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1141-1150 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：

DL Based System for On-Board image Classification in Real Time, Applied to Disaster Mitigation

DL Based System for On-Board Image Classification in Real Ti...

引用

International conference on parallel distributed and Grid Computing (PDGC)

作者： Amogh Shukla Shubh Almal Ankur Gupta Rinisha Jain Rishabh Mishra Dharmesh Dhabliya School of CSE Vellore Institute of Technology Vellore TL India Department of CSE Vaish College of Engineering Rohtak Haryana India Vishwakarma Institute of Information Technology Pune Maharashtra India

ISBN: (纸本)9781665454025

Natural phenomena such as earthquakes that cause the destruction of bridges and can cause tsunamis, among other phenomena and disasters, are on the rise as a result of climate change, which is affecting our planet. This is because of the rise in average global temperature and the development of extreme rains, which causes rivers to overflow. The use of satellites for terrestrial observation has made it possible to keep tabs on events throughout the world in recent years. However, these satellite systems aren't without their drawbacks; one is that cloud cover may make it difficult to accurately record photographs. It is done based on the clouds present, and another drawback is the visiting time that the satellites have, which means that the area that you want to record the image is not always available, so you have to wait for the day and the time in which the satellite orbit can pass through the area of interest that the image is to be recorded. Drones, which fly at low altitudes and do not have cloud problems, are one such alternative, solving a problem of satellites, on cloud cover. In light of this, in the present work, a methodology based on low-cost systems is proposed for on-board processing in drones of such data in the event of an emergency, such as after the effects of rain or an earthquake. Methodology involves processing the image in an embedded device, which is coupled to the drone and connected to the camera, in such a way that the information that is sent to the ground station, concentrates on the affected area; this allows for faster decision-making and lessens the impact of the natural disaster. Therefore, it is shown by testing of the embedded computer based on a Raspberry pi 3 for detecting changes in land cover and transmitting this information to an earth station.

关键词： Training Satellites Rain Clouds Computational modeling Simulation Earthquakes

来源：评论

学校读者我要写书评

暂无评论

A Priority-Driven Deep Reinforcement Learning Scheduler for Resource Management

A Priority-Driven Deep Reinforcement Learning Scheduler for ...

引用

Collaborative Advances in Software and COmputiNg (CASCON), International conference on

作者： Hajer Ayadi Aijun An Yiming Shao Junjie Deng Jimmy X. Huang Michael Feiman Hao Zhou York university Toronto ON Canada IBM Spectrum Computing Toronto ON Canada

ISBN: (数字)9798331504830

ISBN: (纸本)9798331515621

Deep neural networks (DNNs) have gained popularity in various fields, including computer vision and speech recognition. However, the growing size of data and complexity of models have made training DNNs increasingly time-consuming. To accelerate computation, parallel and distributed training of DNNs using multiple GPUs is widely adopted. This approach, however, introduces significant challenges in managing and scheduling GPU resources. One critical challenge is job prioritization, which ensures that urgent jobs are processed promptly. Current solutions often overlook prioritization settings, leading to suboptimal performance. For example, neglecting prioritization can result in long delays for urgent jobs. Conversely, overly prioritizing urgent jobs without balancing the needs of other jobs can lead to extended completion times (JCT) for less urgent tasks. While existing approaches that incorporate prioritization typically rely on heuristic-based methods, which may not be optimal, deep reinforcement learning (DRL)-based methods offer greater adaptability and can generally outperform traditional heuristic-based approaches. To address these challenges, we introduce Prioritize, a novel GPU job scheduler designed to enhance GPU resource management in distributed DNN training. Prioritize employs a DRL model to efficiently select jobs based on their priority. To minimize the JCT for lower-priority jobs, Prioritize dynamically increases their priority over time, thereby reducing their queueing delays. The DRL model maximizes a priority-based reward to ensure effective job selection. Extensive experiments demonstrate that Prioritize outperforms several baseline methods in terms of queueing time, JCT, and Makespan. The proposed approach not only achieves superior scheduling performance but also effectively addresses prioritization challenges, making Prioritize a promising solution for efficient GPU job scheduling in distributed DNN training scenarios.

