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

4,548 篇 会议
82 篇 期刊文献
15 册 图书

馆藏范围

4,645 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,559 篇 工学
- 2,365 篇 计算机科学与技术...
- 1,164 篇 软件工程
- 494 篇 电气工程
- 407 篇 信息与通信工程
- 213 篇 控制科学与工程
- 212 篇 电子科学与技术（可...
- 98 篇 网络空间安全
- 80 篇 动力工程及工程热...
- 80 篇 生物工程
- 68 篇 光学工程
- 65 篇 机械工程
- 56 篇 生物医学工程（可授...
- 36 篇 建筑学
- 30 篇 化学工程与技术
- 29 篇 环境科学与工程（可...
614 篇 理学
- 375 篇 数学
- 144 篇 物理学
- 93 篇 生物学
- 74 篇 系统科学
- 69 篇 统计学（可授理学、...
465 篇 管理学
- 346 篇 管理科学与工程(可...
- 134 篇 图书情报与档案管...
- 129 篇 工商管理
- 65 篇 公共管理
111 篇 法学
- 103 篇 社会学
104 篇 医学
- 73 篇 公共卫生与预防医...
- 31 篇 临床医学
- 29 篇 基础医学(可授医学...
65 篇 文学
- 65 篇 新闻传播学
39 篇 经济学
- 38 篇 应用经济学
17 篇 教育学
10 篇 农学
1 篇 艺术学

主题

1,194 篇 computer archite...
426 篇 hardware
344 篇 high performance...
295 篇 computational mo...
255 篇 concurrent compu...
236 篇 application soft...
214 篇 computer science
205 篇 parallel process...
179 篇 distributed comp...
178 篇 costs
171 篇 delay
170 篇 grid computing
168 篇 bandwidth
164 篇 field programmab...
154 篇 resource managem...
153 篇 cloud computing
144 篇 computer network...
142 篇 throughput
129 篇 processor schedu...
125 篇 scalability

机构

22 篇 institute of com...
16 篇 graphic era deem...
14 篇 chitkara univers...
13 篇 university of ch...
11 篇 college of compu...
10 篇 school of comput...
10 篇 computer science...
9 篇 georgia inst tec...
9 篇 computer systems...
9 篇 intel corp santa...
8 篇 department of co...
8 篇 department of el...
8 篇 ibm thomas j. wa...
8 篇 barcelona superc...
8 篇 mathematics and ...
8 篇 quantum universi...
8 篇 中国电子科技集团...
8 篇 mathematics and ...
8 篇 key laboratory o...
8 篇 univ fed rio gra...

作者

14 篇 navaux philippe ...
10 篇 satvik vats
9 篇 vats satvik
9 篇 i. foster
9 篇 d.k. panda
8 篇 dhabaleswar k. p...
8 篇 dongarra jack
8 篇 loh gabriel h.
8 篇 guedes dorgival
8 篇 viktor k. prasan...
8 篇 prasanna viktor ...
8 篇 mutlu onur
7 篇 shiva mehta
7 篇 borin edson
7 篇 chong frederic t...
7 篇 torrellas josep
7 篇 kim nam sung
7 篇 li chao
7 篇 zhou huiyang
7 篇 ferreira renato

语言

4,522 篇 英文
101 篇 其他
20 篇 中文
3 篇 葡萄牙文
1 篇 法文

检索条件"任意字段=15th Symposium on Computer Architecture and High Performance Computing"

共 4645 条记录，以下是511-520 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：

Accelerating Non-Negative Matrix Factorization on Embedded FPGA with Hybrid Logarithmic Dot-Product Approximation 15

Accelerating Non-Negative Matrix Factorization on Embedded F...

