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

9,948 篇 会议
273 篇 期刊文献
36 册 图书
2 篇 科技报告

馆藏范围

10,259 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,174 篇 工学
- 5,666 篇 计算机科学与技术...
- 3,591 篇 软件工程
- 1,346 篇 信息与通信工程
- 1,283 篇 电气工程
- 844 篇 控制科学与工程
- 823 篇 电子科学与技术（可...
- 464 篇 机械工程
- 462 篇 生物工程
- 384 篇 光学工程
- 370 篇 动力工程及工程热...
- 364 篇 生物医学工程（可授...
- 289 篇 仪器科学与技术
- 261 篇 化学工程与技术
- 234 篇 交通运输工程
- 229 篇 网络空间安全
- 201 篇 材料科学与工程（可...
- 184 篇 土木工程
- 183 篇 安全科学与工程
- 182 篇 航空宇航科学与技...
2,734 篇 理学
- 1,390 篇 数学
- 865 篇 物理学
- 503 篇 生物学
- 352 篇 统计学（可授理学、...
- 344 篇 化学
- 240 篇 系统科学
1,329 篇 管理学
- 817 篇 管理科学与工程(可...
- 627 篇 图书情报与档案管...
- 364 篇 工商管理
445 篇 医学
- 346 篇 临床医学
- 192 篇 基础医学(可授医学...
183 篇 教育学
141 篇 法学
124 篇 经济学
47 篇 农学
41 篇 军事学
31 篇 文学
10 篇 艺术学
1 篇 哲学
1 篇 历史学

主题

1,025 篇 program processo...
727 篇 computer archite...
419 篇 computational mo...
384 篇 hardware
343 篇 high performance...
260 篇 parallel process...
238 篇 computer science
192 篇 optimization
171 篇 benchmark testin...
164 篇 concurrent compu...
163 篇 application soft...
159 篇 runtime
156 篇 computer vision
148 篇 bandwidth
129 篇 registers
128 篇 libraries
127 篇 deep learning
122 篇 parallel program...
120 篇 scalability
120 篇 throughput

机构

69 篇 college of compu...
56 篇 school of comput...
54 篇 university of ch...
42 篇 school of comput...
33 篇 department of co...
31 篇 univ chinese aca...
30 篇 school of comput...
30 篇 tsinghua univers...
30 篇 college of compu...
27 篇 school of comput...
25 篇 school of data a...
23 篇 college of compu...
23 篇 high energy astr...
22 篇 computer network...
22 篇 graduate school ...
21 篇 graduate school ...
20 篇 center for astro...
20 篇 department of ph...
20 篇 department of ph...
20 篇 the graduate sch...

作者

25 篇 tokuno h.
24 篇 ikeda d.
23 篇 belz j.w.
22 篇 jui c.c.h.
22 篇 oshima a.
22 篇 tsuda r.
22 篇 kim j.h.
22 篇 bergman d.r.
22 篇 allen m.
22 篇 matsuyama t.
22 篇 wong t.
22 篇 ishii t.
22 篇 kim s.w.
22 篇 takamura m.
22 篇 yashiro k.
22 篇 kadota k.
22 篇 mayta r.
22 篇 ozawa s.
22 篇 kasami s.
22 篇 rodriguez d.c.

语言

10,022 篇 英文
196 篇 其他
50 篇 中文
3 篇 西班牙文
2 篇 土耳其文
1 篇 葡萄牙文

检索条件"任意字段=Conference on High Performance Computer Modernization Program"

共 10259 条记录，以下是201-210 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：

Implementation and performance Evaluation of Collective Communications Using CIRCUS on Multiple FPGAs

Implementation and Performance Evaluation of Collective Comm...

引用

2023 International conference on high performance Computing in Asia-Pacific Region Workshops, HPC Asia 2023

作者： Kikuchi, Kohei Fujita, Norihisa Kobayashi, Ryohei Boku, Taisuke Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Japan Center for Computational Sciences University of Tsukuba Tsukuba Japan

