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

7,427 篇 会议
348 篇 期刊文献
57 册 图书
13 篇 学位论文

馆藏范围

7,845 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,458 篇 工学
- 3,430 篇 计算机科学与技术...
- 1,724 篇 软件工程
- 1,074 篇 电气工程
- 722 篇 信息与通信工程
- 352 篇 控制科学与工程
- 339 篇 电子科学与技术（可...
- 307 篇 光学工程
- 234 篇 机械工程
- 225 篇 生物医学工程（可授...
- 177 篇 仪器科学与技术
- 152 篇 生物工程
- 90 篇 测绘科学与技术
- 59 篇 化学工程与技术
- 56 篇 航空宇航科学与技...
- 48 篇 材料科学与工程（可...
- 47 篇 土木工程
- 41 篇 动力工程及工程热...
- 40 篇 力学（可授工学、理...
1,602 篇 理学
- 783 篇 物理学
- 695 篇 数学
- 181 篇 生物学
- 144 篇 统计学（可授理学、...
- 143 篇 系统科学
- 82 篇 化学
562 篇 医学
- 459 篇 临床医学
- 108 篇 特种医学
- 81 篇 基础医学(可授医学...
448 篇 管理学
- 290 篇 管理科学与工程(可...
- 179 篇 图书情报与档案管...
- 74 篇 工商管理
37 篇 法学
35 篇 农学
23 篇 经济学
20 篇 文学
17 篇 教育学
7 篇 艺术学
6 篇 军事学

主题

872 篇 parallel process...
691 篇 image processing
326 篇 image segmentati...
297 篇 concurrent compu...
272 篇 distributed comp...
266 篇 computational mo...
253 篇 computer archite...
253 篇 feature extracti...
216 篇 image reconstruc...
201 篇 image edge detec...
184 篇 image coding
177 篇 graphics process...
170 篇 iterative method...
165 篇 deep learning
165 篇 hardware
164 篇 algorithm design...
163 篇 neural networks
159 篇 computer science
142 篇 pixel
140 篇 graphics process...

机构

47 篇 national laborat...
25 篇 college of compu...
21 篇 natl univ def te...
20 篇 natl univ def te...
19 篇 science and tech...
14 篇 natl univ def te...
13 篇 school of comput...
12 篇 univ chinese aca...
11 篇 king saud univer...
11 篇 university of ch...
11 篇 natl univ def te...
10 篇 institute of inf...
10 篇 national univers...
9 篇 natl univ def te...
9 篇 national laborat...
8 篇 natl univ def te...
8 篇 department of co...
8 篇 national laborat...
8 篇 college of compu...
8 篇 school of cyber ...

作者

37 篇 dou yong
28 篇 luo zhigang
27 篇 yong dou
21 篇 zhang xiang
19 篇 zhigang luo
18 篇 li dongsheng
17 篇 naiyang guan
17 篇 qiao peng
15 篇 huang xuhui
15 篇 jie liu
14 篇 niu xin
13 篇 yijie wang
13 篇 lan long
13 篇 wang huaimin
12 篇 anon
11 篇 xiang zhang
11 篇 yang yang
11 篇 liu jie
11 篇 wang yijie
11 篇 pesquet jean-chr...

语言

7,495 篇 英文
294 篇 其他
54 篇 中文
7 篇 土耳其文
3 篇 俄文

检索条件"任意字段=Conference on Parallel and Distributed Methods for Image Processing"

共 7845 条记录，以下是781-790 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：

FedCav: Contribution-aware Model Aggregation on distributed Heterogeneous Data in Federated Learning 21

FedCav: Contribution-aware Model Aggregation on Distributed ...

引用

50th International conference on parallel processing (ICPP)

作者： Zeng, Hui Zhou, Tongqing Guo, Yeting Cai, Zhiping Liu, Fang Natl Univ Def Technol Coll Comp Changsha Peoples R China Hunan Univ Sch Design Changsha Peoples R China

ISBN: (纸本)9781450390682

The emerging federated learning (FL) paradigm allows multiple distributed devices to cooperatively train models in parallel with the raw data retained locally. The local-computed parameters will be transferred to a centralized server for aggregation. However, the vanilla aggregation method ignores the heterogeneity of the distributed data, which may lead to slow convergence and low training efficiency. Yet, existing data scheduling and improved aggregation methods either incur privacy concerns or fail to consider the finegrained heterogeneity. We propose FedCav, a contribution-aware model aggregation algorithm that differentiates the merit of local updates and explicitly favors the model-informed contributions. The intuition is that the local data showing higher inference loss is likely to facilitate better performance improvement. To this end, we design a novel global loss function with explicit optimization preference on informative local updates, theoretically prove its convex property, and use it to regulate the gradient descent process iteratively. Additionally, we propose to identify abnormal updates with fake loss by auditing historic local training statistics. The results of extensive experiments demonstrate that FedCav needs fewer training rounds (similar to 34%) for convergence and achieves better inference accuracy (similar to 2.4%) than the baselines (i.e., FedAvg and FedProx). We also observe that FedCav can actively mitigate the model replacement attacks with agile recovery capability towards the aggregation.