关键词： Training Computational modeling Graphics processing units Artificial neural networks Speech recognition Deep reinforcement learning Throughput Software Delays Resource management

来源：评论

学校读者我要写书评

暂无评论

Enhancing MPI Communication Efficiency for Grid-Based Stencil Computations

Enhancing MPI Communication Efficiency for Grid-Based Stenci...

引用

Computing, Semiconductor, Mechatronics, Intelligent Systems and Communications (COSMIC), International conference on

作者： Santosh Iranagouda Goudar Premkumar SJ Nayaka K K Girish Biswajit Bhowmik Department of Computer Science and Engineering Maharshi Sushrut CAS Lab BRICS Lab National Institute of Technology Karnataka Surathkal Mangalore Bharat

ISBN: (数字)9798331517892

ISBN: (纸本)9798331517908

In parallel computing, where efficiency and speed are crucial, the Message Passing Interface (MPI) is a fundamental paradigm for managing large-scale distributed memory systems. MPI is critical to complex computational tasks, particularly in grid-based computations that solve intricate numerical problems by discretizing spatial domains into structured grids. However, MPI Cartesian communicators exhibit limitations in handling these computations effectively, especially when managing large-scale data exchanges and complex stencil patterns. This paper addresses these challenges by presenting an integrated approach that combines MPI collective and Cartesian communication methods. The proposed solution simplifies data distribution, eliminates redundant interfaces, and enhances communication efficiency. Experimental results show a 43% reduction in execution time and a 40% decrease in communication overhead, with scalability improvements achieving 12.5x speedup using 64 processes. These quantitative outcomes demonstrate the advan-tages of the proposed method over conventional MPI Cartesian approaches, establishing it as a reliable framework for advancing High-Performance Computing (HPC) capabilities in grid-based applications.

关键词： Mechatronics Scalability Message passing Memory management Reinforcement learning parallel processing Real-time systems Computational efficiency Reliability Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Communication Efficient SGD via Gradient Sampling with Bayes Prior

Communication Efficient SGD via Gradient Sampling with Bayes...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Song, Liuyihan Zhao, Kang Pan, Pan Liu, Yu Zhang, Yingya Xu, Yinghui Jin, Rong Alibaba Grp Machine Intelligence Technol Lab Beijing Peoples R China

ISBN: (纸本)9781665445092

Gradient compression has been widely adopted in data-parallel distributed training of deep neural networks to reduce communication overhead. Some literatures have demonstrated that large gradients are more important than small ones because they contain more information, such as Top-k compressor. Other mainstream methods, like random-k compressor and gradient quantization, usually treat all gradients equally. Different from all of them, we regard large and small gradients selection as the exploitation and exploration of gradient information, respectively. And we find taking both of them into consideration is the key to boost the final accuracy. So, we propose a novel gradient compressor: Gradient Sampling with Bayes Prior in this paper. Specifically, we sample important/large gradients based on the global gradient distribution, which is periodically updated across multiple workers. Then we introduce Bayes Prior into distribution model to further explore the gradients. We prove the convergence of our method for smooth non-convex problems in the distributed system. Compared with methods that running after high compression ratio at the expense of accuracy, we pursue no loss of accuracy and the actual acceleration benefit in practice. Experimental comparisons on a variety of computer vision tasks (e.g. image classification and object detection) and backbones (ResNet, MobileNetV2, InceptionV3 and AlexNet) show that our approach outperforms the state-of-the-art techniques in terms of both speed and accuracy, with the limitation of 100x compression ratio.

关键词： Training Degradation Computer vision image coding Quantization (signal) Object detection Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Cloud-Enhanced Transfer Learning Framework for Medical image Analysis: Advancing Diagnostic Speed and Accuracy in Healthcare 3

Cloud-Enhanced Transfer Learning Framework for Medical Image...