ISBN: (纸本)9781450399890

In the high-performance computing domain, Field programmable Gate Array (FPGA) is a novel accelerator that exhibits high flexibility and performance characteristics distinct from other accelerators such as the Graphics Processing Unit (GPU). Recent advanced high-end FPGA is equipped with multiple channels of high speed optical link up to 100Gbps performance for each. This is a crucial feature when we construct PC clusters with FPGAs as accelerators, however it is not easy to utilize from user kernels because this feature is implemented in low level and simple direct communication between neighboring FPGAs. In order to provide the communication feature between FPGAs for accelerated PC clusters, we developed a communication system named CIRCUS which implies a user-friendly API from OpenCL and is equipped with routing function over multi-hop communication on multi-dimensional torus network of FPGAs. However, current CIRCUS only provides a point-to-point communication between source and destination FPGAs. In ordinary parallel processing environment such as MPI, the user program the message passing with various collective communication functions for parallel algorithm, for instance Allreduce, Allgather, etc. In this paper, we implement the collective communication function over CIRCUS for user-friendly programming of ordinary parallel algorithms on FPGAs. As the first target, we implement Allreduce function which is the most essential and important function. The paper describes the CIRCUS system briefly followed by the design, implementation and preliminary performance evaluation on Intel Stratix10 FPGAs. © 2023 ACM.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Multi-class Motor Imagery Classification in Brain computer Interface (BCI) 2

Multi-class Motor Imagery Classification in Brain Computer I...

引用

2nd International conference on Electrical Engineering and Automatic Control (ICEEAC)

作者： Azzougui, Safia Reffad, Aicha Mebarkia, Kamel Setif 1 Univ Fac Technol Dept Electrotech LAS Lab Setif Algeria Setif 1 Univ Fac Technol Dept Elect LIS Lab Setif Algeria

ISBN: (纸本)9798350349740;9798350349757

A Brain-computer Interface (BCI) represents an innovative system created to allow a communication between the human brain and a device in order to enhance the lives of disabled individuals. BCI systems decode user intentions using brain signals, detected through electroencephalography (EEG). The use of BCI with EEG gained popularity due to its non-invasiveness, high portability, and modest cost. The objective of this work is to classify different types of mental tasks involving motor imagery, such as imagining left hand, right hand, foot, and tongue movements, performed by three subjects. To achieve this, we utilized common spatial pattern (CSP) method for multiclass feature extraction. Furthermore, we compared the performance of three classifiers: k-nearest neighbors (KNN), linear discriminant analysis (LDA), and support vector machine (SVM), based on brain activity during motor imagery using the III-a dataset from BCI competition III. The final classification results revealed a notable achievement, with the highest accuracy reaching 77.03%.

关键词： Brain computer interface (BCI) Electroencephalogram (EEG) Motor imagery Common Spatial Pattern (CSP) KNN LDA SVM classification

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation with Adaptive Category Temperatures for Classifying high-Similar Objects 21

Knowledge Distillation with Adaptive Category Temperatures f...

引用

21st International computer conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Wang, Heng Zhang, Yu Hu, Wang Lin, Kezhen Hu, Junjie School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China College of Computer Science Sichuan University Chengdu611731 China

ISBN: (纸本)9798331519254

Grayscale images play a crucial role in X-ray-based welding flaw identification, where variations among different types of flaws primarily arise from disparities in shape and intensity. Consequently, different flaw types often exhibit considerable similarity in their feature descriptions. To tackle this challenge, we propose an enhanced method termed Knowledge Distillation with Adaptive Category Temperatures (KD-ACT) to effectively classify objects with high similarity. To extract implicit information inherent in objects, KD-ACT incorporates an adaptive category temperatures adjustment mechanism, which is guided by feedback from the validation dataset. The proposed method dynamically adjusts the critical temperature parameters of the distillation process, assigning an independent temperature to each category to maximize flexibility in temperature variations. This tailored temperature adjustment enables the welding flaw model to acquire rich information inherent in different flaw types, thereby enhancing its overall performance. Compared to traditional knowledge distillation algorithms, KD-ACT has achieved a maximum improvement of about 4%, with an average improvement of approximately 2 %. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Method for Small Target Detection in high Resolution Optical Satellite Images 3

A Method for Small Target Detection in High Resolution Optic...

引用

3rd International conference on Electronic Information Engineering and computer Science, EIECS 2023

作者： Chen, Can Hubei University of Technology School of Computer Science Wuhan China

ISBN: (纸本)9798350316674

In recent years, target detection has been widely used in many fields such as military reconnaissance, environmental monitoring and disaster assessment, and its importance has become increasingly prominent. However, although there are many excellent target detection methods, there are still many problems and challenges in small target detection, such as small target size and low signal-to-noise ratio. In this paper, the image preprocessing method is studied, and the image quality is improved by radiation correction, geometric correction and image enhancement, which provides basic data guarantee for the subsequent small target detection tasks. In this study, the YOLOv5 model is selected to improve the detection performance of small targets by capturing high-resolution features in the shallow network and semantic information in the deep network, as well as the anchor frame design considering different sizes and aspect ratios. The comparative experimental results of three models on the dataset show that YOLOv5 model is the best for small target detection. © 2023 IEEE.

关键词： deep learning high resolution optical image small object detection

来源：评论

学校读者我要写书评

暂无评论

Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift 23

Reducing Annotation Effort by Identifying and Labeling Conte...

