermarked image in its spatial domain. We then magnify the noise before detection. Next, we recover the watermark information by adjusting the extracted data from the frequency domain according to our global minimum method. Experimental results show that our watermark extraction method is more valid and accurate than the classical method. It can greatly reduce extraction errors.

关键词： Watermarking Decoding Data mining Frequency domain analysis Computer networks signal processing Embedded computing Electronic mail Computer errors Information security

来源：评论

学校读者我要写书评

暂无评论

A public mesh watermarking algorithm based on addition property of Fourier transform

A public mesh watermarking algorithm based on addition prope...

引用

International Conference on Image and Graphics (ICIG)

作者： Li Li Zhigeng Pan David Zhang Hangzhou Dianzi University Hangzhou China State Key Laboratory of CAD&CG University of Zhejiang Hangzhou China Multimedia Signal Processing and Department of Computing Hong Kong Polytechnic University Kowloon Hong Kong China

This paper presents a public mesh watermarking algorithm. First, the resultant watermarked image minus the original image is the watermark information. According to the addition property of the Fourier transform, a change of spatial domain will cause a change in the frequency domain. Then, the watermark information is scaled down and embedded in one part of the x-coordinate of the original mesh. Finally, the x-coordinate of the test mesh is amplified before extraction. Experimental results prove that our algorithm is resistant to a variety of attacks without the need for any preprocessing.

关键词： Watermarking Fourier transforms signal processing algorithms Data mining Frequency domain analysis Wavelet domain Partitioning algorithms Noise robustness Equations Electronic mail

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366页 << < 357 358 359 360 361 362 363 364 365 366 > >>

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：