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

16,563 篇 会议
211 篇 期刊文献

馆藏范围

16,774 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10,863 篇 工学
- 7,728 篇 计算机科学与技术...
- 4,145 篇 电气工程
- 3,546 篇 软件工程
- 3,192 篇 信息与通信工程
- 1,027 篇 控制科学与工程
- 818 篇 电子科学与技术（可...
- 614 篇 生物医学工程（可授...
- 479 篇 机械工程
- 477 篇 仪器科学与技术
- 456 篇 光学工程
- 305 篇 动力工程及工程热...
- 254 篇 生物工程
- 187 篇 交通运输工程
- 166 篇 航空宇航科学与技...
- 160 篇 网络空间安全
- 122 篇 材料科学与工程（可...
- 117 篇 石油与天然气工程
2,786 篇 理学
- 1,610 篇 数学
- 1,137 篇 物理学
- 414 篇 统计学（可授理学、...
- 295 篇 生物学
- 160 篇 系统科学
- 135 篇 化学
1,777 篇 医学
- 1,671 篇 临床医学
- 206 篇 基础医学(可授医学...
- 122 篇 药学(可授医学、理...
- 108 篇 特种医学
882 篇 管理学
- 611 篇 管理科学与工程(可...
- 325 篇 图书情报与档案管...
- 106 篇 工商管理
80 篇 法学
78 篇 农学
59 篇 经济学
38 篇 文学
28 篇 军事学
27 篇 教育学
19 篇 艺术学

主题

3,291 篇 data compression
1,747 篇 image coding
1,244 篇 image compressio...
1,138 篇 video compressio...
900 篇 point cloud comp...
647 篇 three-dimensiona...
571 篇 encoding
536 篇 compression
508 篇 transform coding
501 篇 decoding
450 篇 data mining
415 篇 compression algo...
369 篇 bandwidth
341 篇 video coding
268 篇 training
256 篇 streaming media
247 篇 computer science
245 篇 deep learning
238 篇 data models
232 篇 discrete cosine ...

机构

25 篇 tsinghua univers...
25 篇 univ chinese aca...
23 篇 ieee
23 篇 department of el...
22 篇 univ calif river...
22 篇 department of el...
22 篇 peng cheng lab p...
19 篇 peking univ peop...
19 篇 peking univ inst...
18 篇 university of ch...
17 篇 argonne natl lab...
16 篇 shanghai jiao to...
16 篇 univ sci & techn...
16 篇 harbin institute...
16 篇 signal and data ...
16 篇 hewlett packard ...
15 篇 department of au...
14 篇 penn state univ ...
14 篇 nanyang technolo...
14 篇 peng cheng labor...

作者

50 篇 w. kinsner
22 篇 liang xin
22 篇 tao dingwen
21 篇 xiong hongkai
18 篇 lukin vladimir
18 篇 pratas diogo
17 篇 wang shiqi
16 篇 klasky scott
15 篇 li li
13 篇 ma zhan
12 篇 wang ronggang
12 篇 jin sian
12 篇 moffat a
12 篇 zhou wang
12 篇 pinho armando j.
11 篇 wang jing
11 篇 ye yan
11 篇 liu zhi
11 篇 wang wei
11 篇 shapira dana

语言

16,327 篇 英文
298 篇 其他
116 篇 中文
28 篇 土耳其文
3 篇 俄文
1 篇 西班牙文
1 篇 葡萄牙文

检索条件"任意字段=IEEE Data Compression Conference"

共 16774 条记录，以下是801-810 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：

Durin: CPU-FPGA Heterogeneous Platform for Scalable Low-Dimensional data Clustering

Durin: CPU-FPGA Heterogeneous Platform for Scalable Low-Dime...

引用

2024 ieee International conference on Big data, Bigdata 2024

作者： Lim, Se-Min Aliaj, Esmerald Jun, Sang-Woo University of California Irvine Department of Computer Science IrvineCA United States

ISBN: (纸本)9798350362480

Reconfigurable hardware accelerators, known for their high performance and power efficiency, have yet to be fully leveraged for clustering low-dimensional data at realistic scales. In this work, we identify and address two hurdles for accelerating this important class of applications: the overhead of implementing indexing data structures in hardware, and the PCIe bottleneck when the data capacity spills over from accelerator memory to host storage. We overcome these hurdles for the first time with Durin, a CPU-FPGA heterogeneous system with a hardware-software codesigned index structure, which minimizes the hardware resource overhead of high-performance neighbor search. It also minimizes PCIe overhead by facilitating asynchronous acceleration of distance calculation, and block floating-point compression. We show that a desktop computer with Durin implemented on a mid-range Alveo U50 FPGA can outperform a 32-thread Xeon server by almost 20× , with an order of magnitude power efficiency improvements. Furthermore, Durin outperforms even the best-case projection of a conventional standalone accelerator design, which implements the entirety of the clustering algorithm in the FPGA and its High Bandwidth Memory (HBM), by 2×. © 2024 ieee.