引用

15th IEEE International symposium on Embedded Multicore/Many-Core Systems-on-Chip, MCSoC 2022

作者： Chen, Yizhi Nevarez, Yarib Lu, Zhonghai Garcia-Ortiz, Alberto Kth Royal Institute of Technology School of Electrical Engineering and Computer Science Stockholm Sweden Bremen Germany

ISBN: (纸本)9781665464994

Non-negative matrix factorization (NMF) is an ef-fective method for dimensionality reduction and sparse decom-position. this method has been of great interest to the scien-tific community in applications including signal processing, data mining, compression, and pattern recognition. However, NMF implies elevated computational costs in terms of performance and energy consumption, which is inadequate for embedded applications. To overcome this limitation, we implement the vector dot-product with hybrid logarithmic approximation as a hardware optimization approach. this technique accelerates floating-point computation, reduces energy consumption, and preserves accuracy. To demonstrate our approach, we employ a design exploration flow using high-level synthesis on an embedded FPGA. Compared with software solutions on ARM CPU, this hardware implementation accelerates the overall computation to decompose matrix by 5.597 × and reduces energy consumption by 69.323×. Log approximation NMF combined with KNN(k-nearest neighbors) has only 2.38% decreasing accuracy compared with the result of KNN processing the matrix after floating-point NMF on MNIST. Further on, compared with a dedicated floating-point accelerator, the logarithmic approximation approach achieves 3.718× acceleration and 8.345× energy reduction. Compared with the fixed-point approach, our approach has an accuracy degradation of 1.93% on MNIST and an accuracy amelioration of 28.2% on the FASHION MNIST data set without pre-knowledge of the data range. thus, our approach has better compatibility with the input data range. © 2022 IEEE.

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

Proposal of A Novel Hybrid NAND-Like MRAM/DRAM Memory architecture 20

Proposal of A Novel Hybrid NAND-Like MRAM/DRAM Memory Archit...

引用

20th IEEE-computer-Society Annual symposium on VLSI (ISVLSI)

作者： He, Kuiqing Yang, Zhi Yu, Zhitai Zhi, Jianglong Wang, Zhaohao Wang, Yijiao Beihang Univ Sch Integrated Circuit Sci & Engn Beijing 100191 Peoples R China Beihang Univ Fert Beijing Res Inst Beijing 100191 Peoples R China Beihang Univ MIIT Key Lab Spintron Beijing 100191 Peoples R China Beihang Univ Hefei Innovat Res Inst Hefei 230013 Peoples R China

ISBN: (纸本)9781665439466

Due to the high refresh energy consumption, DRAM cannot meet the low energy consumption demand of IoT terminal, and the volatile data further limits its application in in-memory computing system. A non-volatile architecture utilizing novel hybrid NAND-like MRAM/DRAM cells that enables effective power and area reduction for high performance memory system is presented. the non-volatile characteristic of MRAM makes up for the refresh operation of DRAM and the leakage current path is eliminated in our proposed structure. the proposed two working modes, which are MRAM mode and DRAM mode, are explored with a novel writing scheme and expected to satisfy the demands of different memory hierarchy. To take the advantage of the hybrid structure, computing in memory operation is studied, solving the problem of data destruction caused by DRAM in the memory computing operation At last, power consumption, writing speed and area overhead are analyzed in detail.

关键词： non-volatile DRAM NAND-like MRAM hybrid structure in-memory computing

来源：评论

学校读者我要写书评

暂无评论

Real-Time Parallel LU Decomposition of Space Debris Features On-Board

Real-Time Parallel LU Decomposition of Space Debris Features...

引用

International Conference on Advanced Infocomm Technology (ICAIT)

