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

7,402 篇 会议
350 篇 期刊文献
57 册 图书
17 篇 学位论文

馆藏范围

7,826 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
- 3,421 篇 计算机科学与技术...
- 1,719 篇 软件工程
- 1,074 篇 电气工程
- 713 篇 信息与通信工程
- 343 篇 控制科学与工程
- 339 篇 电子科学与技术（可...
- 307 篇 光学工程
- 233 篇 机械工程
- 224 篇 生物医学工程（可授...
- 177 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...
- 50 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...
1,599 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
- 79 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

869 篇 parallel process...
693 篇 image processing
326 篇 image segmentati...
297 篇 concurrent compu...
272 篇 distributed comp...
260 篇 computational mo...
252 篇 computer archite...
250 篇 feature extracti...
215 篇 image reconstruc...
195 篇 image edge detec...
185 篇 image coding
177 篇 graphics process...
170 篇 iterative method...
165 篇 algorithm design...
165 篇 hardware
164 篇 neural networks
159 篇 computer science
159 篇 deep learning
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

7,661 篇 英文
109 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 7826 条记录，以下是1351-1360 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：

An Ideal Big Data Architectural Analysis for Medical image Data Classification or Clustering Using the Map-Reduce Frame Work 3rd

An Ideal Big Data Architectural Analysis for Medical Image D...

引用

3rd International conference on Communications and Cyber Physical Engineering, ICCCE 2020

作者： Vasireddi, Hemanth Kumar Suganya Devi, K. Computer Science and Engineering National Institute of Technology-Silchar SilcharAssam788010 India Computer Science Engineering Raghu Institute of Technology VisakhapatnamAndhra Pradesh531162 India

ISBN: (纸本)9789811579608

In the present day scenario, where huge volumes of data are being generated from various sources, as such storing and processing these data using traditional systems is a big challenge. The majority of data is of unstructured;hence necessary architectures should be designed to meet the continuous challenges. Among the possible solutions for the big data problem, one of the best solutions to address the huge volumes of unstructured data was Hadoop. In the medical field, huge volumes of clinical image data are resulting from the respective hardware tools. The necessary methods that are required to store, analyze, process and classification of these medical images can be done with map-reduce architecture using the Hadoop framework thereby reduces the computational time for the overall processing as the mapper will perform parallel processing. This paper includes a detailed review of Hadoop and its components. The main motive of this work is to deal with the medical image data using an efficient architecture such that automatic clustering or classification of images will be done within the architecture itself. The clustering of these medical images for future predictions and diagnosis for the disease is essential. In the map-reduce architecture, along with the map and reduce phases, the usage of combiners and partitioners will improve the efficiency of medical image processing for clustering the image data. The other responsibilities of this paper are to review the recent works in the image data clustering along with the state of art techniques for image classification. The clustered medical images will be used for automatic predictions and diagnosis of various patient diseases by applying Convolution Neural Network (CNN) techniques on top of the clustered or classified images. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Self-supervised image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network

Self-supervised Image Denoising with Downsampled Invariance ...

引用

International conference on Computer Vision (ICCV)

作者： Yeong Il Jang Keuntek Lee Gu Yong Park Seyun Kim Nam Ik Cho Department of ECE INMC Seoul National University Seoul Korea Gauss Labs Inc. IPAI Seoul National University Seoul Korea

There have been many image denoisers using deep neural networks, which outperform conventional model-based methods by large margins. Recently, self-supervised methods have attracted attention because constructing a large real noise dataset for supervised training is an enormous burden. The most representative self-supervised denoisers are based on blind-spot networks, which exclude the receptive field’s center pixel. However, excluding any input pixel is abandoning some information, especially when the input pixel at the corresponding output position is excluded. In addition, a standard blind-spot network fails to reduce real camera noise due to the pixel-wise correlation of noise, though it successfully removes independently distributed synthetic noise. Hence, to realize a more practical denoiser, we propose a novel self-supervised training framework that can remove real noise. For this, we derive the theoretic upper bound of a supervised loss where the network is guided by the downsampled blinded output. Also, we design a conditional blind-spot network (C-BSN), which selectively controls the blindness of the network to use the center pixel information. Furthermore, we exploit a random subsampler to decorrelate noise spatially, making the C-BSN free of visual artifacts that were often seen in downsample-based methods. Extensive experiments show that the proposed C-BSN achieves state-of-the-art performance on real-world datasets as a self-supervised denoiser and shows qualitatively pleasing results without any post-processing or refinement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

