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

4,329 篇 会议
70 篇 期刊文献
16 册 图书

馆藏范围

4,415 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,474 篇 工学
- 2,297 篇 计算机科学与技术...
- 1,049 篇 软件工程
- 490 篇 电气工程
- 425 篇 信息与通信工程
- 187 篇 电子科学与技术（可...
- 118 篇 控制科学与工程
- 102 篇 网络空间安全
- 88 篇 动力工程及工程热...
- 73 篇 生物工程
- 48 篇 机械工程
- 46 篇 生物医学工程（可授...
- 41 篇 光学工程
- 34 篇 建筑学
- 30 篇 材料科学与工程（可...
- 22 篇 仪器科学与技术
- 22 篇 土木工程
- 22 篇 化学工程与技术
597 篇 理学
- 422 篇 数学
- 96 篇 物理学
- 83 篇 生物学
- 66 篇 系统科学
- 61 篇 统计学（可授理学、...
- 23 篇 化学
333 篇 管理学
- 248 篇 管理科学与工程(可...
- 136 篇 工商管理
- 99 篇 图书情报与档案管...
60 篇 医学
- 45 篇 临床医学
- 38 篇 基础医学(可授医学...
40 篇 经济学
- 40 篇 应用经济学
38 篇 法学
- 33 篇 社会学
11 篇 教育学
11 篇 农学
6 篇 文学
1 篇 艺术学

主题

1,181 篇 computer archite...
446 篇 hardware
378 篇 high performance...
287 篇 concurrent compu...
276 篇 computational mo...
237 篇 application soft...
229 篇 parallel process...
217 篇 computer science
213 篇 distributed comp...
187 篇 costs
186 篇 bandwidth
179 篇 field programmab...
173 篇 delay
164 篇 throughput
161 篇 cloud computing
157 篇 grid computing
140 篇 computer network...
137 篇 resource managem...
133 篇 laboratories
122 篇 scalability

机构

16 篇 university of ch...
12 篇 school of comput...
12 篇 institute of com...
8 篇 department of co...
8 篇 georgia inst tec...
8 篇 univ chicago dep...
8 篇 barcelona superc...
8 篇 school of comput...
8 篇 carnegie mellon ...
8 篇 mathematics and ...
8 篇 intel corporatio...
7 篇 department of el...
7 篇 college of compu...
7 篇 univ illinois ur...
7 篇 computer systems...
7 篇 department of co...
7 篇 mathematics and ...
7 篇 intel corp santa...
7 篇 univ fed rio gra...
6 篇 univ toronto on

作者

13 篇 navaux philippe ...
11 篇 d.k. panda
9 篇 viktor k. prasan...
9 篇 prasanna viktor ...
9 篇 mutlu onur
9 篇 i. foster
8 篇 dhabaleswar k. p...
8 篇 dongarra jack
8 篇 guedes dorgival
7 篇 borin edson
7 篇 cristal adrian
7 篇 chong frederic t...
7 篇 loh gabriel h.
7 篇 kim nam sung
7 篇 zhou huiyang
7 篇 panda dhabaleswa...
7 篇 magoules frederi...
7 篇 ferreira renato
7 篇 xiaowei li
7 篇 buyya rajkumar

语言

4,396 篇 英文
10 篇 其他
10 篇 中文
2 篇 葡萄牙文
1 篇 法文

检索条件"任意字段=16th Symposium on Computer Architecture and High Performance Computing"

共 4415 条记录，以下是4371-4380 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：

Automatic Sleep-Wake Scoring with Optimally Selected EEG Channels from high-Density EEG 16th

Automatic Sleep-Wake Scoring with Optimally Selected EEG Ch...

引用

16th International Conference on Brain Informatics, BI 2023

作者： Herleiksplass, Karoline Seljevoll Moctezuma, Luis Alfredo Furuki, Junya Suzuki, Yoko Abe, Takashi Molinas, Marta Department of Engineering Cybernetics Norwegian University of Science and Technology Trondheim Norway University of Tsukuba Ibaraki Tsukuba Japan