关键词： Personal computers

来源：评论

学校读者我要写书评

暂无评论

Enabling Efficient Cloud-Based data Collection System for Smart Home IoT data Using data Binning and Lossless compression 16

Enabling Efficient Cloud-Based Data Collection System for Sm...

引用

16th International conference on Knowledge and Smart Technology, KST 2024

作者： Wongbubpha, Panipak Malitong, Pavida Pinthong, Napathsara Fugkeaw, Somchart School of ICT Sirindhorn International Institute of Technology Thammasat University Pathum Thani Thailand

ISBN: (纸本)9798350370737

The ever-growing volume of data generated by Internet of Things (IoT) devices necessitates efficient storage and retrieval mechanisms. This paper proposes a data collection system tailored to accommodate the unique characteristics of IoT data. The system aimed at optimizing the storage space within the Firestore, a NoSQL schemeless cloud-based database, by implementing the data binning technique, grouping similar values and replacing the original data with its group name, and the GZIP lossless data compression technique to enhance data retrieval performance to dynamic web pages. The proposed data storage scheme comprises two collections: the Temporary Collection, where formatted data of IoT devices is temporarily stored every one-second interval, and the Archived Collection, where data older than one hour is compressed and archived. We also developed a web-based dashboard to visualize the data of the past hour by extracting a dataset from the Temporary Collection, while historical data is retrieved by decompressing data from the Archived Collection only. Experimental results reveal a compression ratio of 4.538:1 and a space-saving ratio of 0.789, promising substantial cost savings on cloud-based platforms by reducing data size for storage and transmission. With a reasonable decompression time of 11.26 milliseconds and a significantly lower response time of 130.2 milliseconds compared to 1916.36 milliseconds of test cases, the proposed system remarkably improves real-time data processing, contributing to enriched user experiences and informed decision-making within the IoT web-based dashboard. © 2024 ieee.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Succinct data Structure for Path Graphs

Succinct Data Structure for Path Graphs

引用

data compression conference (DCC)

作者： Balakrishnan, Girish Chakraborty, Sankardeep Narayanaswamy, N. S. Sadakane, Kunihiko Indian Inst Technol Madras Chennai Tamil Nadu India Univ Tokyo Tokyo Japan

ISBN: (纸本)9781665478939

We consider the problem of designing space-efficient data structures for unlabelled path graphs with n vertices while supporting basic navigational queries such as degree, adjacency, and neighborhood queries efficiently. We provide two solutions for this problem. Our first data structure is succinct and occupies n log n + o(n log n) bits while answering adjacency query in O(log n) time, and neighborhood and degree queries in O(d log(2) n) time where d is the degree of the queried vertex. Our second data structure answers all these queries faster at the expense of slightly more space. More specifically, it consumes O(n log(2) n) bits while answering adjacency and degree queries in constant time and neighborhood query in O(d log n) time. Central to our data structures is the usage of the classical heavy path decomposition, followed by a careful bookkeeping using an orthogonal range search data structure among others, which may be of independent interest for designing succinct data structures for other graphs.

关键词： Navigation Algorithms data compression data structures

来源：评论

学校读者我要写书评

暂无评论

Compressed Matrix Computations 9

Compressed Matrix Computations

引用

ieee/ACM 15th International conference on Utility and Cloud Computing (UCC) / 9th International conference on Big data Computing, Applications and Technologies (BDCAT)

作者： Martel, Matthieu Univ Perpignan LAMPS 52 Ave Paul Alduy Perpignan France

ISBN: (纸本)9781665460903

Frugal computing is becoming an important topic for environmental reasons. In this context, several techniques have been proposed to reduce the storage of scientific data by dedicated compression methods specially tailored for arrays of floating-point numbers. While these techniques are quite efficient to save memory, they introduce additional computations to compress and decompress data before processing them. In this article, we introduce a new lossy, fixed-rate compression technique for 2D-arrays of floating-point numbers which allows one to compute directly on the compressed data, without decompressing them. We obtain important speedups since less operations are needed to compute among the compressed data and since no decompression and re-compression is needed. More precisely, our technique makes it possible to perform basic linear algebra operations such as addition, multiplication by a constant among compressed matrices and dot product and matrix multiplication among partly uncompressed matrices. This work has been implemented into a tool named blaz and we present a comparison with the wellknown compressor zfp in terms of execution-time and accuracy.

