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

1,444 篇 会议
30 篇 期刊文献
16 册 图书

馆藏范围

1,490 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,167 篇 工学
- 933 篇 计算机科学与技术...
- 396 篇 软件工程
- 164 篇 电气工程
- 137 篇 光学工程
- 121 篇 信息与通信工程
- 96 篇 生物医学工程（可授...
- 91 篇 控制科学与工程
- 90 篇 生物工程
- 70 篇 机械工程
- 69 篇 仪器科学与技术
- 44 篇 电子科学与技术（可...
- 35 篇 化学工程与技术
- 32 篇 材料科学与工程（可...
- 15 篇 土木工程
- 14 篇 力学（可授工学、理...
- 13 篇 建筑学
394 篇 理学
- 220 篇 数学
- 181 篇 物理学
- 103 篇 生物学
- 74 篇 统计学（可授理学、...
- 37 篇 化学
- 13 篇 系统科学
330 篇 医学
- 323 篇 临床医学
- 33 篇 基础医学(可授医学...
- 25 篇 药学(可授医学、理...
107 篇 管理学
- 69 篇 图书情报与档案管...
- 42 篇 管理科学与工程(可...
37 篇 艺术学
- 37 篇 设计学（可授艺术学...
15 篇 农学
- 12 篇 作物学
10 篇 法学
- 10 篇 社会学
5 篇 教育学
3 篇 经济学
2 篇 军事学

主题

142 篇 pattern recognit...
110 篇 image segmentati...
94 篇 feature extracti...
83 篇 image processing
63 篇 image analysis
56 篇 image color anal...
41 篇 principal compon...
40 篇 face recognition
38 篇 image recognitio...
31 篇 support vector m...
30 篇 deep learning
30 篇 local binary pat...
30 篇 image reconstruc...
29 篇 computer vision
29 篇 shape
27 篇 image classifica...
26 篇 image enhancemen...
26 篇 pattern matching
25 篇 training
24 篇 neural networks

机构

7 篇 institute of aut...
5 篇 inesc tec porto
5 篇 univ porto fac e...
4 篇 guangdong univer...
4 篇 univ porto fac c...
4 篇 south china univ...
4 篇 microsoft resear...
4 篇 king fahd univer...
4 篇 shanghai jiao to...
3 篇 córdoba
3 篇 comp vis ctr bar...
3 篇 department of co...
3 篇 tarbiat modares ...
3 篇 univ porto fac e...
3 篇 inst res fundame...
3 篇 chitkara univers...
3 篇 universidade de ...
3 篇 harvard univ sch...
3 篇 ryerson univ dep...
3 篇 univ alicante ui...

作者

11 篇 cardoso jaime s.
9 篇 vidal enrique
8 篇 calvo-zaragoza j...
8 篇 oliveira helder ...
6 篇 lee seong-whan
6 篇 suen c.y.
5 篇 casacuberta fran...
5 篇 marques jorge s.
5 篇 pina pedro
4 篇 shengli xie
4 篇 pietikainen matt...
4 篇 bioucas-dias jos...
4 篇 dongbin zhao
4 篇 c.y. suen
4 篇 forero manuel g.
4 篇 yuanqing li
4 篇 el-sayed m. el-a...
4 篇 derong liu
4 篇 weickert joachim
4 篇 singh s

语言

1,454 篇 英文
33 篇 其他
6 篇 中文
1 篇 日文

检索条件"任意字段=3rd Iberian Conference on Pattern Recognition and Image Analysis"

共 1490 条记录，以下是131-140 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：

Robust Fault Diagnostics of Industrial Motors: The Signal-to-image Approaches for Sensor Data Using Multi-Task Transformers with Diverse Attention Mechanism

Robust Fault Diagnostics of Industrial Motors: The Signal-to...

引用

International conference on Control, Instrumentation, Energy and Communication (CIEC)

作者： Sudipta Mukhopadhyay Indrajit Kar Zonunfeli Ralte Zensar Technologies Bangalore India

Vibration analysis serves as a valuable method to identify defects within mechanical systems. This process involves monitoring the auditory signals generated by the system and discerning patterns that signify potential issues. Nevertheless, due to the intricate nature of motors, relying solely on one modality (such as acoustic signals) might prove inadequate for comprehensively detecting all faults. Our research introduces a novel approach to enhance fault detection in mechanical systems, specifically focusing on motors. A more comprehensive system health assessment is achieved by utilizing multi-modal vibration analysis, combining acoustic signals and heat signatures. Effective information fusion is facilitated by integrating attention-based transformers, capable of capturing cross-modal correlations. The proposed neural network employs classification and regression loss functions for fault identification and severity assessment respectively. Evaluation on a motor fault dataset demonstrates significant classification accuracy improvements compared to conventional deep and machine learning methods. Incorporating a signal-to-image transformation further aids in fault pattern recognition. This method offers a promising avenue for accurate and comprehensive fault diagnosis in mechanical systems, showcasing the potential of multi-modal analysis and attention mechanisms for industrial equipment maintenance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Collation of Face recognition Techniques: image Registration and Dimension Reduction Approaches

Collation of Face Recognition Techniques: Image Registration...