ISBN: (纸本)9783031430749

this paper presents a sleep versus wake-classification model based on high-density electroencephalographic (EEG) sleep data. In a second stage, an optimization algorithm is applied to select the minimal set of EEG channels according to their contribution to classification performance. the performance of these subsets are compared to the ones recommended by the American Academy of Sleep Medicine (AASM) and with the 128 available channels in the tested dataset. We focus on accurate classification of the wake stage because of its importance as a metric of sleep quality and in diagnosing several sleep disorders. the performed experiment demonstrates that high-density EEG channels can achieve an accuracy and kappa score of 0.970 and 0.778 using the proposed method and dataset. But most importantly, the results from the optimization algorithm, Non-dominated Sorting Genetic Algorithm (NSGA)-III, indicate that using 3 to 9 channels can yield an average accuracy ranging between 0.955 to 0.975 and a kappa score between 0.678 and 0.795. the three most important channels detected by the optimization algorithm were D25, A19 and B14 from the 10-10 international system. this represents a significant improvement compared to the results obtained using the AASM-recommended channels, which yielded an average accuracy and kappa score of 0.951 and 0.573, respectively. © 2023, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

TAP: Transformers Driven Adaptive Prefetching for Hybrid Memory Systems

TAP: Transformers Driven Adaptive Prefetching for Hybrid Mem...

引用

International Conference on Soft computing and Machine Intelligence (ISCMI)

作者： Chandranil Chakraborttii Mohammad Maminur Islam Department of Computer Science Trinity College Hartford Connecticut

ISBN: (数字)9798331518127

ISBN: (纸本)9798331518134

In the rapidly evolving landscape of hybrid memory systems, which integrate different types of memory, optimizing cache management is vital for achieving high performance and efficiency. Traditional prefetching techniques often struggle to adapt to modern systems’ dynamic and complex I/O access patterns. this paper proposes a novel machine learning-based cache replacement framework tailored for hybrid memory architectures. Our framework leverages advanced transformerbased sequence-to-sequence models to analyze historical access patterns and make data-driven cache management decisions. By continuously learning from past access behavior and adapting to real-time workload changes, our system enhances cache hit rates, reduces latency, and optimizes storage performance. Our Transformer-based adaptive prefetching approach addresses the problem of predicting within large address spaces and shows significant improvements over traditional (Stride) and machine learning (ML) based (Markov Chains, Long Short Term Memory) prefetchers, achieving hit ratios of 0.71, 0.91, and 0.47 for mixed, streaming, and random access workloads. It yields 16-64% improvements across various traces and settings by capturing complex contextual relationships and adapting to dynamic access patterns, enhancing hybrid memory systems and enabling efficient, scalable storage management in modern computing environments.

关键词： Training Adaptive systems Prefetching Memory management Storage management Memory architecture Random access memory Transformers Real-time systems Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Distributed mobility management for fast terminals in an IP-based micro-cellular network along roads

Distributed mobility management for fast terminals in an IP-...

引用

International symposium on Communication Systems, Networks and Digital Signal Processing, CNSDSP

作者： Takahiko Yamada Satoshi Yamashita Takashi Okumura Phan thanh Hoa College of Science and Engineering Ritsumeikan University Kusatsu Shiga Japan

this paper presents a scalable control system for a unified micro-cellular network named MM-MAN (mobile multimedia metropolitan area network) in which fast terminals are provided high-bit rate IP packet transfer. In our previous papers, proposed schemes to guarantee smooth connections to fast movers in spite of frequent movement are LMC (logical macro cell) and parallel polling. LMC-a multicast group of adjacent micro-cells and pollings are emitted from all BSs of the same LMC create a symmetric environment as a virtual single cell so the cell-to-cell movement of a mobile terminal within an LMC can be passed over. Detail of the distributed control for mobility management is described in this article. An extended LMC is introduced to conduct pre-downloading of packets and to allow distributed processing for the LMC switchover. However, the radio active channel is manipulated only at BSs in the LMC range but not in the extended LMC to save radio resources due to the overhead of parallel polling. If the polling response comes to the BS which differs from the central cellpsilas BS of the LMC, this BS will be placed to become the central cell of the new LMC, and polling acknowledgement is multicast to the new extended LMC. the neighboring BS on the movement direction of the target mobile terminal (MT) can realize movement of the MT, and starts actions to join the new LMC by itself without help from the centralized control. these procedures can hide the delay in the cell-to-cell movement of the terminal even when it goes out from the LMC, and guarantee scalable and high-performance control over micro-cellular network. the simulation results tells the handover latency is less than 5 ms, and the throughput for MT in case of the continuous multimedia like moving picture is 2 Mbps over the 54 Mbps wireless interface.