关键词： Green computing Frugal Computing Lossy compression Floating-point numbers Linear algebra

来源：评论

学校读者我要写书评

暂无评论

Evaluating Model compression Techniques for On-Device Browser Sign Language Recognition Inference 31

Evaluating Model Compression Techniques for On-Device Browse...

引用

31st ieee International conference on Electronics, Electrical Engineering and Computing, INTERCON 2024

作者： Salazar, Mauricio Bandara, Danushka Bejarano, Gissella Pontificia Universidad Católica del Perú Digital Humanities Laboratory Lima Peru Fairfield University Dept. of Comp. Sci. and Engineering FairfieldCT06824 United States Marist College Department of Computer Science PoughkeepsieNY United States

ISBN: (纸本)9798350378344

Due to the improvement of sign language (SL) recognition models, more work has started to build upon them to create end-user platforms such as video-based dictionaries. Although most of them base their design on cloud services or APIs, this approach can become expensive, especially when working with such substantial dimensional data as videos. Other realities, such as regions with low internet connection and few economic resources, can benefit from the offline alternative for deploying these systems. However, models deployed in websites' front-end or edge devices have some constraints on their size. Therefore, our work evaluates two model compression techniques to enhance the performance of on-device inference for a SL recognition model. We test knowledge quantization and distillation on three datasets varied in size, ultimately deploying and evaluating them on a locally hosted web page. To the best of our knowledge, this is the first evaluation of a quantized and distilled transformer-based SL recognition model for on-device browser inference. Furthermore, the combination of both compression techniques achieves a size reduction of up to 17.83 times and a speedup of 5.9 times the baseline. © 2024 ieee.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Graph-based Transform based on 3D Convolutional Neural Network for Intra-Prediction of Imaging data

Graph-based Transform based on 3D Convolutional Neural Netwo...

引用

data compression conference (DCC)

作者： Roy, Debaleena Guha, Tanaya Sanchez, Victor Univ Warwick Dept Comp Sci Coventry W Midlands England Univ Glasgow Sch Comp Sci Glasgow Lanark Scotland

ISBN: (纸本)9781665478939

This paper presents a novel class of Graph-based Transform based on 3D convolutional neural networks (GBT-CNN) within the context of block-based predictive transform coding of imaging data. The proposed GBT-CNN uses a 3D convolutional neural network (3D-CNN) to predict the graph information needed to compute the transform and its inverse, thus reducing the signalling cost to reconstruct the data after transformation. The GBT-CNN outperforms the DCT and DCT/DST, which are commonly employed in current video codecs, in terms of the percentage of energy preserved by a subset of transform coefficients, the mean squared error of the reconstructed data, and the transform coding gain according to evaluations on several video frames and medical images.

关键词： Three-dimensional displays Symmetric matrices Quantization (signal) Transform coding Transforms Convolutional neural networks Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

SK-Gradient: Efficient Communication for Distributed Machine Learning with data Sketch 39

SK-Gradient: Efficient Communication for Distributed Machine...

引用

39th ieee International conference on data Engineering, ICDE 2023

作者： Gui, Jie Song, Yuchen Wang, Zezhou He, Chenhong Huang, Qun Peking University China

ISBN: (纸本)9798350322279

With the explosive growth of data volume, distributed machine learning has become the mainstream approach for training deep neural networks. However, distributed machine learning incurs non-trivial communication overhead. To this end, various compression schemes are proposed to alleviate the communication volume among nodes. Nevertheless, existing compression schemes, such as gradient quantization or gradient sparsification, suffer from low compression ratios and/or high computational overheads. Recent studies advocate leveraging sketch techniques to assist these schemes. However, the limitations of gradient quantization and gradient sparsification remain. In this paper, we propose SK-Gradient, a novel gradient compression scheme that solely builds on sketch. The core component of SK-Gradient is a novel sketch namely FGC Sketch that is tailored for gradient compression. FGC Sketch precomputes the costly hash functions to alleviate computational overheads. Its simplified design makes it convenient for GPU acceleration. In addition, SK-Gradient leverages various techniques including selective gradient compression and periodic synchronization strategy to improve computational efficiency and compression accuracy. Compared with the state-of-the-art schemes, SK-Gradient achieves up to 92.9% reduction in computational overhead and up to 95.2% improvement in training speedups at the same compression ratio. © 2023 ieee.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Novel Real-Time Image Transmission (RTIT) Algorithm for Remote Electronic Engineering Labs 5

Novel Real-Time Image Transmission (RTIT) Algorithm for Remo...