引用

3rd International conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Prabu, S. Chandra, N. Subhash Bhavani, M. Varma, V. K. Chaitanya Soni, Mukesh Mahendra Institute of Technology Department of Electronics and Communication Engineering Namakkal India Cvr College of Engineering Department of Computer Science and Engineering Mangalpalle India Rajalakshmi Institute of Technology Department of Artificial Intelligence and Data Science Chennai India Sagi Rama Krishnam Raju Engineering College Department of Mechanical Engineering Bhimavaram India Dr. D. Y. Patil Vidyapeeth Dr. D. Y. Patil School of Science & Technology Pune India

ISBN: (纸本)9798331508456

When it comes to medical image analysis, problems arise due to the scarce amount of data and computational resources in medical environments. This is because, as earlier stated, cloud settings demand efficient models capable of delivering more reliable diagnostic results without straining the cloud's computing resources. In this work, we presented a transfer learning based on DenseNet-201 as well ResNet-152 architectures with a new large dataset containing 15,000 medical images of different modality. By utilizing the distributed cloud computing and hypermeters precision strategy, the proposed model was found to have 95.8 % of accuracy, 94.2% sensitivity, and 96.3%specificity. It also reduced the processing time by sixty-eight percent over standard methods across the facilities. Five different datasets validated the proposed approach, achieving an external accuracy of 92.4%, indicating improved generalization performance. The enhancement of accuracy to approximately 90% and the reduction in required computation demonstrate its feasibility for extensive clinical applications on the cloud, spanning across hospitals. © 2025 IEEE.

关键词： distributed cloud

来源：评论

学校读者我要写书评

暂无评论

Towards Real-world Deployment of Deep Learning Solutions for Global Road Damage Detection and Classification

Towards Real-world Deployment of Deep Learning Solutions for...

引用

IEEE International conference on Big Data

作者： Jooyoung Yoo Reem Emad Shtaiwi Mohammad Yasin Dweep Trivedi Abdullah Alfarrarjeh Amani Abu Jabal Seon Ho Kim Integrated Media Systems Center University of Southern California Los Angeles California USA Department of Computer Science German Jordanian University Amman Jordan

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Effective monitoring of essential road infrastructure is critical to ensure economic growth and community connectivity, as deterioration from climate change and intensive use can compromise safety and hamper emergency services. To address these critical issues, we propose optimized approaches for road damage detection using YOLOv5, YOLOv8, and YOLOv10 models, with fine-tuning and hyperparameter optimization to improve detection accuracy. Our approaches achieve good overall accuracy (in terms of F1-score) by combining models of different sizes and frameworks using ensemble methods. Moreover, to enhance the speed of inference, parallel processing techniques are used. In order to obtain fast detection performance, small models, such as YOLOv5-small and YOLOv8-nano were given priority in modeling to balance between detection accuracy and inference speed. In the context of the 2024 IEEE BigData Optimized Road Damage Detection Challenge (ORDDC’2024), our approach achieved an F1 score greater than 0.7 with an inference speed of 0.0432 seconds per image, meeting the ORDDC’s accuracy and inference speed goal.

关键词： YOLO Economics Accuracy Roads Biological system modeling Transfer learning parallel processing Stability analysis Ensemble learning Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Cluster-based parallel Doppler Search Algorithm for Deep Space Exploration Applications 2

A Cluster-based Parallel Doppler Search Algorithm for Deep S...

引用

2nd International conference on Networking Systems of AI, INSAI 2022

作者： Yu, Yun Guo, Quan Shanghai Astronomical Observatory Chinese Academy of Sciences Shanghai China

ISBN: (纸本)9781665491785

The orbit predictions are subject to considerable errors due to the orbital maneuvers and systematic errors of the deep space probes. The detector signals are Doppler-shifted, so the correlated data cannot be integrated for a long time to achieve a higher signal-to-noise ratio. In addition, the computation of correlation increases with the increase of ground tracking stations, space detectors, and correlation channels. In this paper, we propose a cluster based Doppler search technique. First, a priory model is used to run fringe rotation and phase compensation relative to the center of the Earth. Second, a phase structure approach is applied to solve the Doppler frequency problem with high accuracy. Finally, a least square method is used to generate a polynomial model as the input to the correlation model. Due to the multi-channel signal and many grounds receiving stations, the data calculation can be enriched with Doppler search methods at the theoretical level and specific parallel algorithm design solutions at the application level. Through the analysis of the algorithms;the search speed can be improved by using cluster-distributed computing. The results of this study can help to improve the determination of deep space probe orbit capability by differential VLBI technology for application in deep space exploration in China. © 2022 IEEE.

关键词： Orbits

来源：评论

学校读者我要写书评

暂无评论

Enhancing Movie Recommendation Systems with MapReduce Genetic Algorithms: Addressing Scalability and Accuracy Challenges

Enhancing Movie Recommendation Systems with MapReduce Geneti...