关键词： federated learning data heterogeneity model replacement

来源：评论

学校读者我要写书评

暂无评论

引用

International conference on parallel distributed and Grid Computing (PDGC)

作者： Shailesh Bhosekar Prabhishek Singh Deepak Garg School of Computer Science and Artificial Intelligence SR University Warangal Telangana India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (数字)9798331521349

ISBN: (纸本)9798331521356

image fusion is a critical domain in image processing that integrates two or more compromised or obscured images into a single, clearer, and more informative result. Multi-modal medical image fusion (M3IF), a category of image fusion, amalgamates images from many medical modalities into a single complete image, hence augmenting diagnostic efficacy. This research examines the integration of Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) to enhance the precision and detail of medical visualization. The suggested hybrid approach (M3IF-FSIM-DC) utilizes Stationary Wavelet Transform (SWT) to decompose input medical CT and MRI images into low-frequency components (LFC) and high-frequency components (HFC). The LFC are amalgamated using the Feature Similarity Index Metric (FSIM), therefore preserving structural and feature- based information. The HFC are integrated using a directive contrast-based fusion rule that maintains edge details and minimizes artifacts. This hybrid M3IF-FSIM-DC methodology tackles significant issues in medical image fusion, such as the loss of intricate features, edge blurring, and distortion, while improving visual quality and parametric precision. M3IF-FSIM-DC enhances diagnostic understanding by preserving more essential information from each modality, surpassing current procedures. The improved fusion quality enables medical practitioners to understand intricate medical images more effectively, offering a more reliable instrument for clinical decision-making and analysis.

关键词： Wavelet transforms Visualization Accuracy Magnetic resonance imaging Computed tomography image edge detection Decision making Distortion Medical diagnostic imaging image fusion

来源：评论

学校读者我要写书评

暂无评论

A Robust Visual Localization Method with 4 DOF in the Case of Planar Motion

A Robust Visual Localization Method with 4 DOF in the Case o...

引用

Information Science, parallel and distributed Systems (ISPDS), International conference on

作者： Binxin Zhang Hangzhou Normal University Hangzhou P. R. China

ISBN: (数字)9798350352719

ISBN: (纸本)9798350352726

As robotics technology advances rapidly, robots are being extensively utilized in a variety of areas including warehouse inspection, logistics handling, and smart homes. However, in methods utilizing 2D image databases for visual localization, factors such as dynamic object interference, changes in lighting conditions, and environments with low texture lead to high errors in image feature matching points and sparse matching points, thereby reducing the success rate of localization. To tackle this problem, this study introduces a robust visual localization method for planar motion scenarios. Unlike existing approaches that focus solely on rotation around the Y-axis, this method accounts for rotations around both the X-axis and the Y-axis. By incorporating motion constraints, it optimizes the estimation of the essential matrix and the triangulation process. This reduces the need for 2D-2D feature matching points between query images and reference images in the database, thereby enhancing the robustness of the localization method. Finally, the proposed method demonstrates higher localization accuracy, robustness, and success rate in both simulation experiments and publicly available real-world localization datasets. This provides a significant approach for addressing the localization challenges of planar motion robots.

关键词： Location awareness Visualization Transmission line matrix methods Estimation Lighting Smart homes Interference

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Multi-Slice MRI Reconstruction Using Outline Information and Multiple Variable Density Sampling

Simultaneous Multi-Slice MRI Reconstruction Using Outline In...

引用

IEEE International conference on Signal and image processing (ICSIP)

作者： Yongxiang Fang Lin Chen Jiabing Sun Jiawen Huang Huabin Zhang Bensheng Qiu Medical Imaging Center University of Science and Technology of China Hefei Anhui China Anhui Fuqing Medical Equipment Co. Ltd Institute of advanced technology university of science and technology of China Hefei Anhui China

