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

2,119 篇 会议
48 篇 期刊文献
28 册 图书

馆藏范围

2,195 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,500 篇 工学
- 1,133 篇 计算机科学与技术...
- 655 篇 软件工程
- 274 篇 电气工程
- 252 篇 信息与通信工程
- 141 篇 生物医学工程（可授...
- 135 篇 控制科学与工程
- 133 篇 光学工程
- 104 篇 生物工程
- 93 篇 机械工程
- 66 篇 仪器科学与技术
- 61 篇 电子科学与技术（可...
- 59 篇 材料科学与工程（可...
- 55 篇 化学工程与技术
- 33 篇 建筑学
- 33 篇 土木工程
- 24 篇 力学（可授工学、理...
- 20 篇 安全科学与工程
664 篇 理学
- 348 篇 数学
- 207 篇 物理学
- 177 篇 生物学
- 95 篇 统计学（可授理学、...
- 59 篇 化学
- 33 篇 系统科学
206 篇 管理学
- 137 篇 图书情报与档案管...
- 79 篇 管理科学与工程(可...
- 25 篇 工商管理
140 篇 医学
- 132 篇 临床医学
- 49 篇 基础医学(可授医学...
- 31 篇 药学(可授医学、理...
21 篇 法学
- 21 篇 社会学
20 篇 艺术学
11 篇 教育学
9 篇 经济学
9 篇 农学
2 篇 文学
1 篇 军事学

主题

635 篇 pattern recognit...
92 篇 feature extracti...
60 篇 pattern matching
59 篇 local binary pat...
59 篇 neural networks
59 篇 face recognition
54 篇 data mining
41 篇 image segmentati...
40 篇 pattern recognit...
40 篇 machine learning
40 篇 character recogn...
37 篇 shape
36 篇 pattern analysis
35 篇 image processing
34 篇 support vector m...
34 篇 image recognitio...
33 篇 bioinformatics
33 篇 computer vision
32 篇 image analysis
31 篇 artificial intel...

机构

13 篇 national laborat...
6 篇 chinese acad sci...
5 篇 pattern recognit...
5 篇 chinese acad sci...
5 篇 univ windsor sch...
5 篇 university of to...
5 篇 chinese academy ...
4 篇 university colle...
4 篇 pattern recognit...
4 篇 institute of ima...
4 篇 the hebrew unive...
4 篇 the university o...
4 篇 sorbonne univers...
4 篇 eurecom biot
4 篇 national lab of ...
4 篇 key laboratory o...
4 篇 école centrale d...
4 篇 national institu...
4 篇 computer vision ...
3 篇 institute of ima...

作者

11 篇 ngom alioune
9 篇 ma songde
8 篇 li stan z.
8 篇 suen ching y.
6 篇 c.y. suen
6 篇 lei zhen
6 篇 suen c.y.
5 篇 lu hanqing
5 篇 wang wei
5 篇 duin robert p. w...
5 篇 anon
5 篇 liao shengcai
5 篇 kropatsch walter...
4 篇 leo joskowicz
4 篇 li yifeng
4 篇 liu cheng-lin
4 篇 hagras hani
4 篇 diana mateus
4 篇 song de ma
4 篇 maria a. zuluaga

语言

2,122 篇 英文
65 篇 其他
12 篇 中文

检索条件"任意字段=3rd IAPR International Conference on Pattern Recognition in Bioinformatics"

共 2195 条记录，以下是581-590 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：

A Novel Approach of Feature Vector Design for Financial Information Extraction Using Supervised Learning 3

A Novel Approach of Feature Vector Design for Financial Info...

引用

3rd international conference on Soft Computing and Machine Intelligence (ISCMI)

作者： Dadhich, Mahesh Lewis, James G. Bangalore India Los Angeles USA

ISBN: (纸本)9781509036967

Financial information extraction from big financial reports is a tedious task. This paper speaks about page-wise feature generation and applying learning algorithms for identifying financial information (balance sheets, cash flows, and income statements) in Form 10-K or annual reports of companies. Balance sheets, cash flows, and income statements have some structure in them and are semi-structured information. This approach employs selection of unigrams and bigrams based on frequency of occurrence and expert advice, generation of page wise features, and applying learning models for identifying patterns of specific financial information. Different supervised learning models are applied yielding results with very high accuracy (greater than 99%).