关键词： Mobile communication Switches computer architecture Passive optical networks Optical network units Microprocessors Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Smart Parking System Using IoT

Smart Parking System Using IoT

引用

International Conference on Electronics, computers and Artificial Intelligence (ECAI)

作者： Hiba A. Abu-Alsaad Rana Riad K. Al-Taie Computer Engineering Dept. Mustansiriyah University Baghdad Iraq

ISBN: (数字)9798350371154

ISBN: (纸本)9798350371161

Sometimes parking practices lead to inefficiency and confusion, for example traffic congestion, drivers searching for vacant spaces, and insufficient revenue management for parking operators. Here the role of smart parking systems is highlighted in overcoming these challenges by providing live updates about the presence of unoccupied parking spots, improving the use of all parking spaces, and completing a convenient payment process. this paper introduces a parking system that incorporates cloud technology for seamless integration (Internet of things IoT). Proposed system involves deploying an IoT module on-site to monitor and indicate the system offers up-to-date information on the presence of each parking space, and it also offers a mobile application for end users to conveniently check parking space availability and make reservations as needed. the paper also provides an overview of the system architecture at a high level. Furthermore, the paper includes a use that demonstrates the operational functionality of the model being proposed. this use case serves as evidence to validate the accuracy and effectiveness of the system. Overall, this research contributes to addressing issues like traffic congestion, restricted parking options, and roadway safety through the implementation of IoT technology in a parking system that is integrated with cloud technology. this system strives to improve the utilization of parking spaces and elevate the parking experience by providing real time data and convenient booking choices.

关键词： Cloud computing Smart cities Transforms Automated parking Real-time systems Mobile applications Internet of things

来源：评论

学校读者我要写书评

暂无评论

MATE-CG: A Map Reduce-Like Framework for Accelerating Data-Intensive Computations on Heterogeneous Clusters

MATE-CG: A Map Reduce-Like Framework for Accelerating Data-I...

引用

International symposium on Parallel and Distributed Processing (IPDPS)

作者： Wei Jiang Gagan Agrawal Department of Computer Science and Engineering Ohio State University Columbus OH USA

Clusters of GPUs have rapidly emerged as the means for achieving extreme-scale, cost-effective, and powerefficient high performance computing. At the same time, high level APIs like map-reduce are being used for developing several types of high-end and/or data-intensive applications. Map-reduce, originally developed for data processing applications, has been successfully used for many classes of applications that involve a significant amount of computations, such as machine learning, image processing, and data mining applications. Because such applications can be accelerated using GPUs (and other accelerators), there has been interest in supporting map-reduce-like APIs on GPUs. However, while the use of map-reduce for a single GPU has been studied, developing map-reduce-like models for programming a heterogeneous CPU-GPU cluster remains an open challenge. this paper presents the MATE-CG system, which is a map reduce-like framework based on the generalized reduction API. We develop support for enabling scalable and efficient implementation of data-intensive applications in a heterogeneous cluster of multi-core CPUs and many-core GPUs. Our contributions are three folds: 1) we port the generalized reduction model on clusters of modern GPUs with a map-reduce-like API, dealing with very large datasets, 2) we further propose three schemes to better utilize the computing power of CPUs and/or GPUs and develop an auto-tuning strategy to achieve the best-possible heterogeneous configuration for iterative applications, 3) we show how analytical models can be used to optimize important parameters in our system. We evaluate our system using three representative data intensive applications and report results on a heterogeneous cluster of 128 CPU cores and 16 GPUs (7168 GPU cores). We show an average speedup of 87× on this cluster over execution with 2 CPU-cores. Our applications also achieve an average improvement of 25% by using CPU cores and GPUs simultaneously, over the best p

关键词： Graphics processing unit Runtime Analytical models Acceleration Data processing Computational modeling Multicore processing

来源：评论

学校读者我要写书评

暂无评论

2d-3d Hierarchical Feature Fusion Network For Segmentation Of Bone Structure In Knee Mr Image

2d-3d Hierarchical Feature Fusion Network For Segmentation O...

引用

IEEE International symposium on Biomedical Imaging

作者： Hui Wang Demin Yao Jiayi Chen Yanjing Liu Wensheng Li Yonghong Shi Digital Medical Research Center School of Basic Medical Sciences Fudan University Shanghai China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Fudan University Shanghai China. Histology and Embryology School of Basic Medical Sciences Fudan University Shanghai China.