引用

Technological Advancements in Computational Sciences (ICTACS), International conference on

作者： Gaurav Gupta Anuj Kumar Goel Computer Science Engineering Department Chandigarh University Apex Institute of Technology Mohali Punjab India Electronics and Communication Engineering Department Chandigarh University Chandigarh University Mohali Punjab India

Faces must be present in images for intelligent vision-based human computer interaction to work. Since many years ago, face recognition research has been ongoing and significant. This procedure entails facial tracking, expression recognition, and many other things. It is crucial to first register the positions of the photos in this process. However, maintaining such a database is highly challenging because of pose invariance, illumination invariance, shift invariance, scale and noise invariance. The image Registration Algorithm will be used to register all of the unknown photos that are currently in the database. With the use of a reference, this registration technique tries to align a pattern image. This algorithm will produce features that are independent of translation, scaling and rotation. High dimension space, which must be decreased using a dimension reduction algorithm, is the primary challenge in face recognition. This low dimension subspace can be produced using dimension reduction methods like as Linear Discriminant analysis, Principal Component analysis and Locality Preserving Projection. In order to find the needed image from the given database, this study will first minimize the dimensions of every image that is now there.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on road extraction model of remote sensing image based on the fused convolutional module and attention mechanism 3

Research on road extraction model of remote sensing image ba...

引用

3rd International conference on Computer Vision and pattern analysis, ICCPA 2023

作者： Feng, Jing Li, Weiming Shandong Technology and Business University Shandong Yantai China

ISBN: (纸本)9781510667563

As an important feature element in remote sensing images, road network extraction in remote sensing images has become a research hotspot for scholars at home and abroad. With the development of deep learning, road extraction based on the convolutional neural network has achieved certain results. However, due to the complexity of the road environment, it is still difficult to quickly and accurately separate the road content from the surrounding land cover from the high-resolution remote sensing images. In this paper, we make improvements based on the LinkNet network to address the above problems: firstly, in the coding layer part, we design a new fused convolutional module to replace the original residual module in the coding layer, and use multiple small convolutional kernel networks to stack instead of large convolutional kernel networks to improve the operation efficiency of the model;secondly, we introduce an attention mechanism to enhance the focus on road regions and suppress the influence of background regions on road target The second, the attention mechanism is introduced to enhance the attention to the road region and suppress the influence of background region on the road target segmentation. © 2023 SPIE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Parameter correction method of motor system based on particle swarm and convolutional neural network

A Parameter correction method of motor system based on parti...

引用

Fully Actuated System Theory and Applications (CFASTA), conference on

作者： Depeng Zeng Junjie Hong Liangheng Han Kun Zhang Yueru Ren ZunHeng Wang College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

In order to generate accurate predictions in the vibration characteristics analysis of the motor structure, a motor system parameter correction method based on particle swarm optimization is proposed in this paper. Initially, focusing on the motor itself and utilizing modal analysis theory, finite element analysis software is employed for modal simulation analysis of the motor model. Subsequently, parameters such as shell stiffness, shell density, and spring stiffness between end caps and the shell are adjusted to better match the actual motor model. The particle swarm optimization algorithm is then used to optimize the structural parameters of the motor, obtaining a non-inferior optimal solution between the vibration performance and operational performance of the driving motor. At the same time, in order to reduce the manual workload, the image recognition model is established according to convolutional neural network to find out the target output image. Finally, the proposed method is subjected to simulation analysis. The results indicate that this strategy can to some extent achieve identification and optimization of motor system parameters. Additionally, the algorithm can reduce the complexity of modal calculations for motor systems and the image recognition model can find the target pattern accurately, demonstrating practical value.

关键词： Vibrations image recognition Modal analysis Software algorithms Manuals Motors Structural engineering

来源：评论

学校读者我要写书评

暂无评论

A Binocular Stereo Vision Packaging Dimension Measurement Algorithm Based on Improved SURF 3

A Binocular Stereo Vision Packaging Dimension Measurement Al...