关键词： page wise Information extraction Feature generation SVM Random Forest logistic regression Naive Bayes cross validation 10k reports pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Impact of Feature Selection and Engineering in the Classification of Handwritten Text 3

Impact of Feature Selection and Engineering in the Classific...

引用

3rd international conference on Computing for Sustainable Global Development (INDIACom)

作者： Kaushik, Anupama Gupta, Himanshu Latwal, Digvijay Singh Maharaja Surajmal Inst Technol Dept IT Delhi India

ISBN: (纸本)9789380544199

Feature selection forms an important aspect of machine learning and character recognition. It is a process of selecting the most important features (attributes) from the dataset. Accurate feature selection results in significant reduction in the number of irrelevant (constant, redundant) attributes thereby, reducing the processing time and increasing the accuracy of the model without any loss of information. This paper focuses on the impact of feature selection and engineering in the classification of handwritten text by identifying and extracting those attributes of the training dataset that will contribute most towards the classification task using classifiers like J48, NaiveBayes and Sequential Minimal Optimization (SMO). This results in improved accuracy of the classifiers as compared to the work reported earlier. Further, a comparative performance evaluation of the classifiers used for OCR and pattern recognition is done. Initial classification performance of all the classifiers listed above was recorded on the raw dataset. Finally, the dataset was transformed after performing relevant feature selection and engineering on its attributes. The same classifiers were again trained on the transformed dataset and their accuracy was recorded. This paper uses the widely used MNIST dataset of handwritten digits for training the classifiers.

关键词： Character recognition J-48 MNIST Dataset NaiveBayes Optical Character recognition (OCR) Principal Components Analysis (PCA) Sequential Minimal Optimization (SMO) WEKA pattern recognition Machine Learning

来源：评论

学校读者我要写书评

暂无评论

7th iapr TC3 Workshop on Artificial Neural Networks in pattern recognition, ANNPR 2016

7th IAPR TC3 Workshop on Artificial Neural Networks in Patte...

引用

7th iapr TC3 Workshop on Artificial Neural Networks in pattern recognition, ANNPR 2016

ISBN: (纸本)9783319461816

The proceedings contain 27 papers. The special focus in this conference is on Learning Algorithms, Architectures and Applications. The topics include: A spiking neural network for personalised modelling of electrogastrography;improving generalization abilities of maximal average margin classifiers;finding small sets of random Fourier features for shift-invariant kernel approximation;incremental construction of low-dimensional data representations;soft-constrained nonparametric density estimation with artificial neural networks;interpretable classifiers in precision medicine;on the evaluation of tensor-based representations for optimum-path forest classification;on the harmony search using quaternions;learning parameters in deep belief networks through firefly algorithm;towards effective classification of imbalanced data with convolutional neural networks;on CPU performance optimization of restricted Boltzmann machine and convolutional RBM;comparing incremental learning strategies for convolutional neural networks;approximation of graph edit distance by means of a utility matrix;time series classification in reservoir- and model-space;objectness scoring and detection proposals in forward-looking sonar images with convolutional neural networks;background categorization for automatic animal detection in aerial videos using neural networks;predictive segmentation using multichannel neural networks in Arabic OCR system;quad-tree based image segmentation and feature extraction to recognize online handwritten bangla characters;using radial basis function neural networks for continuous and discrete pain estimation from bio-physiological signals;emotion recognition in speech with deep learning architectures and on gestures and postural behavior as a modality in ensemble methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Abnormal mass classification in breast mammography using rotation invariant LBP 3

Abnormal mass classification in breast mammography using rot...