引用

23rd IEEE/CVF Winter conference on Applications of computer Vision (WACV)

作者： Agarwal, Sharat Anand, Saket Arora, Chetan IIIT Delhi Delhi India

ISBN: (纸本)9781665493468

In Active Domain Adaptation (ADA), one uses Active Learning (AL) to select a subset of images from the target domain, which are then annotated and used for supervised domain adaptation (DA). Given the large performance gap between supervised and unsupervised DA techniques, ADA allows for an excellent trade-off between annotation cost and performance. Prior art makes use of measures of uncertainty or disagreement of models to identify 'regions' to be annotated by the human oracle. However, these regions frequently comprise of pixels at object boundaries which are hard and tedious to annotate. Hence, even if the fraction of image pixels annotated reduces, the overall annotation time and the resulting cost still remain high. In this work, we propose an ADA strategy, which given a frame, identifies a set of classes that are hardest for the model to predict accurately, thereby recommending semantically meaningful regions to be annotated in a selected frame. We show that these set of 'hard' classes are context-dependent and typically vary across frames, and when annotated help the model generalize better. We propose two ADA techniques: the Anchor-based and Augmentation-based approaches to select complementary and diverse regions in the context of the current training set. Our approach achieves 66.6 mIoU on *** dataset with an annotation budget of 4.7% in comparison to 64.9 mIoU by MADA [22] using 5% of annotations. Our technique can also be used as a decorator for any existing frame-based AL technique, e.g., we report 1.5% performance improvement for CDAL [1] on Cityscapes using our approach.

关键词： Training computer vision Costs Uncertainty Annotations Semantic segmentation Measurement uncertainty

来源：评论

学校读者我要写书评

暂无评论

Attacker Detection Based on Multi-Level Tenant Classification 21

Attacker Detection Based on Multi-Level Tenant Classificatio...

引用

21st International computer conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Qimin, Jing Shaoming, Wang Yanping, Xiang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798331519254

Co-resident attacks in the cloud environment have always been a concern. Different from other network attacks, it is a cache-based side-channel attack. Many studies have shown that it can be co-located with the target user on a server, and then analyze some cached data to steal or tamper with user data, thereby launching an attack. Therefore, how to detect and judge malicious users is an urgent issue. Researchers have proposed a variety of detection and defense methods. This paper proposes a detection model to detect and classify malicious users according to abnormal hardware events. The Deep Belief Network (DBN) is responsible for extracting features, while the Support Vector Machine (SVM) handles the classification. Extracting features improves classification efficiency while maintaining high accuracy. According to the experimental results, the proposed method can classify malicious users, and the accuracy rate reaches 99.49 % and the classification speed demonstrates performance that is on par with existing methods. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

UNet-AFF: U-Net based on attention feature fusion for COVID-19 focus segmentation 7

UNet-AFF: U-Net based on attention feature fusion for COVID-...

引用

7th International conference on computer Information Science and Application Technology, CISAT 2024

作者： Ye, Xi Yang, Zhihong Zhang, Zhiwei Zhang, Quanxin Institute of Intelligent Manufacturing Jianghan University Wuhan China Institute of Computer Science and Technology Wuhan University of Bioengineering Wuhan China

ISBN: (纸本)9798350375107

In response to the limitations of conventional U-Net in fusing high- and low-level features in automatic segmentation of neocoronal pneumonia foci, this paper proposes an attention feature fusion-based segmentation model for U-Net pneumonia foci. The model incorporates an attention feature fusion module in the decoding stage of the network for the purpose of integrating high- and low-level features. The attention feature fusion module is designed to focus on and emphasise the effective expression of features when they are fused through the attention mechanism. This helps the network to integrate the semantic information and spatial details of features at different layers, thereby improving the accuracy of the network's decoding. Finally, this paper presents experimental results on the COVID19 CT lung infection segmentation dataset with new crown pneumonia foci. The results demonstrate that the improved segmentation model in this paper can effectively improve the segmentation performance for new crown pneumonia foci. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

FISCO-BCOS: An Enterprise-grade Permissioned Blockchain System with high-performance 23

FISCO-BCOS: An Enterprise-grade Permissioned Blockchain Syst...

