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

7,403 篇 会议
348 篇 期刊文献
57 册 图书
17 篇 学位论文

馆藏范围

7,825 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,450 篇 工学
- 3,422 篇 计算机科学与技术...
- 1,717 篇 软件工程
- 1,076 篇 电气工程
- 714 篇 信息与通信工程
- 343 篇 控制科学与工程
- 342 篇 电子科学与技术（可...
- 304 篇 光学工程
- 233 篇 机械工程
- 224 篇 生物医学工程（可授...
- 178 篇 仪器科学与技术
- 154 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...
- 53 篇 材料科学与工程（可...
- 47 篇 土木工程
- 42 篇 动力工程及工程热...
- 40 篇 力学（可授工学、理...
1,599 篇 理学
- 781 篇 物理学
- 690 篇 数学
- 181 篇 生物学
- 145 篇 统计学（可授理学、...
- 142 篇 系统科学
- 80 篇 化学
556 篇 医学
- 456 篇 临床医学
- 103 篇 特种医学
- 80 篇 基础医学(可授医学...
446 篇 管理学
- 288 篇 管理科学与工程(可...
- 176 篇 图书情报与档案管...
- 74 篇 工商管理
37 篇 法学
36 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

868 篇 parallel process...
693 篇 image processing
326 篇 image segmentati...
297 篇 concurrent compu...
273 篇 distributed comp...
259 篇 computational mo...
252 篇 computer archite...
250 篇 feature extracti...
215 篇 image reconstruc...
195 篇 image edge detec...
186 篇 image coding
177 篇 graphics process...
170 篇 iterative method...
166 篇 hardware
165 篇 algorithm design...
164 篇 neural networks
160 篇 deep learning
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 national univers...
9 篇 natl univ def te...
9 篇 institute of inf...
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 comput...

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

7,657 篇 英文
112 篇 其他
52 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 7825 条记录，以下是881-890 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：

HPC-in-Containers: A Containerized parallel Environment for parallel Programming Learning Using Docker

HPC-in-Containers: A Containerized Parallel Environment for ...

引用

International conference on Information Technology Systems and Innovation (ICITSI)

作者： Andria Arisal Heru Suhartanto Research Center for Data and Information Sciences National Research and Innovation Agency Bandung Indonesia Faculty of Computer Science University of Indonesia Depok Indonesia

ISBN: (数字)9798331511470

ISBN: (纸本)9798331511487

This paper presents HPC-in-Containers, a novel containerized parallel computing environment using Docker. It is designed to facilitate learning parallel programming concepts, where users do not have to deploy a multicomputer infrastructure. Instead, they can use their desktop and laptop to easily have a multicomputer environment by utilizing containerization on the multi-core CPU. The environment offers a comprehensive platform for exploring various parallel programming paradigms, including distributed memory parallelism, shared memory parallelism, and hybrid approaches. We include source code samples for each paradigm to demonstrate its capabilities: parallel multicomputer implementations using MPI, parallel thread implementations for single computers using OpenMP, and hybrid parallelization techniques combining both MPI and OpenMP. Furthermore, to enhance user interaction and ease of use, the Docker image incorporates a Jupyter Notebook interface with a C interpreter, allowing users to write, execute, and visualize parallel code through a web browser. This feature makes HPC-in-Containers particularly suitable for educational settings, enabling students to experiment with parallel programming concepts in a controlled, reproducible environment. Our work contributes to the field of parallel computing education by providing a flexible, scalable, and easily deployable platform that bridges the gap between theoretical concepts and practical implementation. It offers a valuable resource for educators, students, and researchers seeking to explore and master the intricacies of parallel programming in a containerized setting.

关键词： Visualization Technological innovation Portable computers parallel programming Source coding Instruction sets Education parallel processing User experience Monitoring

来源：评论

学校读者我要写书评

暂无评论

distributed Data Analysis Workflow System across Multiple Data Hubs

Distributed Data Analysis Workflow System across Multiple Da...

引用

IEEE International conference on Big Data

作者： Siwoon Son Seong-Hwan Kim Heesun Won CybreBrain Section Electronics and Telecommunications Research Institute Daejeon Korea

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

In multisite data hub environments, data transfer costs and resource constraints challenge efficient data analysis workflow execution. Traditional analysis methods across multi-hubs often reduce performance and increase costs. To address these challenges, we introduce CROSS (Collaborative Resource-Oriented Scheduling System), which optimizes distributed workflows by utilizing data and resources across multiple hubs. CROSS enables collaboration between hubs, minimizes data transfer, and maximizes resource use through an efficient scheduling algorithm that considers data locality, resources, and workflow structure. Experiments with four scientific workflows show CROSS reduces makespan by up to 33.5% and improves CPU and memory efficiency by 1.58x and 1.59x, respectively, making it effective for multisite workflows.