引用

3rd international conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016

作者： Khan, Haider Adnan Helal, Abdullah Al Ahmed, Khawza I. Mostafa, Raqibul Department of Electrical and Electronic Engineering United International University Dhaka1209 Bangladesh

ISBN: (纸本)9781509029068

We present a novel approach for abnormal breast mass classification from digitized mammography images. The proposed framework exploits rotation invariant uniform Local Binary pattern (LBP) as texture feature. These features are classified using Support Vector Machine (SVM). In addition, we take advantage of the breast mammograms taken from multiple views or angles. We classify breast scans from 'cranial-caudal' view and 'mediolateral-oblique' view separately, and combine these classification scores to make an improved diagnosis. This reduces the classification error, and achieves higher recognition rate than that of either views individually. The proposed computer aided diagnosis system was evaluated on DDSM (Digital Database for Screening Mammography) data set, and was able to achieve a classification accuracy of 74%. © 2016 IEEE.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Finding shortest triangular path in a digital object 19th

Finding shortest triangular path in a digital object

引用

19th iapr international conference on Discrete Geometry for Computer Imagery, DGCI 2016

作者： Sarkar, Apurba Biswas, Arindam Mondal, Shouvick Dutt, Mousumi Department of Computer Science and Technology Indian Institute of Engineering Science and Technology Shibpur India Department of Information Technology Indian Institute of Engineering Science and Technology Shibpur India Department of Computer Science and Engineering International Institute of Information Technology Naya Raipur India

ISBN: (纸本)9783319323596

A combinatorial algorithm to find a shortest triangular path (STP) between two points inside a digital object imposed on triangular grid is designed having (equation found) time complexity, n being the number of pixels on the contour of the object and g being the grid size. First the inner triangular cover of the given digital object is constructed which maximally inscribes the object. Certain combinatorial rules are formulated based on the properties of triangular grid and are applied whenever necessary to obtain a shortest triangular path, where the path lies entirely in the digital object and moves only along the grid edges. The length of STP and number of monotonicity may be two useful parameters to determine shape complexity of the object. Experimental results show the effectiveness of the algorithm. © Springer international Publishing Switzerland 2016.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

2016 3rd international conference on Information Retrieval and Knowledge Management, CAMP 2016 - conference Proceedings

2016 3rd International Conference on Information Retrieval a...

引用

3rd international conference on Information Retrieval and Knowledge Management, CAMP 2016

ISBN: (纸本)9781509029549

The proceedings contain 26 papers. The topics discussed include: a Malay text summarizer using pattern-growth method with sentence compression rules;using concatenation cost for unit selection of homosonic segments in concatenative sound synthesis;prosodic breaks on Malay speech corpus: evaluation of pitch, intensity and duration;information extraction: evaluating named entity recognition from classical Malay documents;ontology-based information retrieval for historical documents;graph-based text representation for Malay translated Hadith text;fuzzy logic on reading recommendation system;content-based image retrieval system for marine invertebrates;document level assessment for pairwise system evaluation;and query refinement for ontology information extraction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emotion Representation in Whole-brain Functional Connectivity patterns: An fMRI Study

Emotion Representation in Whole-brain Functional Connectivit...

引用

2017 3rd international conference on Artificial Intelligence and Industrial Engineering (AIIE2017)

作者： Yin LIANG School of Computer Science and Technology Tianjin Key Laboratory of Cognitive Computing and ApplicationTianjin University

The representation of emotion in human brain is an important question in the cognitive neuroscience. However, it was remained unclear to what extent the connections between different brain regions contribute to the emotion recognition. The present study mainly focused on the emotion decoding based on the functional connectivity patterns. We designed the experiment and collected the neural activities while participants viewed emotion stimuli using the functional magnetic resonance imaging(f MRI) technology. We constructed the whole-brain functional connectivity patterns for each emotion, and performed emotion classification using multivariate pattern analysis combined with machine learning algorithms. We found that emotions could be successfully decoded from the whole-brain functional connectivity patterns. These results provide new evidence that large-scale functional connectivity patterns contain rich emotion information and contribute to the emotion recognition. Our study extends exist f MRI studies on emotion perception and may further our understanding of how human beings achieve easy and quick recognition of emotions.