引用

Smart Electronics and Communication Systems (ISENSE), International conference on

作者： Priyansh Patidar Sathwik Venkata Posa Girish K K Shaifali Rao Biswajit Bhowmik Department of Computer Science and Engineering Ishwarchandra Vidyasagar AIT Lab BRICS Lab National Institute of Technology Karnataka Mangalore Bharat

ISBN: (数字)9798331528126

ISBN: (纸本)9798331528133

In the world of big data, the efficacy of movie recommendation systems is crucial for personalizing user experiences in digital entertainment. Traditional methods, including collaborative and content-based filtering, often encounter limitations such as data sparsity, cold start problems, and scalability issues. This paper introduces a novel approach that integrates MapReduce technology with Genetic Algorithms (GAs) to address these chal-lenges. Utilizing the Hadoop framework, our MapReduce Genetic Algorithm (MRGA) efficiently processes extensive datasets by distributing tasks across a cluster of machines. The genetic algorithm component optimizes recommendation accuracy through advanced techniques like selection, crossover, and mutation. Our experimental results, based on the MovieLens 100K dataset, demonstrate that the MRGA approach outperforms traditional collaborative filtering methods in terms of recommendation accuracy and scalability. By leveraging MapReduce's distributed computing power and the GA's optimization capabilities, this research offers a robust solution to improve movie recommendations and handle large-scale data efficiently.

关键词： Accuracy Filtering Scalability Collaborative filtering Entertainment industry parallel processing Motion pictures Recommender systems Optimization Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Rapid face image retrieval for large scale based on spark and machine learning 2

Rapid face image retrieval for large scale based on spark an...

引用

2021 2nd International conference on Computer Science and Communication Technology, ICCSCT 2021

作者： Zeng, Yuting Li, Yujin Hu, Qiming Tang, Yuan School of Information Science and Technology Chengdu University of Technology Chengdu610059 China

This paper proposed a distributed computing environment large-scale face image retrieval method. Based on Spark platform, a face retrieval method based on machine learning is established, which takes advantage of parallel computing to improve the efficiency of face image retrieval. In the method, SIFT algorithm is used for feature coding, PCA dimension reduction processing, HBase database is used for data storage, and KD-Tree query algorithm is used to match images similar to the query images. Meanwhile, large-scale computing engine uses Spark to process data to improve the retrieval efficiency. The CelebA dataset is selected to test the method, and the experimental results show the effectiveness of the method. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

FedMIL: Federated-Multiple Instance Learning for Video Analysis with Optimized DPP Scheduling

FedMIL: Federated-Multiple Instance Learning for Video Analy...

引用

International conference on distributed Computing in Sensor Systems (DCOSS)

作者： Ashish Bastola Hao Wang Xiwen Chen Abolfazl Razi School of Computing Clemson University Clemson USA

ISBN: (数字)9798350369441

ISBN: (纸本)9798350369458

Many AI platforms, including traffic monitoring systems, use Federated Learning (FL) for decentralized sensor data processing for learning-based applications while preserving privacy and ensuring secured information transfer. On the other hand, applying supervised learning to large data samples, like high-resolution images requires intensive human labor to label different parts of a data sample. Multiple Instance Learning (MIL) alleviates this challenge by operating over labels assigned to the ’bag’ of instances. In this paper, we introduce Federated Multiple-Instance Learning (FedMIL). This framework applies federated learning to boost the training performance in video-based MIL tasks such as vehicle accident detection using distributed CCTV networks. However, data sources in decentralized settings are not typically Independently and Identically distributed (IID), making client selection imperative to collectively represent the entire dataset with minimal clients. To address this challenge, we propose DPPQ, a framework based on the Determinantal Point Process (DPP) with a quality-based kernel to select clients with the most diverse datasets that achieve better performance compared to both random selection and current DPP-based client selection methods even with less data utilization in the majority of non-IID cases. This offers a significant advantage for deployment on edge devices with limited computational resources, providing a reliable solution for training AI models in massive smart sensor networks. 1

关键词： Training Performance evaluation Data privacy Federated learning Computational modeling image edge detection Data models

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 << < 111 112 113 114 115 116 117 118 119 120 > >>

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：