关键词： Data analysis Costs Scheduling algorithms Memory management distributed databases Collaboration parallel processing Big Data Data transfer

来源：评论

学校读者我要写书评

暂无评论

P-ODA: A Fast and Robust parallel Ommatidia Detection Algorithm for High-Throughput Insect Ommatidia Detection

P-ODA: A Fast and Robust Parallel Ommatidia Detection Algori...

引用

Advanced Algorithms and Control Engineering (ICAACE), International conference on

作者： Wentao Zhu Chaofan Zhang Tianhao Zhang Zhenyu Gao Siqin Ge Yong Liu Anhui Institute of Optics and Fine Mechanics Hefei Institutes of Physical Science Chinese Academy of Sciences University of Science and Technology of China Anhui China Anhui Institute of Optics and Fine Mechanics Hefei Institutes of Physical Science Chinese Academy of Sciences Anhui China Key Laboratory of Animal Biodiversity Conservation and Integrated Pest Management Institute of Zoology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Key Laboratory of Animal Biodiversity Conservation and Integrated Pest Management Institute of Zoology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

The automatic detection and analysis of ommatidia, the fundamental visual units of insect compound eyes, is vital for advancing biological research and understanding insect vision. Compound eyes, with their multi-lens structure, provide a broad field of view and high visual resolution. Researchers typically obtain ommatidia structures through CT imaging of insect compound eyes. However, processing these high-resolution 3D images requires significant computational resources due to the complexity and scale of the data. Existing methods struggle with inefficiency and poor robustness, particularly when dealing with large and complex datasets. To overcome these challenges, we introduce a groundbreaking framework, P-ODA, for fast and robust ommatidia detection by integrating parallel computing into the CT image analysis insect compound eyes. By harnessing the power of both Graphics processing Units (GPUs) with Compute Unified Device Architecture (CUDA) and multicore Central processing Units (CPUs), we present a novel approach to enhance the Ommatidia Detection Algorithm (ODA). Our method efficiently processes large-scale datasets and demonstrates unprecedented scalability. We offer two independent implementations: one utilizing CUDA for GPU acceleration, and another leveraging Python's multicore CPU capabilities. Experimental results show that P-ODA dramatically improves execution time and scalability over traditional ODA methods. Moreover, the system is designed for ease of use with a Linux graphical interface. This innovative framework sets the stage for the next generation of biological dataset processing and hybrid parallel computing systems.

关键词： Visualization Insects Computed tomography Scalability Graphics processing units parallel processing Biology Central processing Unit Compounds Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Early Warning Support System for Financial Crisis based on Fully Homomorphic Encryption Algorithm

An Intelligent Early Warning Support System for Financial Cr...

引用

distributed Systems, Computer Networks and Cybersecurity (ICDSCNC), International conference on

作者： Fanling Kong College of Finance and Economics Guangdong University of Science &Technology Dongguan China

ISBN: (数字)9798350375442

ISBN: (纸本)9798350375459

The financial crisis has an important impact on social and economic development, and the existing economic management methods cannot achieve massive data analysis, so on this basis This paper proposes an intelligent early warning support system for financial crisis based on fully homomorphic encryption algorithm to solve the problems of data privacy and security in the traditional early warning system. In this paper, the appropriate CKKS fully homomorphic encryption algorithm is used to implement encryption, decryption and homomorphic operations. The results show that the fully homomorphic encryption algorithm can be simplified, with a simplification rate of 10%, and polynomial adjustment can be realized, which can improve the early warning efficiency of financial crisis to 90%, which is better than the traditional method. Therefore, the financial crisis intelligent early warning system established in this paper can be used and promoted in an efficient and comprehensive manner.

关键词： Economics Data privacy Accuracy Data analysis distributed databases Alarm systems parallel processing Polynomials Homomorphic encryption Optimization

来源：评论

学校读者我要写书评

暂无评论

Single-View Reconstruction via Decoupled 3D Gaussian Splatting

Single-View Reconstruction via Decoupled 3D Gaussian Splatti...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Sheng Liu Shiming Zhu Huilong Pi Yunchuan Qin Zhuo Tang Ruihui Li College of Computer Science and Electronic Engineering Hunan University Changsha China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Creating high-quality 3D object representations from a single-view image is challenging. Existing methods tend to infer the geometry and texture information simultaneously within a shared network. However, decoding geometry and texture from a unified network often leads to their entanglement, causing geometric structure collapse or floating artifacts. After revisiting this task, we propose a single-view reconstruction framework based on 3D Gaussian Splatting. The key idea is to decouple Gaussian position attribute generation from texture feature generation. Technically, our framework combines a Geometry Generator, a Texture Generator, and a Gaussian Attributes Decoder. Two parallel branches, Geometry Generator and Texture Generator, aim for point cloud prediction and texture optimization, respectively. Then the Gaussian Attributes Decoder integrates the generated position and texture attributes into a coherent Gaussian point cloud, facilitating efficient novel view synthesis. Extensive qualitative and quantitative evaluations of public datasets demonstrate that our method consistently outperforms existing methods in terms of reconstruction quality and inferring efficiency.