关键词： Emotion Functional magnetic resonance imaging Functional connectivity Multivariate pattern analysis Machine learning

来源：评论

学校读者我要写书评

暂无评论

Factographic information retrieval for competences forming 3

Factographic information retrieval for competences forming

引用

3rd international conference on Digital Information Processing, Data Mining, and Wireless Communications (DIPDMWC)

作者： Kulik, Sergey Natl Res Nucl Univ MEPHI Moscow Engn Phys Inst Fac Cybernet & Informat Secur Moscow Russia

ISBN: (纸本)9781467393799

The effective factographic information retrieval problem has been investigated in the paper. The primary objective of this paper is to outline factographic information retrieval and new Lemma related to properties of factographic information retrieval. The special curriculum has been developed for the set competences. The curriculum contains specialized disciplines. These disciplines use factographic information retrieval. Factographic information retrieval has effectiveness indicators. New Lemma about effectiveness and properties of factographic information retrieval was proved.

关键词： competence factographic information security information retrieval pattern recognition effectiveness

来源：评论

学校读者我要写书评

暂无评论

19th iapr international conference on Discrete Geometry for Computer Imagery, DGCI 2016

19th IAPR International Conference on Discrete Geometry for ...

引用

19th iapr international conference on Discrete Geometry for Computer Imagery, DGCI 2016

ISBN: (纸本)9783319323596

The proceedings contain 34 papers. The special focus in this conference is on Combinatorial Tools, Discretization, Discrete Tomography and Combinatorial Topology. The topics include: Convergent geometric estimators with digital volume and surface integrals;discrete calculus, optimisation and inverse problems in imaging;number of words characterizing digital balls on the triangular tiling;generation of digital planes using generalized continued-fractions algorithms;a tomographical interpretation of a sufficient condition on H-graphical sequences;geometrical characterization of the uniqueness regions under special sets of three directions in discrete tomography;a comparison of some methods for direct 2d reconstruction from discrete projected views;homotopic thinning in 2d and 3d cubical complexes based on critical kernels;p-simple points and general-simple deletion rules;two measures for the homology groups of binary volumes;shape classification according to LBP persistence of critical points;signature of a shape based on its pixel coverage representation;computation of the normal vector to a digital plane by sampling significant points;finding shortest triangular path in a digital object;digital surfaces of revolution made simple;on functionality of quadraginta octants of naive sphere with application to circle drawing;encoding specific 3d polyhedral complexes using 3d binary images;interactive curvature tensor visualization on digital surfaces;construction of digital ellipse by recursive integer intervals;digitization of partitions and tessellations;bijective rigid motions of the 2D Cartesian grid and adaptive tangential cover for noisy digital contours.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Encoding specific 3D polyhedral complexes using 3D binary images 19th

Encoding specific 3D polyhedral complexes using 3D binary im...

引用

19th iapr international conference on Discrete Geometry for Computer Imagery, DGCI 2016

作者： Gonzalez-Diaz, Rocio Jimenez, Maria-Jose Medrano, Belen Applied Mathematics Department I School of Computer Engineering University of Seville Seville Spain

ISBN: (纸本)9783319323596

We build upon the work developed in [4] in which we presented a method to "locally repair" the cubical complex Q(I) associated to a 3D binary image I, to obtain a "well-composed" polyhedral complex P(I), homotopy equivalent to Q(I). There, we developed a new codification system for P(I), called ExtendedCubeMap (ECM) representation, that encodes: (1) the (geometric) information of the cells of P(I) (i.e., which cells are presented and where), under the form of a 3D grayscale image gP;(2) the boundary face relations between the cells of P(I), under the form of a set BP of structuring elements. In this paper, we simplify ECM representations, proving that geometric and topological information of cells can be encoded using just a 3D binary image, without the need of using colors or sets of structuring elements. We also outline a possible application in which well-composed polyhedral complexes can be useful. © Springer international Publishing Switzerland 2016.

关键词： Binary images

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220页 << < 55 56 57 58 59 60 61 62 63 64 > >>

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：