ISBN: (纸本)9781665412469;9781665429474

Automatic segmentation of knee bone structures is an important task in orthopedics diagnosis of knee disease based on MRI images. Inspired by doctors' diagnosis of knee in sagittal plane of MR image, we propose to first calculate the sagittal maximum intensity projection (MIP) of MR image, then construct a high precision 2D-3D hierarchical feature fusion network for automatic segmentation of knee based on convolutional encoding and decoding architecture. It includes: 1) A 2D bypass network extracting global features based on MIP; 2) A 3D backbone network calculating local details based on MR volume; 3) A feature fusion module integrating 2D global context and 3D local details hierarchically. Particularly, the global features as anchor points will be fused with the local details at each level of the encoding path to enrich the context of local details and improve the segmentation accuracy. Our method is verified on SKI10 dataset. the average dice coefficients of femur, femoral cartilage, tibia and tibia cartilage are 0.978, 0.848, 0.979 and 0.848, respectively, and the segmentation performance is far better than the state-of-the-art methods.

关键词： Image segmentation three-dimensional displays Image coding Magnetic resonance imaging Semantics Medical services Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Energy Manager for high performance computer Clusters

An Energy Manager for High Performance Computer Clusters

引用

International symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Fernando Alvarruiz Carlos de Alfonso Miguel Caballer Vicente Hern'ndez Instituto de Instrumentación para Imagen Molecular (I3M) Universitat Politècnica de València Valencia Spain Universitat Politecnica de Valencia Valencia Valenciana ES

this paper presents a general energy management system for HPC clusters and cloud infrastructures that powers off cluster nodes when they are not being used, and conversely powers them on when they are needed. this system can be integrated with different HPC cluster middleware, such as Batch-Queuing Systems or Cloud Management Systems, by using a set of connectors, and is also able to deal with different mechanisms for powering on and off the computing nodes (such as Wake-on-Lan, Power Device Units, Intelligent Platform Management Interface or other infrastructure-specific mechanisms). While some existing Batch-Queuing Systems provide energy saving mechanisms, other popular choices lack this feature. Cloud management middleware do not generally provide this feature out of the box, and incorporating it implies making modifications to the middleware. the advantage of our approach is that it can be integrated with different resource management middleware, without needing any modification of that middleware. the paper describes the successful integration of the system proposed with the popular Torque/PBS management system, and also with the OpenNebula open source cloud management tool. Two real use-cases are presented, involving two different HPC clusters. these use cases show significant energy/costs savings of 38% and 16%.

关键词： Middleware Connectors Switches Resource management Virtual machining Booting computers

来源：评论

学校读者我要写书评

暂无评论

FloatAP: Supporting high-performance Floating-Point Arithmetic in Associative Processors

FloatAP: Supporting High-Performance Floating-Point Arithmet...

引用

IEEE/ACM International symposium on Microarchitecture (MICRO)

作者： Kailin Yang José F. Martínez Computer Systems Laboratory Cornell University Ithaca NY USA ByteDance Ltd. San José CA USA

ISBN: (数字)9798350350579

ISBN: (纸本)9798350350586

Associative Processors (AP) enable in-situ, data-parallel computation in content-addressable memories (CAM). In particular, arithmetic operations are accomplished via bit-serial sequences of bulk search and update primitives. the data-parallel nature of AP-based computation, whereby thousands of operations can take place concurrently, more than makes up for the slowness of its bit-serial arithmetic; as a result, APs can deliver very high performance. Indeed, recent AP proposals have shown promising results across various application domains, primarily for integer codes. However, floating-point (FP) support is crucial for many critical AI/ML and scientific workloads. this paper introduces FloatAP, the first highly programmable AP architecture tailored for high-performance FP arithmetic. We show that the straightforward application of AP-based bit-serial arithmetic to FP leads to insufficient computational through-put. With FloatAP, we propose a bit- and component-parallel vector mantissa alignment method that significantly improves the throughput of vector FP addition and reduction. We also repurpose the existing adder trees in modern APs to efficiently implement multiplication and dot product operations, markedly outperforming AP's traditional bit-serial multiplication. FloatAP is flexible enough to accommodate different FP formats while maintaining high utilization and integer compat-ibility. It is programmable using RISC-V ‘V’ vector extension and easily accommodates domain-specific languages and ML frameworks. We evaluate FloatAP using contemporary ML workloads, including CNN-, RNN-, and LLM-based parallel codes. the results show that, on average, FloatAP achieves 2.7 × higher inference throughput compared to an area-equivalent NVIDIA A100 Tensor Core GPU for single-precision FP (1.5 × for bfloat16) and 2.4 × higher energy efficiency (1.6 ×for bfloat16).