InstancePose: Fast 6DoF Pose Estimation for Multiple Objects from a Single RGB image 18

InstancePose: Fast 6DoF Pose Estimation for Multiple Objects...

引用

18th IEEE/CVF International conference on Computer Vision (ICCV)

作者： Aing, Lee Lie, Wen-Nung Chiang, Jui-Chiu Lin, Guo-Shiang Natl Chung Cheng Univ CCU Dept Elect Engn Minxiong Township Chiayi Taiwan Natl Chung Cheng Univ CCU Ctr Innovat Res Aging Soc CIRAS Minxiong Township Chiayi Taiwan Natl Chung Cheng Univ CCU Adv Inst Mfg High Tech Innovat AIM HI Minxiong Township Chiayi Taiwan Natl Chin Yi Univ Technol Dept Comp Sci & Informat Engn Taichung Taiwan

ISBN: (纸本)9781665401913

6DoF object pose estimation depends on positional accuracy, implementation complexity and processing speed. This study presents a method to estimate 6DoF object poses for multi-instance object detection that requires less time and is accurate. The proposed method uses a deep neural network, which outputs 4 types of feature maps: the error object mask, semantic object masks, center vector maps (CVM) and 6D coordinate maps. These feature maps are combined in post processing to detect and estimate multi-object 2D-3D correspondences in parallel for PnP RANSAC estimation. The experiments show that the method can process input RGB images containing 7 different object categories/ instances at a speed of 25 frames per second with competitive accuracy, compared with current state-of-the-art methods, which focus only on some specific conditions.

关键词： Deep learning image segmentation Computer vision Three-dimensional displays conferences Semantics Pose estimation

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis and Recognition of Power Equipment Infrared images Based on Lightweight VGG16 and BCBAM

Fault Diagnosis and Recognition of Power Equipment Infrared ...

引用

Clean Energy and Electric Power Engineering (ICCEPE), International conference on

作者： Bin Zhang Jiaxin Zhang Bingbing Qiu State Grid Liaoning Electric Power Research Institute Shenyang Liaoning Province China State Grid Liaoning Electric Power Co. Ltd. Shenyang Liaoning Province China

ISBN: (数字)9798350390315

ISBN: (纸本)9798350390322

Due to the various defects of power equipment that can affect the normal operation of the power grid, it is of great significance to use infrared images to quickly and accurately identify power equipment faults. A fault diagnosis and recognition algorithm based on the improved VGG model is proposed. The algorithm optimizes the fully connected layer to reduce the computational load of the network and embeds the BCBAM attention mechanism into the network model. Normalization methods are introduced to improve the channel attention module and spatial attention module, thereby improving the accuracy of the algorithm's fault diagnosis and recognition. Based on the original cascading network characteristics and processing process, the linking method is changed to parallel, improving the network structure and performance. Experimental data shows that the model has accurate fault recognition ability, and is superior to Faster RCNN and Resnet in accuracy evaluation indicators. 50 and traditional models such as VGG 16 were used to verify the accuracy of the algorithm in diagnosing and identifying faults.