作者： Jiyang Yu Dan Huang Jinyang Li Wenjie Li Xianjie Wang Qunzhi Li China Academy of Space Technology Beijing Institute of Spacecraft System Engineering Beijing China China Research & Development Academy of Machinery Equipment Chongqing University of Technology Beijing China Chongqing China Beijing Blackstone Matrix Technology Co. LTD Chongqing Feima Innovation Research Institute Chongqing China College of Computer Science and Engineering Chongqing University of Technology Chongqing China

this paper provides a parallel LU decomposition calculation method for on orbit Real-time computing calculation of space debris target characteristics. the purpose is to overcome the shortcomings of the traditional LU decomposition design, carry out high-precision approximate calculation of division in the LU calculation process, design a full pipeline parallel computing architecture based on digital logic devices according to the interrelationship between Land $U$ matrix elements, and design the calculation process and timing of each sub step by combing the correlation of each element in the calculation process, Real time LU decomposition of space target is realized on the basis of ensuring the calculation accuracy and executable frequency, and the target principal component features are obtained. the LU solution based on this design can effectively distinguish the characteristics of stars and debris targets in batches. through experimental verification, the overall calculation performance has been improved by an order of magnitude compared to previous designs, and the designed fixed point calculation error is not more than 1%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low Power, high Speed Current Starved Ring Oscillator based ADC using 18nm FinFET Technology

Low Power, High Speed Current Starved Ring Oscillator based ...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Gokul Chandrasekaran P Pavithara P M Dinesh V Arun Kumar J S Sharanyanivasini K Kavin Kumar Department of Electronics and Communication Engineering Karpagam Institute of Technology Coimbatore Department of Electronics and Communication Engineering Kongu Engineering College Perundurai Erode Department of Electronics and Communication Engineering Sona College of Technology Salem Department of Electrical and Electronics Engineering Nandha Engineering College Erode India Department of Computer Science and Engineering Erode Sengunthar Engineering College Perundurai Thuduppathi

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

the goal of achieving high performance, low power consumption, and small area footprint is still central to the field of analog-to-digital converters (ADCs). this work describes a new methodology that enables the design of Current Starved Ring Oscillator (CSRO) architecture using 18nm FinFET technology. the CSRO based ADC meets the growing needs of contemporary electronic systems with promised improvements in speed, power efficiency, and portability. the intrinsic qualities of FinFET transistors are utilized by the CSRO architecture to produce high performance metrics such as improved sub threshold behavior, lower leakage currents, and superior gate control, all of which are essential for low power consumption and high speed operation. In addition, compared to conventional ADC designs, the 18 nm production node enables tighter component integration, resulting in a compact ADC design. the precise analog-to- digital conversion is made possible by controlling the oscillation frequency through the use of current starving techniques. In order to reduce power consumption, mitigate electromagnetic interference and extend the battery life, starving ring oscillators are employed. the ability of the GDI (Gate Diffusion Input) technique to lower space overhead and power consumption provides an effective solution for low-power and high-density applications in contemporary integrated circuits. the proposed CSRO based ADC with GDI technique experiences a delay of 1.208 ns and power consumption of 356.08 mW while the ADC without GDI technique involves a delay of 1.44 ns and 391 mW of power consumption. this shows that the proposed ADC exhibits 14% improvement inspeed and 9% improvement in power compared to the ADCwithout GDI technique.

关键词： Ring oscillators performance evaluation Power demand Production Logic gates Signal processing FinFETs Delays Transistors Propagation delay

来源：评论

学校读者我要写书评

暂无评论

Ternary-Valued Associative Processor Design

Ternary-Valued Associative Processor Design

引用

IEEE International symposium on Quality Electronic Design

作者： Mira Hout Rouwaida Kanj Ahmed M. Eltawil Mohammed E. Fouda ECE Dept. American University of Beirut Lebanon Synopsys Inc Austin TX USA King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia Rain Neuromorphics Inc. San Francisco CA USA

ISBN: (数字)9798331509422

ISBN: (纸本)9798331509439

In-memory computing architectures have emerged as a promising solution to address the memory-wall bottleneck and enable efficient vectorized and parallel arithmetic operations. this paper proposes a hardware architecture and algorithms for ternary-valued associative processors (TAP) which is a critical step toward broadening their computational versatility. To facilitate the in-memory implementation of complex arithmetic and logic functions, we introduce an efficient methodology for the automatic generation of corresponding look-up tables (LUTs). A SPICE-MATLAB co-simulator is developed to evaluate the performance of the proposed TAP-based in-memory ternary adder in terms of energy consumption, computational delay, and area overhead. Comparative analysis demonstrates that the ternary AP adder achieves energy and area reductions of 11% and 6.2%, respectively, compared to its binary counterpart. Furthermore, compared to state-of-the-art ternary carry-lookahead adder, the proposed solution exhibits around 100x and 9.5x reduction in energy and delay, respectively. this work highlights the potential of in-memory and parallel computing processors to high-efficiency arithmetic operations, offering scalable and energy-efficient solutions for emerging computational workloads.