关键词： Geometry Point cloud compression Three-dimensional displays Signal processing Reconstruction algorithms Generators Decoding Speech processing image reconstruction Optimization

来源：评论

学校读者我要写书评

暂无评论

Integrate Memory Efficiency methods for Self-supervised Learning on Pathological image Analysis

Integrate Memory Efficiency Methods for Self-supervised Lear...

引用

conference on Medical Imaging - image processing

作者： Liu, Quan Millis, Bryan A. Asad, Zuhayr Cui, Can Dean, William F. Smith, Isabelle T. Madden, Christopher Roland, Joseph T. Zwerner, Jeffrey P. Zhao, Shilin Wheless, Lee E. Huo, Yuankai Vanderbilt Univ Dept Elect Engn & Comp Sci Nashville TN 37235 USA Vanderbilt Univ Dept Cell & Dev Biol Nashville TN 37235 USA Vanderbilt Univ Coll Arts & Sci Nashville TN 37235 USA SUNY Downstate Hlth Sci Univ Coll Med Brooklyn NY 11203 USA Vanderbilt Univ Med Ctr Dept Pathol Nashville TN 37215 USA Vanderbilt Univ Med Ctr Dept Dermatol Nashville TN 37215 USA

ISBN: (数字)9781510649408

ISBN: (纸本)9781510649408;9781510649392

Contrastive learning, a recent family of self-supervised learning, leverages pathological image analysis by learning from large-scale unannotated data. However, the state-of-the-art contrastive learning methods (e.g., SimCLR, BYOL) are typically limited by the more expensive computational hardware (with large GPU memory) as compared with traditional supervised learning approaches in achieving large training batch size. Fortunately, recent advances in the machine learning community provide multiple approaches to reduce GPU memory usage, such as (1) activation compressed training, (2) In-place activation, and (3) mixed precision training. Yet, such approaches are currently deployed independently without systematical assessments for contrastive learning. In this work, we applied these memory-efficient approaches into a self-supervised framework. The contribution of this paper is three-fold: (1) We combined previously independent GPU memory-efficient methods with self-supervised learning framework;(2) Our experiments are to maximize the memory efficiency via limited computational resources (a single GPU);(3) The self-supervised learning framework with GPU memory-efficient method allows a single GPU to triple the batch size that typically requires three GPUs. From the experimental results, contrastive learning model with larger batch size leads to higher accuracy enabled by GPU memory-efficient method on single GPU.

关键词： GPU acceleration parallel computing mixed precision self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

An image Stitching Technique Based on image Moments

An Image Stitching Technique Based on Image Moments

引用

Intelligent Computing and Robotics (ICICR), International conference on

作者： Changjin Li Jiquan Yuan Xinyan Cao Wei Ren Xixin Cao School of Software and Microelectronics Peking University Beijing China

ISBN: (数字)9798350372274

ISBN: (纸本)9798350372281

With the evolution of technology and the advancement of computer science, image moments have gained increasingly widespread application in the field of image analysis. Geometric moment computation stands as a pivotal topic in the domain of image processing. Nevertheless, the computational complexity associated with moment calculations is relatively high, to a certain extent constraining its practical applicability. This paper delves into the investigation of various aspects, including the representation of high-order moments, the selection of image moment orders, parallel computation of image moments, and image stitching based on image moments. It deduces high-order moment functions, utilizing these higher-order moments for the extraction of image features, thereby enhancing the accuracy and stability of image feature representation. Based on actual images, the algorithm selects the expression of moment function orders, balancing the choice of image moment orders by weighing preset target quantities and sampling parameters. This provides a more targeted image moment calculation scheme for practical applications. The moment calculation algorithm is optimized by transforming multiplication operations into addition operations, simplifying the complexity of the original serial calculations. Through parallel computation, the computational workload is reduced, thus enhancing the performance of image moments in practical applications. Employing machine learning methods and deep learning techniques in conjunction with image moments facilitates image recognition and classification, thereby improving recognition efficiency.

关键词： Deep learning Computer science image recognition Accuracy Machine learning algorithms image analysis Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Jigsaw: A Slice-and-Dice Approach to Non-uniform FFT Acceleration for MRI image Reconstruction 35

Jigsaw: A Slice-and-Dice Approach to Non-uniform FFT Acceler...