ISBN: (数字)9798350350920

ISBN: (纸本)9798350350937

In Magnetic Resonance Imaging (MRI), Simultaneous Multi-Slice (SMS) using parallel reconstruction has become a major image technique to accelerate data acquisition. In these reconstructions, it is crucial to mitigate the inter-slice aliasing caused by SMS and the artifacts due to undersampling in parallel MRI (pMRI). In this study, we proposed to incorporate the outline information present in different slices to address inter-slice aliasing in SMS data. Additionally, the Multiple Variable Density Sampling (MVDS) method was proposed in SMS to reduce the undersampling-induced aliasing artifacts. This approach enhances image quality by utilizing sampling schemes with multiple reduction factors. Furthermore, the outline information and MVDS can be used jointly. In an experiment, the proposed reconstruction methods were compared with advanced algorithms such as SPSG, SMS-COOKIE, and ROCK-SPIRiT based on traditional uniform undersampling methods using in vivo human brain data evaluated by PSNR and mean structure similarity. Experimental results demonstrate that our proposed method (i.e. SMS with outline information or MVDS) improves image reconstruction performance by reducing noise and artifacts as compared to traditional methods. The joint use of outline information and MVDS further suppress the noise and artifacts in the reconstructed images,

关键词： image quality In vivo Magnetic resonance imaging Noise Noise reduction Data acquisition Reconstruction algorithms

来源：评论

学校读者我要写书评

暂无评论

Generative Enhancement-based Similarity Prediction Hashing for image Retrieval

Generative Enhancement-based Similarity Prediction Hashing f...

引用

International conference on parallel and distributed Systems (ICPADS)

作者： Yuan Cao Fanlei Meng Xiangyu Wu Zijie Wang School of Computer Science and Technology Ocean University of China Qingdao China

Hashing is frequently used in approximate nearest neighbor search due to its storage and search efficiency. On account of the bottleneck of traditional learning to hash methods, deep-based learning to hash has gained quite a popularity among researchers recently. While such methods show a promising performance gain by utilizing deep neural networks into its end-to-end training process to generate compact binary codes, the intrinsic connections between components make it unfeasible to optimize the architecture significantly. Subject to noise interference and absence of similarity labels of training data, normal unsupervised deep models even carry a noticeable deviation at representation learning stage. By integrating Generative Adversarial Network, this paper presents a novel architecture for generating compact hash codes from an extended set derived from original images while using the benefit of similarity prediction. Extensive experiments conducted on three benchmarks, NUS-WIDE, CIFAR-10, and MS-COCO illustrate that our method outperforms state-of-the-art image retrieval models and generates high-quality binary hash codes seamlessly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Test Paper Generation Algorithm Integrating Normal Distribution and parallel Genetic Algorithm

Intelligent Test Paper Generation Algorithm Integrating Norm...

引用

Intelligent Computing and Human-Computer Interaction (ICHCI), International conference on

作者： Chuangye Liu Guimin Huang Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350368284

ISBN: (纸本)9798350368291

Genetic algorithms have been widely used in intelligent test paper generation systems. However, traditional genetic algorithms cannot ensure that the difficulty of test questions is normally distributed, and are prone to falling into local optimal solutions. To address the above problems, we proposed an intelligent test paper generation algorithm that combines normal distribution and parallel genetic algorithms. In the population initialization stage, we use the cumulative distribution function (CDF) of the normal distribution to initialize the population. In the subsequent genetic operations, we designed a directed mutation mechanism and added KL divergence as a penalty number in the design of the fitness function to ensure that the difficulty of the test questions is normally distributed. At the same time, in order to speed up the efficiency of the algorithm and escape from the local optimal solution, an adaptive migration strategy was introduced. Experimental results show that the difficulty of the test questions generated by this algorithm is normally distributed, and the algorithm performance is better than other algorithms.

关键词： Human computer interaction Heuristic algorithms Gaussian distribution Genetics Genetic algorithms Distribution functions Convergence

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Techniques and Approaches in Medical image Fusion

Comprehensive Analysis of Techniques and Approaches in Medic...

引用

distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International conference on

作者： Hayath T. M Sai Madhavi D Department of Computer Science and Engineering Ballari Institute of Technology and Management Ballari India Visvesvaraya Technological University Belagavi India Department of Artificial Intelligence and Machine Learning Rao Bahadur Y Mahabaleshwarappa Engineering College Ballari India

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

Medical image fusion is a major area in the field of medical imaging, the main objective is to integrate information from multiple imaging modalities to improve diagnostic accuracy. Medical image fusion brings together different types of imaging data—like MRI, CT, and PET scans—to compensate for the weaknesses of using just one method. By merging these complementary views, medical professionals gain a clearer, more complete picture of what’s happening inside the body, which leads to better diagnoses and smarter treatment plans. This article explore the latest techniques for combining these images, from traditional approaches to cutting-edge AI tools. Older methods, such as wavelet transforms and principal component analysis (PCA), focus on preserving fine details like edges and textures but often struggle with noisy images or slow processing. Newer AI-driven methods, like generative adversarial networks (GANs) and transformers, excel at learning complex patterns from data, creating sharper fused images. By examining the strengths, limitations, and practical implications of each technique, this paper offers a structured analysis of fusion methods and their applications.