关键词： Energy consumption Program processors computer architecture Parallel processing In-memory computing Energy efficiency Delays Table lookup Adders Arithmetic

来源：评论

学校读者我要写书评

暂无评论

Breaking the Fake: A CNN-BiLSTM Approach for Fake News Detection on Social Media

Breaking the Fake: A CNN-BiLSTM Approach for Fake News Detec...

引用

IEEE Annual computing and Communication Workshop and Conference (CCWC)

作者： Rohit Viswakarma Pidishetti Uma Chinta Department of Computer Science Texas Tech University Texas USA

ISBN: (数字)9798331507695

ISBN: (纸本)9798331507701

Misinformation, especially during global crises like the COVID-19 pandemic, has posed significant challenges by spreading harmful and baseless claims at an unprecedented scale. Addressing this critical issue requires robust methods for distinguishing reliable information from fake news. this study presents a novel deep learning approach that leverages a hybrid Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) model to detect misinformation with high accuracy. Using the COVID-19 Fake News dataset, comprising 8,560 tweets validated by fact-checking organizations, our proposed model achieves a remarkable 92% accuracy, surpassing traditional machine learning models and other deep learning approaches. this paper details the development of the hybrid architecture, its implementation, and a comparative analysis with existing methods, demonstrating its effectiveness in combating the spread of fake news on social media platforms.

关键词： COVID-19 Deep learning Accuracy Social networking (online) Computational modeling Text categorization Reliability Convolutional neural networks Fake news Testing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Early Disease Detection: A CNN Approach to Classify Potato, Tomato, and Pepper Leaf Diseases

Deep Learning for Early Disease Detection: A CNN Approach to...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Karan Sarawagi Hardik Dhiman Ashutosh Pagrotra Navjot Singh Talwandi Department of CSE Chandigarh University MOHALI India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Early disease detection is crucial for maximizing crop yields and minimizing financial losses in agriculture. In order to categorize leaf diseases in pepper, tomato, and potato plants, this study suggests a revolutionary CNN design. the algorithm collects disease-specific features from input photos by using data augmentation techniques to artificially enlarge the training dataset. ReLU-activated convolutional layers gradually capture features at different levels, from low to high, while max pooling layers minimize spatial dimensionality. After the characteristics are extracted, a fully-connected layers with a SoftMax activation function classify them into illness groups. A well-chosen dataset containing labelled healthy and sick leaves is used to train and validate the model. Generalizability to untested data is ensured via performance evaluation on an independent testing set. the field of deep learning for agricultural applications benefits from this research. this strategy has the ability to revolutionize agricultural practices by enabling automated disease identification. this might result in early interventions, better crop health, and eventually sustainable agricultural production.

关键词： Training Deep learning Training data computer architecture Production Data augmentation Data models Convolutional neural networks Diseases Testing