关键词： Microarchitecture Codes Tensors Memory management Graphics processing units throughput Vectors Energy efficiency Hardware Proposals

来源：评论

学校读者我要写书评

暂无评论

A Novel U-Net Based CNN Algorithm for high-Accuracy Weather Forecasting

A Novel U-Net Based CNN Algorithm for High-Accuracy Weather ...

引用

International Conference on Computational Intelligence and Communication Networks (CICN)

作者： thirumurugan Shanmugam Chirag Chandrashekar Arun Kumar Sivaraman Janakiraman Nithiyanantham Priya Ravindran S T Sarvesh Narayanan Department of Computing and Information Sciences University of Technology and Applied Sciences Suhar Oman School of CSE Vellore Institute of Technology Chennai India Digital Engineering Solution Centre Photon Interactive Inc. Ontario Canada Department of ECE K.L.N. College of Engineering Tamilnadu India School of Computer Science Dalhousie University Halifax Canada

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505271

Accurate weather forecasting is essential for sectors like agriculture, aviation, and disaster management. However, deep learning algorithms face challenges in prediction accuracy due to issues like vanishing gradients, overfitting, and high computational demands. this research proposes a novel U-Net based architecture utilizing a Convolutional Neural Network (CNN) bottleneck layer to improve weather forecasting. Key features include a skip-connection mechanism, modified weight update rules, Gaussian-mutation operations, and the Adam optimizer for enhanced feature extraction and faster, more accurate predictions. the model was tested using precipitation data from Doppler Weather Radar (DWR) Chennai Radar and weather parameters from European Centre for Medium-Range Weather Forecasts (ECMWF). A dedicated GeoServer facilitates realtime data processing. Experimental results show the proposed algorithm achieves 97.5% accuracy, outperforming CNN and long short-term memory (LSTM) models by 5.84% and 2.41%, respectively.

关键词： Accuracy Computational modeling Atmospheric modeling Weather forecasting Predictive models Feature extraction Prediction algorithms Convolutional neural networks Long short term memory Meteorology

来源：评论

学校读者我要写书评

暂无评论

Clothing Detection Action Recognition Based on Hierarchical Transformer Networks

Clothing Detection Action Recognition Based on Hierarchical ...

引用

International Conference on Communication Software and Networks, ICCSN

作者： Yuancheng Ma Xiaodong Wang Jian Yuan Lianjun Zhang Jimeng Chen Keshu Fen Linyun Yu College of Electrical Engineering and Computer Sciences Ningbo University Zhejiang Risun Intelligent Technology Co. Ltd Ningbo China

ISBN: (数字)9798331506322

ISBN: (纸本)9798331506339

In the application of industrial production operation action analysis based on computer vision, Transformer networks have the problem of large computational overhead and insufficient real-time performance. To address this issue and enable the network to be applied to clothing detection in industrial production operation recognition, a hierarchical Transformer network was constructed using network pooling and unit attention designs, which improved the accuracy of action recognition and focused on computing local information. A cosine re-weighting method was designed to replace the softmax operator in the self-attention mechanism of the Transformer network to reduce network overhead. the robustness of this network was verified on the HMDB51 dataset, achieving an accuracy of 91.7%, with a FLOPs of 42.8 G and 29 M parameters. Compared with other Transformer models, it significantly reduced network overhead while achieving high accuracy. For the analysis of clothing detection actions on a self-built dataset, an edge detection algorithm was added to the network to improve recognition accuracy. the improved network achieved a FLOPs of 22.9 G and 10 M parameters on the self-built clothing detection action dataset, with an accuracy of $\mathbf{9 7. 4 \%}$.

关键词： Accuracy Image edge detection Clothing Production Transformers Robustness Vectors Software Real-time systems Optimization

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442页 << < 433 434 435 436 437 438 439 440 441 442 > >>

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：