引用

3rd International conference on Computer Vision and pattern analysis, ICCPA 2023

作者： Zhou, Xin Zhang, Zhigang School of Communication Engineering Chongqing College of Electronic Engineering Chongqing401331 China College of Information Technology Jiaozuo University Jiaozuo454003 China

ISBN: (纸本)9781510667563

To achieve non-contact automatic measurement of packaging cases in the transportation process of the logistics industry, such as secondary packaging, transshipment, and warehousing, a machine vision dimension measurement system based on binocular stereo vision was proposed. Firstly, the method of combining the SURF algorithm with FREAK descriptor improves the execution efficiency of the algorithm while ensuring the acquisition of better identification feature points;Then, the MISMATCHING feature points are eliminated through the PROSAC mechanism, and the initial disparity map is optimized using bilateral filtering. The spatial information of the measured object is obtained through three-dimensional reconstruction;Finally, a combination of Canny edge detection and Harris corner detection is used to extract the edge information of the object, and the geometric description of the external contour of the target object is obtained through line fitting and calculate the precise size of the measured object through the modified three-dimensional space volume. The experimental results show that this method can effectively identify and describe the shape of various specifications of the measured object, and the measurement error and real-time performance can solve the industrial requirements of the logistics industry. © 2023 SPIE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Classification of Non-motorized Vehicle Based on Micro-Doppler Effect and image Processing 3

Classification of Non-motorized Vehicle Based on Micro-Doppl...

引用

3rd International conference on Computer Vision and pattern analysis, ICCPA 2023

作者： Lin, Yang Liu, Jing Zhu, Lingzhi Zhang, Shuning School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing China School of Networks and Telecommunications Engineering Jingling Institute of Technology Nanjing China

ISBN: (纸本)9781510667563

With the rise of the take-out food industry and bicycle sharing, the frequency of non-motorized vehicle using has increased significantly, and the ensuing safety hazards have become increasingly serious. Since motor vehicles are always subject to traffic violations by non-motorized vehicles, it is important to classify non-motorized vehicles for optimal handling in emergency situations. Due to the uniqueness of the target information, the micro-Doppler effect is increasingly used to distinguish between different targets. In this paper, we propose a non-motorized vehicle classification method based on the micro-Doppler effect and image processing. Firstly, the relationship model between ground non-motorized vehicles and radar is established, the expression of the echo signal is derived, and the simulation analysis is carried out according to the set parameters, the differences between the non-motorized time-domain frequency domain diagrams and the joint time-frequency diagrams were investigated. Secondly, the classification features of the car hub echo signal are introduced, and the feasibility of these features as classification criteria is verified by simulations. Then, the feature extraction methods based on image processing are introduced, and the extraction results of different edge detection operators are compared and analyzed. Finally, the classification method of non-motorized vehicles based on these three features is introduced. © 2023 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Lifelong Learning for Document image Binarization: An Experimental Study 11th

Lifelong Learning for Document Image Binarization: An Experi...

引用

11th iberian conference on pattern recognition and image analysis, IbPRIA 2023

作者： González-Barrachina, Pedro Alfaro-Contreras, María Nieto-Hidalgo, Mario Calvo-Zaragoza, Jorge University of Alicante Alicante Spain

ISBN: (纸本)9783031366154

Binarization is one of the ubiquitous processes in the field of document image analysis. In recent years, there has been an increasing number of approaches based on deep learning, which in turn require labeled data of each document collection. In many real cases, however, the possible domains of document collections are not known in advance but appear incrementally. Adapting a model to accommodate new domains is known as lifelong (or continual) learning. In this scenario, neural networks suffer from catastrophic forgetting;i.e., when learning about a new domain, the knowledge from the previous ones is lost. This paper presents an experimental study of alternatives to prevent catastrophic forgetting in a continuous learning scenario for document binarization. We present results with different evaluation protocols considering four different document collections of heterogeneous features. Our results show that while there is no single approach that consistently outperforms the others, all of the proposed mechanisms help prevent catastrophic forgetting to some extent. Interestingly, we found that relatively simple mechanisms such as transfer learning tend to perform better on average than specifically designed strategies for continual learning. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Extracting Descriptive Words from Untranscribed Handwritten images 10th

Extracting Descriptive Words from Untranscribed Handwritten ...

