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

16,564 篇 会议
215 篇 期刊文献

馆藏范围

16,779 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

10,867 篇 工学
- 7,725 篇 计算机科学与技术...
- 4,148 篇 电气工程
- 3,544 篇 软件工程
- 3,193 篇 信息与通信工程
- 1,022 篇 控制科学与工程
- 815 篇 电子科学与技术（可...
- 614 篇 生物医学工程（可授...
- 478 篇 机械工程
- 474 篇 仪器科学与技术
- 458 篇 光学工程
- 303 篇 动力工程及工程热...
- 254 篇 生物工程
- 185 篇 交通运输工程
- 167 篇 航空宇航科学与技...
- 158 篇 网络空间安全
- 124 篇 材料科学与工程（可...
- 114 篇 石油与天然气工程
2,782 篇 理学
- 1,609 篇 数学
- 1,138 篇 物理学
- 413 篇 统计学（可授理学、...
- 295 篇 生物学
- 160 篇 系统科学
- 132 篇 化学
1,776 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
877 篇 管理学
- 608 篇 管理科学与工程(可...
- 323 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
1,749 篇 image coding
1,244 篇 image compressio...
1,138 篇 video compressio...
901 篇 point cloud comp...
648 篇 three-dimensiona...
571 篇 encoding
531 篇 compression
508 篇 transform coding
504 篇 decoding
450 篇 data mining
414 篇 compression algo...
370 篇 bandwidth
341 篇 video coding
268 篇 training
256 篇 streaming media
248 篇 computer science
245 篇 deep learning
239 篇 data models
233 篇 discrete cosine ...

机构

25 篇 univ chinese aca...
24 篇 tsinghua univers...
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

16,034 篇 英文
597 篇 其他
116 篇 中文
28 篇 土耳其文
3 篇 俄文
1 篇 西班牙文

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

共 16779 条记录，以下是961-970 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：

Unsupervised 4D LiDAR Moving Object Segmentation in Stationary Settings with Multivariate Occupancy Time Series 23

Unsupervised 4D LiDAR Moving Object Segmentation in Stationa...

引用

23rd ieee/CVF Winter conference on Applications of Computer Vision (WACV)

作者： Kreutz, Thomas Muehlhaeuser, Max Guinea, Alejandro Sanchez Tech Univ Darmstadt Telekooperat Lab Darmstadt Germany

ISBN: (纸本)9781665493468

In this work, we address the problem of unsupervised moving object segmentation (MOS) in 4D LiDAR data recorded from a stationary sensor, where no ground truth annotations are involved. Deep learning-based state-of-the-art methods for LiDAR MOS strongly depend on annotated ground truth data, which is expensive to obtain and scarce in existence. To close this gap in the stationary setting, we propose a novel 4D LiDAR representation based on multivariate time series that relaxes the problem of unsupervised MOS to a time series clustering problem. More specifically, we propose modeling the change in occupancy of a voxel by a multivariate occupancy time series (MOTS), which captures spatio-temporal occupancy changes on the voxel level and its surrounding neighborhood. To perform unsupervised MOS, we train a neural network in a self-supervised manner to encode MOTS into voxel-level feature representations, which can be partitioned by a clustering algorithm into moving or stationary. Experiments on stationary scenes from the Raw KITTI dataset show that our fully unsupervised approach achieves performance that is comparable to that of supervised state-of-the-art approaches.

关键词： Point cloud compression Computer vision Laser radar Annotations Time series analysis Neural networks Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Lung Image Segmentation and compression Using Deep Learning

Lung Image Segmentation and Compression Using Deep Learning

引用

2024 International conference on Advances in Computing Research on Science Engineering and Technology, ACROSET 2024

作者： Tiwari, Puneet Phulre, Sunil Lnct University Bhopal Department of Computer Science & Engineering India