关键词： Fault diagnosis Accuracy Attention mechanisms image recognition Computational modeling Data models Power grids Character recognition Load modeling Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Lobster: Load Balance-Aware I/O for distributed DNN Training 22

Lobster: Load Balance-Aware I/O for Distributed DNN Training

引用

Proceedings of the 51st International conference on parallel processing

作者： Jie Liu Bogdan Nicolae Dong Li University of California Merced United States of America Argonne National Laboratory United States of America

ISBN: (纸本)9781450397339

The resource-hungry and time-consuming process of training Deep Neural Networks (DNNs) can be accelerated by optimizing and/or scaling computations on accelerators such as GPUs. However, the loading and pre-processing of training samples then often emerges as a new bottleneck. This data loading process engages a complex pipeline that extends from the sampling of training data on external storage to delivery of those data to GPUs, and that comprises not only expensive I/O operations but also decoding, shuffling, batching, augmentation, and other operations. We propose in this paper a new holistic approach to data loading that addresses three challenges not sufficiently addressed by other methods: I/O load imbalances among the GPUs on a node; rigid resource allocations to data loading and data preprocessing steps, which lead to idle resources and bottlenecks; and limited efficiency of caching strategies based on pre-fetching due to eviction of training samples needed soon at the expense of those needed later. We first present a study of key bottlenecks observed as training samples flow through the data loading and preprocessing pipeline. Then, we describe Lobster, a data loading runtime that uses performance modeling and advanced heuristics to combine flexible thread management with optimized eviction for distributed caching in order to mitigate I/O overheads and load imbalances. Experiments with a range of models and datasets show that the Lobster approach reduces both I/O overheads and end-to-end training times by up to 1.5 × compared with state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review of 4-2 Compressors: Based on Accuracy and Performance Analysis

A Review of 4-2 Compressors: Based on Accuracy and Performan...

引用

International conference on Recent Trends in Machine Learning, IOT, Smart Cities and Applications, ICMISC 2020

作者： Venkata Ganesh, P. Jagadeeswara Rao, E. Nandan, Durgesh Department of Electronics and Communication Engineering Aditya College of Engineering and Technology SurampalemAndhra Pradesh India Accendere Knowledge Management Services Pvt. Ltd. CL Educate Ltd. New Delhi India

ISBN: (纸本)9789811572333

A very urgent need for high-speed adders needed in signal processing applications (SPA). Due to parallel addition circuits play a major role in SPA but it appears the errors after adding the input bits. So, few researchers focus to reduce the error in recent years, and also few researchers focus to improve the speed and reduce the area, also they develop the Compressors (COMP) to compare with the conventional methods. COMP is also more useful in image processing application like edge detector method and it also plays a major role in approximate multipliers (MULP’s). In this paper, we mainly focus to give the review of how to improve the performance of COMP. In the last few years which were developed by different researchers work in this area. Finally, this paper gives some recent COMP performance analysis in terms of Delay, Power consumption (PC), and power delay product (PDP). © 2021, Springer Nature Singapore Pte Ltd.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

An improved tile-based scalable distributed management model of massive high-resolution satellite images 25

An improved tile-based scalable distributed management model...

引用

25th KES International conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES)

作者： Hajjaji, Yosra Boulila, Wadii Farah, Imed Riadh Univ Manouba Natl Sch Comp Sci RIADI Lab Manouba 2010 Tunisia Taibah Univ Coll Comp Sci & Engn IS Dept Medina 42353 Saudi Arabia

The amount of remote sensing (RS) data has increased at an unexpected scale, due to the rapid progress of earth-observation and the growth of satellite RS and sensor technologies. Traditional relational databases attend their limit to meet the needs of high-resolution and large-scale RS Big Data management. As a result, massive RS data management is currently one of the most imperative topics. To address this problem, this paper describes a distributed architecture for big RS data storage based on a unified metadata file, pyramid model, and Hilbert curve for data composition and indexing using NoSQL databases (i.e, Apache Hbase). In this paper, a Hadoop-based framework in AzureInsight cloud platform is designed to manage massive RS data in a parallel and distributed way. Experimental results prove that our method has the potential to overcome the weakness of traditional methods. The proposed model is suitable for massive high-resolution image data management. (C) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of KES International.

关键词： Big data High-resolution remote sensing Satellite images Pyramid model Hilbert curve Standard metadata model Hbase Oracle spatial

来源：评论

学校读者我要写书评

暂无评论

An approach to Detect melanoma skin cancer Using fastai CNN Models

An approach to Detect melanoma skin cancer Using fastai CNN ...