来源：评论

学校读者我要写书评

暂无评论

DeeplabV3+ for precise GI Tract segmentation in MRI images

DeeplabV3+ for precise GI Tract segmentation in MRI images

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Dasari Chinna Veeraiah Bindu Madhavi Tummala Rishitha Jaladi Aruna Kumari Peruri Computer Science and Engineering Velagapudi Ramakrishna Siddhartha Engineering College Vijayawada India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Medical image processing has revolutionized the way in which healthcare professionals diagnose and treat various diseases and conditions. GI cancer is the fastest-growing cancer in recent times with an estimated 5 million new cases annually. Radiation therapy is a successful treatment option, but it requires precise targeting of high X-ray beam dosages to the tumors while protecting the surrounding healthy organs. Daily tumor positions are viewed by the latest MRI modality called MR-Linacs. From the obtained medical images, the radiologist has to manually segment the healthy organs at risk like the stomach and intestines. It is a time-consuming process that can drag the treatment time and increase the suffering of the patients. In this study, we use the DeepLabv3+ model, a cutting-edge convolutional neural network architecture for semantic segmentation, to present a unique method for GI tract segmentation. Leveraging its powerful features, including atrous spatial pyramid pooling (ASPP) and encoder-decoder architecture, the DeepLabv3+ model demonstrates remarkable accuracy. the loss function Sparse Categorical Cross Entropy is employed in this study. Its accuracy is 0.9892, and its IOU Mean score is 0.5678.

关键词： Stomach Accuracy Intestines Magnetic resonance imaging Computational modeling computer architecture Radiation therapy X-ray imaging Tumors Cancer

来源：评论

学校读者我要写书评

暂无评论

Partial Convolution U-Net for Inpainting Distorted Images

Partial Convolution U-Net for Inpainting Distorted Images

引用

International Conference on computing and Networking Technology (ICCNT)

作者： R Rashmi Adyapady B Annappa Prem Sagar Department of Artificial Intelligence and Machine Learning NITTE (Deemed to be University)NMAM Institute of Technology Nitte Karnataka India Department of Computer Science and Engineering DISCOVER Lab National Institute of Technology Karnataka Mangalore Karnataka India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Image inpainting is a domain in which researchers have shown considerable interest, and when it comes to deep learning techniques, realistic problems become interesting and challenging. In image inpainting, a corrupted facial image with missing holes or significant holes can be restored and compared to the original image to see if it is real or fake. In addition to fixing the texture of the image and getting the image’s high-level abstract properties, it may also recover semantic images such as human faces. In the field of image-inpainting models, the Attention model with features learned through semantic approaches and progressive networks has become particularly popular. the proposed model introduces (i) Attention blocks in each decoder layer of U-Net architecture and (ii) a hybrid loss function leveraging both Mean Square Error (MSE) and Mean Absolute Error (MAE). the proposed Attention-based U-Net showed remarkable performance with SSIM and PSNR by 0.1067 and 13.63, respectively, compared to the previous approaches.

关键词： Deep learning Convolution Semantics Mean square error methods Predictive models Generative adversarial networks Decoding Image restoration Security Faces

来源：评论

学校读者我要写书评

暂无评论

Joint Wireless and computing Resource Management with Optimal Slice Selection in in-network-edge Metaverse System

Joint Wireless and Computing Resource Management with Optima...

引用

International Conference on Information and Communication Technology Convergence (ICTC)

作者： Sulaiman Muhammad Rashid Ibrahim Aliyu Abubakar Isah Jihoon Lee Sangwon Oh Minsoo Hahn Jinsul Kim Department of Intelligent Electronics and Computer Engineering Chonnam National University Gwangju S/Korea Department of Computational and Data Science Astana IT University Astana Kazakhstan

ISBN: (数字)9798350364637

ISBN: (纸本)9798350364644

this paper presents an approach to joint wireless and computing resource management in slice-enabled metaverse networks, addressing the challenges of inter-slice and intra-slice resource allocation in the presence of in-network computing. We formulate the problem as a mixed-integer nonlinear programming (MINLP) problem and derive an optimal solution using standard optimization techniques. through extensive simulations, we demonstrate that our proposed method significantly improves system performance by effectively balancing the allocation of radio and computing resources across multiple slices. Our approach outperforms existing benchmarks, particularly in scenarios with high user demand and varying computational tasks.

关键词： Wireless communication Metaverse System performance Computational modeling Programming Information and communication technology Resource management Standards Optimization Convergence

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465页 << < 48 49 50 51 52 53 54 55 56 57 > >>

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：