引用

2023 International conference for high performance Computing, Networking, Storage and Analysis, SC 2023

作者： Li, Huizhong Chen, Yujie Shi, Xiang Bai, Xingqiang Mo, Nan Li, Wenlin Guo, Rui Wang, Zhang Sun, Yi WeBank Shenzhen China Beijing China

ISBN: (纸本)9798400701092

Enterprise-grade permissioned blockchain systems provide a promising infrastructure for data sharing and cooperation between different companies. However, performance bottlenecks seriously hinder the adoption of these systems in many industrial applications that process complex business logic and huge transaction volumes. Our research identifies two key factors that limit the system performance: 1) At the block level, the serial dependency of inter-block processing severely limits the system throughput. A new block must wait for the completion of all previous blocks. 2) At the transaction level, the lack of efficient intra-block transactions concurrency makes it difficult to achieve high performance, especially when dealing with multiple CPU-heavy contracts which are commonly used in industrial *** this paper, we present FISCO-BCOS, an enterprise-grade permissioned blockchain system with high performance. To overcome serial limitations and fully utilize machine resources, FISCO-BCOS introduces Block Level Pipelining (BLP) workflow to process blocks in a pipeline manner. In addition, a scheduling algorithm Deterministic Multi-Contract (DMC) is designed to efficiently execute transactions in parallel. Under BLP and DMC, FISCO-BCOS achieves inter-block and intra-block paralleling to meet high-performance requirements in industrial application scenarios. We conducted experiments on two popular test workloads and compared FISCO-BCOS with state-of-the-art platforms in academia and industry such as BIDL and Hyperledger Fabric (HLF). The result shows that FISCO-BCOS achieves 7.4 times and 28.4 times the throughput of BIDL and HLF, respectively, with half the latency of them. BCOS has already been used in over 300 different large-scale industrial scenarios and has become one of the most popular permissioned blockchains. © 2023 Owner/Author(s).

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

DistTGL: Distributed Memory-Based Temporal Graph Neural Network Training 23

DistTGL: Distributed Memory-Based Temporal Graph Neural Netw...

引用

2023 International conference for high performance Computing, Networking, Storage and Analysis, SC 2023

作者： Zhou, Hongkuan Zheng, Da Song, Xiang Karypis, George Prasanna, Viktor University of Southern California Los Angeles United States AWS AI Santa Clara United States

ISBN: (纸本)9798400701092

Memory-based Temporal Graph Neural Networks are powerful tools in dynamic graph representation learning and have demonstrated superior performance in many real-world applications. However, their node memory favors smaller batch sizes to capture more dependencies in graph events and needs to be maintained synchronously across all trainers. As a result, existing frameworks suffer from accuracy loss when scaling to multiple GPUs. Even worse, the tremendous overhead of synchronizing the node memory makes it impractical to deploy the solution in GPU clusters. In this work, we propose DistTGL - - an efficient and scalable solution to train memory-based TGNNs on distributed GPU clusters. DistTGL has three improvements over existing solutions: an enhanced TGNN model, a novel training algorithm, and an optimized system. In experiments, DistTGL achieves near-linear convergence speedup, outperforming the state-of-the-art single-machine method by 14.5% in accuracy and 10.17× in training throughput. © 2023 Owner/Author(s).

关键词： program processors

来源：评论

学校读者我要写书评

暂无评论

5 ExaFlop/s HPL-MxP Benchmark with Linear Scalability on the 40-Million-Core Sunway Supercomputer 23

5 ExaFlop/s HPL-MxP Benchmark with Linear Scalability on the...

引用

2023 International conference for high performance Computing, Networking, Storage and Analysis, SC 2023

作者： Lin, Rongfen Yuan, Xinhui Xue, Wei Yin, Wanwang Yao, Jienan Shi, Junda Sun, Qiang Song, Chaobo Wang, Fei National Research Center of Parallel Computer Engineering & Technology Beijing China Tsinghua University BNRist Beijing China Qinghai University Xining China Tsinghua University Beijing China

ISBN: (纸本)9798400701092

HPL-MxP is an emerging high performance benchmark used to measure the mixed-precision computing capability of leading supercomputers. In this work, we present our efforts on the new Sunway that linearly scales the benchmark to over 40 million cores, sustains an overall mixed-precision performance exceeding 5 ExaFlop/s, and achieves over 85% of peak performance, which is the highest efficiency reached among all heterogeneous systems on the HPL-MxP list. The optimizations of our HPL-MxP implementation include the following: (1) a Two-Direction Look-Ahead and Overlap algorithm that enables overlaps of all communications with computation;(2) a multi-level process-mapping and communication scheduling method that uses the entire network as best as possible while maintaining conflict-free algorithm-flow;and (3) a CG-Fusion computing framework that eliminates up to 60% of inter-chip communications and removes the memory access bottleneck while serving both computation and communication simultaneously. This work could also provide useful insights for tuning cutting-edge applications on Sunway supercomputers as well as other heterogeneous supercomputers. © 2023 Owner/Author(s).

关键词： Linear algebra

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 << < 17 18 19 20 21 22 23 24 25 26 > >>

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：