关键词： Deep learning Wavelet transforms Accuracy Computational modeling image edge detection Wavelet analysis Integrated circuit modeling Medical diagnostic imaging image fusion Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Optimization Modeling and Simulation of Motion Monitoring based on Multi layer Perceptual Neural Network

Optimization Modeling and Simulation of Motion Monitoring ba...

引用

distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International conference on

作者： Limin Zhang Kang Shao Yingjie Li Cong Liu Weifang Engineering Vocational College Weifang China Beihang University Beijing China

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

In order to solve the problems of signal noise interference, low accuracy of motion pattern recognition, and high real-time requirements in motion monitoring, an optimization method based on MLP (multi-layer perceptron) is used to improve the accuracy and real-time performance of the motion monitoring system. First, the signal preprocessing algorithms such as wavelet transform denoising and filtering are used to ensure the quality of input data. Then, combined with the MLP model, data parallel processing strategy and model pruning technology are adopted to ensure that the motion monitoring system can run efficiently under large-scale data input. In all 20 tests, the response time and processing delay of the lightweight model have a small fluctuation range, with a response time of 97~100 milliseconds and a processing delay of 104~107 milliseconds, providing a new technical path for the field of motion monitoring.

关键词： Accuracy Noise Optimization methods Interference Real-time systems Data models Delays Time factors Monitoring Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

A System Architecture in Multiple Views for an image processing Graphical User Interface 23

A System Architecture in Multiple Views for an Image Process...

引用

23rd International conference on Enterprise Information Systems, ICEIS 2021

作者： Maciel, Roberto Wagner Santos Soares, Michel S. Dantas, Daniel Oliveira Departamento de Computação Universidade Federal de Sergipe SE São Cristóvão Brazil

ISBN: (纸本)9789897585098

Medical images are important components in modern health institutions, used mainly as a diagnostic support tool to improve the quality of patient care. Researchers and software developers have difficulty when building solutions for segmenting, filtering and visualizing medical images due to the learning curve, complexity of installation and use of image processing tools. VisionGL is an open source library that facilitates programming through the automatic generation of C++ wrapper code. The wrapper code is responsible for calling parallel image processing functions or shaders on CPUs using OpenCL, and on GPUs using OpenCL, GLSL and CUDA. An extension to support distributed processing, named VGLGUI, involves the creation of a client with a workflow editor and a server, capable of executing that workflow. This article presents a description of architecture in multiple views, using the architectural standard ISO/IEC/IEEE 42010:2011, the 4+1 View Model of Software Architecture and the Unified Modeling Language (UML), for a visual programming language with parallel and distributed processing capabilities. Copyright © 2021 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Real time road defect monitoring from UAV visual data sources 23

Real time road defect monitoring from UAV visual data source...

引用

16th ACM International conference on Pervasive Technologies Related to Assistive Environments (PETRA)

作者： Katsamenis, Iason I. K. Bakalos, Nikolaos N. B. Protopapadakis, Eftychios E. P. Karolou, Eleni Eirini E. K. Kopsiaftis, Georgios G. K. Voulodimos, Athanasios A. V. Natl Tech Univ Athens Athens Greece Univ Macedonia Athens Greece

ISBN: (纸本)9798400700699

The use of UAVs and artificial intelligence has emerged as a promising approach for monitoring road defects. This paper highlights the importance of these technologies in improving road inspection, maintenance, and safety. Traditional methods for inspecting roads are often time-consuming, expensive, and can put human inspectors in dangerous situations. However, drones equipped with high-resolution cameras and sensors can capture pavement image data quickly and safely. Deep learning algorithms can then analyze this data to identify and localize areas in need of repair. By leveraging these technologies, engineers and road construction experts can more efficiently monitor and maintain roads, reducing the costs associated with repairs and maintenance, while in parallel improving safety. To this end, this work emphasizes the potential of UAVs in conjunction with deep learning techniques to provide a more comprehensive view of road conditions, allowing for targeted repairs and more effective maintenance strategies, such as prefabrication and robotic interventions. Experimental results using objective evaluation criteria, such as precision, recall, F1-score, and IoU are promising, which entails that this study advocates for the adoption of these technologies to enhance the monitoring and maintenance of road infrastructures.

关键词： Object detection UAV image processing Road infrastructure monitoring Computer vision

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500页 << < 75 76 77 78 79 80 81 82 83 84 > >>

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：