引用

10th iberian conference on pattern recognition and image analysis (IbPRIA)

作者： Ramon Prieto, Jose Vidal, Enrique Andreu Sanchez, Joan Alonso, Carlos Garrido, David Univ Politecn Valencia PRHLT Res Ctr Valencia Spain TranSkriptorium AI Valencia Spain Univ Cadiz HUM313 Res Grp Cadiz Spain

ISBN: (纸本)9783031048814;9783031048807

Extracting descriptive text from manuscripts to be included in the manuscript metadata is an important task that is generally performed in archives and libraries by experts with a wealth of knowledge on the manuscripts contents. Unfortunately, many manuscript collections are so vast that it is not feasible to rely solely on experts to perform this task. To our knowledge, this is the first work aiming at automatic extraction of descriptive text from untranscribed text images. To attempt dealing with such a task, a first step would be to transcribe the handwritten images into text - but achieving sufficiently accurate transcripts is generally unfeasible for large sets of historical manuscripts. We propose new approaches to automatically extract descriptive words which do not rely on any explicit image transcripts. They are based on "probabilistic indexing" , a relatively novel technology which allows to effectively represent the intrinsic word-level uncertainty generally exhibited by handwritten text images. We assess the performance of this approach on samples of a large collection of complex manuscripts from the Spanish Archivo General de Indias. Since no standard metrics exist for the novel task considered in this work, we propose two new evaluation measures which aim at measuring the quality of the detected descriptive words in terms close to practical usage of these words. Using these metrics we report promising preliminary results.

关键词： Descriptive words Content-based image retrieval Historical manuscripts

来源：评论

学校读者我要写书评

暂无评论

Differential Gene Expression analysis of the Most Relevant Genes for Lung Cancer Prediction and Sub-type Classification 10th

Differential Gene Expression Analysis of the Most Relevant G...

引用

10th iberian conference on pattern recognition and image analysis (IbPRIA)

作者： Ramos, Bernardo Pereira, Tania Silva, Francisco Costa, Jose Luis Oliveira, Helder P. INESC TEC Inst Syst & Comp Engn Technol & Sci Porto Portugal Univ Porto FCUP Fac Sci Porto Portugal Univ Porto i3S Inst Invest & Inovacao Saude Porto Portugal Univ Porto IPATIMUP Inst Mol Pathol & Immunol Porto Portugal Univ Porto FMUP Fac Med Porto Portugal

ISBN: (纸本)9783031048814;9783031048807

An early diagnosis of cancer is essential for a good prognosis, and the identification of differentially expressed genes can enable a better personalization of the treatment plan that can target those genes in therapy. This work proposes a pipeline that predicts the presence of lung cancer and the subtype allowing the identification of differentially expressed genes for lung cancer adenocarcinoma and squamous cell carcinoma subtypes. A gradient boosted tree model is used for the classification tasks based on RNA-seq data. The analysis of gene expressions that better differentiate cancerous from normal tissue, and features that distinguish between lung subtypes is the main focus of the present work. Differential expressed genes are analyzed by performing hierarchical clustering in order to identify gene signatures that are commonly regulated and biological signatures associated with a specific subtype. This analysis highlighted patterns of commonly regulated genes already known in the literature as cancer or subtype-specific genes, and others that are not yet documented in the literature.

关键词： AI-based prediction models Feature importance Gene signatures Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Research on On-line Data Prediction of Electrical Equipment Based on Wavelet analysis and Data Fusion 22

Research on On-line Data Prediction of Electrical Equipment ...

引用

3rd Asia-Pacific conference on image Processing, Electronics and Computers, IPEC 2022

作者： Wang, Guorong Mao, Wentao Tang, Yingzhi Xiao, Yan School Mechatronic Engineering Wuhan Donghu University Wuhan430212 China Wuhan Donghu University Wuhan430212 China School of Computer Science Wuhan Donghu University Wuhan430212 China

ISBN: (纸本)9781450395786

In the process of fault analysis and diagnosis of electrical equipment, it is of great significance to use wavelet transform to detect the fault time of fault signal. In order to overcome this deficiency, wavelet analysis can decompose mixed signals with different frequencies into block signals with different frequency components, which can effectively separate signal from noise, extract features and diagnose faults. According to the virtual instrument solution, this paper comprehensively processes various multi-source fault data information through data fusion technology. In fault pattern recognition, how to make full use of the advantages of various diagnosis methods, combine each other and learn from each other is of great significance to improve the resolution of fault pattern and enhance the comprehensiveness and reliability of fault diagnosis. Data fusion technology is a new frontier discipline to study multi-source information processing and analysis methods. In military, information processing and other fields, the application of multi-sensor data fusion technology to fault diagnosis has attracted more and more attention. This paper discusses the application characteristics of electrical equipment based on wavelet analysis and data fusion, and gives the latest research results and development trend. © 2022 Association for Computing Machinery. All rights reserved.

关键词： Wavelet analysis

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149页 << < 10 11 12 13 14 15 16 17 18 19 > >>

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：