引用

5th International conference on data Intelligence and Cognitive Informatics, ICDICI 2024

作者： He, Xiaoyu He, Zhaobin Huang, Xujun School of Arts and Communication Xiamen Institute of Technology Fujian Xiamen361021 China

ISBN: (纸本)9798350389609

Real-time image processing methods are well applied in engineering practice. This study presents a breakthrough real-time image transmission algorithm designed specifically for remote electronic engineering laboratories. By taking into account the latest communication technologies, the algorithm overcomes the limitations of conventional engineering experiments and facilitates remote experimentation. It is composed of a novel image compression algorithm, a real-time image transmission model, and remote communication ideas. The tests result reflect the effectiveness of the algorithm with the results showing that the average success rate of 99.05% in 13 tests. It significantly performs better than the traditional methods with an average of 93.03%. This proposed methodology suggests the better performance in the real-time image transmission studies. © 2024 ieee.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

An Energy Efficient Improved Clustering based data compression Protocol in Wireless Sensor Network 7

An Energy Efficient Improved Clustering based Data Compressi...

引用

7th International conference on Contemporary Computing and Informatics, IC3I 2024

作者： Anshad, A.S. Tiwari, Sourabh Vignesh, G.D. Charan, Piyush Chandra, K. Ramesh Manchanda, Rachit John Cox Memorial Csi Institute of Technology Kerala Thiruvananthapuram India Chandigarh University Department of Cse Punjab Mohali India St Joseph's College of Engineering Department of Ece OMR Tamil Nadu Chennai India Manav Rachna University Department of Ece Haryana Faridabad India Vishnu Institute of Technology Department of Ece Andhra Pradesh Kovvada India

ISBN: (纸本)9798350350067

Extensive research methodologies have revealed that wireless sensor networks (WSNs) are being utilized across a diverse array of applications, facilitating wireless data collection, communication, and intelligent computing. Sensor nodes (SNs) are compact in size, battery-powered and they are incorporated with intelligent computing capabilities to detect changes in the physical environment. These SNs convert sensed data into digital format and transmit it to a central data collection node. Nevertheless, SNs face resource limitations and rely on finite battery power. On the other hand, continuous monitoring of the physical environment consumes significant energy, leading to rapid battery depletion and potential node failure. Therefore, energy preservation in WSNs is regarded as a paramount concern to sustain node functionality over extended durations. In this research paper, we proposed a model that employs a Compressive sensing (CS) in WSN which optimizes transmission rates and distributes traffic load evenly in the network. Moreover, Cluster-based strategies are also incorporated with CS for overall network energy efficiency and to effectively extend the lifespan of the network. This approach has resulted in the development of an energyefficient clustering protocol, referred to as the An Energy Efficient Improved Clustering-Based data compression Protocol (EEIC-DCP), proposed specifically for WSNs. Extensive simulations have validated that our proposed approach significantly improves energy conservation and prolongs the network's operational lifespan. © 2024 ieee.

关键词： data compression

来源：评论

学校读者我要写书评

暂无评论

LNPT: Label-free Network Pruning and Training

LNPT: Label-free Network Pruning and Training

引用

International Joint conference on Neural Networks (IJCNN)

作者： Xiao Jinying Ping Li Zhe Tang Jie Nie Changsha Univ Sci & Technol Sch Comp & Commun Engn Changsha Peoples R China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329;9798350359312

Pruning before training enables the deployment of neural networks on smart devices. By retaining weights conducive to generalization, pruned networks can be accommodated on resource-constrained smart devices. It is commonly held that the distance on weight norms between the initialized and the fully-trained networks correlates with generalization performance. However, as we have uncovered, inconsistency between this metric and generalization during training processes, which poses an obstacle to determine the pruned structures on smart devices in advance. In this paper, we introduce the concept of the learning gap, emphasizing its accurate correlation with generalization. Experiments show that the learning gap, in the form of feature maps from the penultimate layer of networks, aligns with variations of generalization performance. We propose a novel learning framework, LNPT, which enables mature networks on the cloud to provide online guidance for network pruning and learning on smart devices with unlabeled data. Our results demonstrate the superiority of this approach over supervised training.

关键词： Model compression Generalization

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 << < 77 78 79 80 81 82 83 84 85 86 > >>

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：