引用

35th IEEE International parallel and distributed processing Symposium (IPDPS)

作者： West, Brendan L. Fessler, Jeffrey A. Wenisch, Thomas F. Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9781665440660

The Fast Fourier Transform (FFT) is a fundamental algorithm in signal processing;significant efforts have been made to improve its performance using software optimizations and specialized hardware accelerators. Computational imaging modalities, such as MRI, often rely on the Non-uniform Fast Fourier Transform (NuFFT), a variant ()I' the EFT for processing data acquired from non-uniform sampling patterns. The most time-consuming step of the NuFFT algorithm is "gridding," wherein non-uniform samples are interpolated to allow a uniform FFT to be computed over the data. Each non-uniform sample affects a window of non-contiguous memory locations, resulting in poor cache and memory bandwidth utilization. As a result, gridding can account for more than 99.6% of the NuFFT computation time, while the FFT requires less than 0.4%. We present Slice-and-Dice, a novel approach to the NuFFT's gridding step that eliminates the presorting operations required by prior methods and maps more efficiently to hardware. Our GPI! implementation achieves gridding speedups of over 250x and 16x vs prior ***-art CPU and GPU implementations, respectively. We achieve further speedup and energy efficiency gains by implementing Slice-and-Dice in hardware with JIGSAW, a streaming hardware accelerator for non-uniform data gridding. JIGSAW uses stall-free fixed-point pipelines to process M non-uniform samples in approximately M cycles, irrespective of sampling pattern-yielding speedups of over 1500x the CPU baseline and 36x the state-of-the-art GPU implementation, consuming similar to 200 mW power and similar to 12 mm(2) area in 16 nm technology. Slice-and-Dice GPU and JIGSAW ASIC implementations achieve unprecedented end-to-end NuFFT speedups of 8x and 36x compared to the state-of-the-art GPU implementation, respectively.

关键词： Runtime Power demand Fast Fourier transforms Magnetic resonance imaging Software algorithms Graphics processing units Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Labeled image Segmentation and Retrieval for Fast images processing Using K-NN Algorithm

Labeled Image Segmentation and Retrieval for Fast Images Pro...

引用

International conference on Science Technology Engineering and Management (ICONSTEM)

作者： T.R. Chenthil B. Arun Vijayakumar S. Ranjith G. Balachandran Department of Electronics and Communication Engineering Jeppiaar Engineering College Chennai Tamilnadu India

In digital world the image processing has made a revolution. The demand for the faster processing needs the image to be compactable. Proposed work provides an segmentation and image retrieval technique for faster processing of the segmented image in a parallel manner .The image mid points are obtained and segmented, Each segmented image is named according and stored in an individual address with 24 bit numbers . The segmentation image is further segmented and stored under the First level of segmented image for easier processing this is done in an iterative manner is proposed as mid-point segmentation technique (MPS). The image segmentation level depends on the user requirement. The image retrieval is done by the address or label given to the each segmented image this methods is proposed as addressing image retrieval(AIR) technique. It avoids confusion in the image revival process. image segmented using mid-point segmentation technique islabed, feature are extracted and formed as the network using K-NN Algorithm (K-NN ALGORITHM). It enable the image retrieval with addressing image retrieval method for quick reterival in image *** the area of securing the data in the image which provides dual layer of security.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accelerating Geo-distributed Transaction processing with Fast Logging

Accelerating Geo-Distributed Transaction Processing with Fas...

引用

9th IEEE International conference on Big Data (IEEE BigData)

作者： Ogura, Takuto Akita, Yoshiki Miyazawa, Yuki Kawashima, Hideyuki Mitsubishi UFJ Informat Technol Harumi 2-1-40 Tokyo Japan Keio Univ Fac Environm & Informat Studies Endo 5322 Fujisawa Kanagawa Japan

ISBN: (纸本)9781665439022

We herein propose three novel optimization methods to accelerate distributed transaction processing into a geographically distributed database. The first optimization involves the parallelization of the write-ahead logging protocol. It allows multiple worker threads to synchronize log entries to the storage device simultaneously without any dependencies. The second optimization involves the grouped transfer of log entries from the leader to followers. This reduces the number of transmissions and effectively uses the network bandwidth. The third optimization involves the separation of the worker thread logic. By breaking the logic into the prepare phase and the commit phase, the worker threads at the leader node run asynchronously in parallel without waiting for responses from the follower nodes. The experimental results demonstrated that the proposed method achieved more than 10 million tps and less than 100 ms with client interactions through the network. The CPU utilization was almost 100%, which implied a dramatic reduction in synchronization in worker threads.

关键词： Geo-distributed Database distributed Transaction distributed Consistency Recovery

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 << < 85 86 87 88 89 90 91 92 93 94 > >>

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：