引用

International conference on Computer Communication and Informatics (ICCCI)

作者： Md Shazzad Mia Sumaiya Mustari Mim Mohammad Jahangir Alam Md Razib Mahamudullah Saurabh Bilgaiyan Department of CSE Daffodil International University Dhaka Bangladesh School of Computer Engineering Kalinga Institute of Industrial Technology Bhubaneswar India

Skin cancer, which can be lethal, is essentially the improper proliferation of skin tissues. It has recently developed into one of the most dangerous sorts of additional malignancies in humans. Early detection may help the patient endure. Skin cancer is notoriously difficult to detect. Currently, computer vision performs incredibly well when used to diagnose medical images. Along with technological development and the rapid rise in computer accessibility, several machine learning algorithms and deep learning algorithms have been developed for the interpretation of medical images, especially images of skin lesions. According to our paper, there are five fast-ai CNN pre-trained models with various image pre-processing techniques that enhance the classification capability of skin lesions and make them more precise than other existing models. The HAMIOOOO dataset’s benign and malignant cancer lesions are distinguished by utilizing a number of pre-processing methods. The experimental findings showed that the suggested model improved its accuracy to 97% in both training and testing.

关键词： Training Machine learning algorithms distributed databases Melanoma Skin Lesions Informatics

来源：评论

学校读者我要写书评

暂无评论

distributed Acquisition and processing Network for Experimental Vibration Testing of Aero-Engine Structures 38th

Distributed Acquisition and Processing Network for Experimen...

引用

38th IMAC, A conference and Exposition on Structural Dynamics, 2020

作者： Szydlowski, Michal J. Schwingshackl, Christoph W. Rix, Andrew Imperial College London South Kensington London United Kingdom Rolls-Royce plc 62 Buckingham Gate London United Kingdom

ISBN: (纸本)9783030477127

Detailed vibration testing of large assembled structures, such as aeroengines, leads to significant requirements on data acquisition and processing. This can lead to high system cost and long post processing times, which often limit the amount of data that can be acquired. A novel hardware-software acquisition system combination is proposed here to overcome some of the challenges of large scale data acquisition, based on the idea to distribute the acquisition and data processing load between a network of specialized acquisition nodes. The nodes work in parallel and are independent of each other, while sharing a synchronization clock. Each node has the capability to process the data being acquired on-line. The network allows for testing of novel data analysis methods and its modular nature enables an easy expansion of the system when required. © 2021, The Society for Experimental Mechanics, Inc.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Improved Partitioning Graph Embedding Framework for Small Cluster 14th

Improved Partitioning Graph Embedding Framework for Small Cl...

引用

14th International conference on Knowledge Science, Engineering, and Management (KSEM)

作者： Sun, Ding Huang, Zhen Li, Dongsheng Ye, Xiangyu Wang, Yilin Natl Univ Def Technol Changsha 410073 Hunan Peoples R China Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)9783030821364;9783030821357

Graph embedding is a crucial method to produce node features that can be used for various machine learning tasks. Because of the large number of embedded parameters in large graphs, a single machine cannot load the entire graph into GPUs at once, so a partitioning strategy is required. However, there are some problems with partitioning strategies. Firstly, partitioning introduces data I/O and processing overhead, which increases training time, especially on the cluster with a small number of sites. Secondly, partitioning can affect the performance of the model. For multi-relation graphs, this effect is often negative. To address these problems, we propose the training pipeline and random partitions recombination methods. The training pipeline can reduce the time overhead by masking data loading time to GPU computation, and partitions recombination can effectively improve multi-relation model performance. We conducted experiments on multi-relation graphs and social networks, and the results show that both methods are effective.

关键词： Graph embedding Knowledge graphs Partitioning graph framework GPU distributed graph algorithms

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 << < 132 133 134 135 136 137 138 139 140 141 > >>

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：