ISBN: (纸本)9798350388800

Lung image compression and segmentation are essential diagnostic and monitoring techniques for a variety of respiratory ailments. We present a novel deep learning-based technique for segmenting and compressing lung images in this paper. To ascertain lung sections precisely in medical images, it is imperative to initially train a convolutional neural network (CNN) model. By understanding intricate patterns and features present in lung images, the CNN model is designed to identify and extract certain lung regions. This segmentation process saves medical staff a great deal of time and reduces the possibility of human error by eliminating the need for manual annotation. Following segmentation, lung image storage requirements are reduced without compromising diagnostic quality by employing a deep learning-based compression technique. The compression model's goal is to remove irrelevant and uninformative content while extracting the most important information. By employing deep learning, our compression technique achieves notable compression ratios while preserving essential information for accurate diagnosis. We conducted extensive trials with many lung imaging datasets to evaluate our proposed approach. When compared to traditional image processing methods, the results demonstrate increased segmentation accuracy and compression efficiency. We assessed the effectiveness of our method using several metrics, such as the compression ratio, mean squared error and coefficient of rolls. The proposed architecture for lung image segmentation and compression has great promise for enhancing respiratory illness identification and treatment. When segmentation is automated and lung picture compression is done rapidly, medical data may be sent, stored, and analyzed more efficiently, leading to better healthcare outcomes. © 2024 ieee.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Efficient Privacy-Preserving Federated Learning with Byzantine Robustness

Efficient Privacy-Preserving Federated Learning with Byzanti...

引用

2024 ieee International conference on Cognitive Computing and Complex data

作者： Jin, Chunhua Li, Lulu Wang, Jiahao Sun, Youwang Jin, Ying Chen, Guanhua Huaiyin Inst Technol Fac Comp & Software Engn Huaian Peoples R China

ISBN: (纸本)9798350352900;9798350352894

Federated learning is a distributed machine learning paradigm. It entails training a global model across diverse organizations while ensuring privacy constraints are upheld. Despite its promising potential, challenges arise when adversaries attempt to infer private information from exchanged parameters or compromise the global model. Although the development of multiple protocols to mitigate security threats, safeguarding the privacy of individual participants while countering Byzantine adversaries remains a challenge. Furthermore, the frequent transmission of gradients between the master server and participants results in significant c ommunication overhead, thereby limiting the training efficiency o f f ederated l earning. In this study, We propose an efficient p rivacy-preserving federated learning scheme with Byzantine robustness (EFL-PB). For privacy protection and Byzantine robustness, we propose a novel aggregation strategy based on the multi-message shuffle protocol in differential privacy. For enhancing communication efficiency, we develop an adaptive gradient compression scheme. Theoretical analysis demonstrates that our multi-message shuffle protocol can satisfy differential privacy. Experimental results on the MNIST, FashionMNIST, and CIFAR-10 datasets validate the robustness and efficiency o f t he E FL-PB s cheme. A s w ell, t he EFL-PB scheme exhibits strong performance on non-iid datasets.

关键词： fedetated learning differential privacy byzantine robustness adaptive gradient compression

来源：评论

学校读者我要写书评

暂无评论

Throughput Optimization with a NUMA-Aware Runtime System for Efficient Scientific data Streaming

Throughput Optimization with a NUMA-Aware Runtime System for...

引用

2023 International conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023

作者： Jamil, Hasibul Chung, Joaquin Bicer, Tekin Kosar, Tevfik Kettimuthu, Rajkumar New York United States Argonne National Laboratory IL United States

ISBN: (纸本)9798400707858

With the surge in data generation rates from advanced scientific instruments, there is an urgent need for effective network management and resource utilization strategies for data streaming. Present strategies often lag behind hardware advancements, leading to resource underutilization. Modern servers typically employ non-uniform memory access (NUMA) multiprocessors, which, despite their benefits, can pose performance challenges. This paper presents a novel runtime system tailored for efficient multi-stream data management, optimizing both its compression and decompression phases, and enhancing network I/O based on the server's unique hardware design. Our system coordinates parallel tasks for data compression, decompression, and transfer, aiming to reduce network data influx. Empirical tests show that aligning streaming tasks with the right NUMA domain results in a 1.48X throughput boost compared to cutting-edge methods and a 2.6X improvement over standard techniques. © 2023 ACM.

关键词： data compression

来源：评论

学校读者我要写书评

暂无评论

Reprojection methods for Koopman-based modelling and prediction 62

Reprojection methods for Koopman-based modelling and predict...

引用

62nd ieee conference on Decision and Control (CDC)

作者： van Goor, Pieter Mahony, Robert Schaller, Manuel Worthmann, Karl Australian Natl Univ Sch Engn Syst Theory & Robot Grp Canberra Australia Tech Univ Ilmenau Inst Math Optimizat Based Control Grp Ilmenau Germany

ISBN: (纸本)9798350301243

Extended Dynamic Mode Decomposition (eDMD) is a powerful tool to generate data-driven surrogate models for the prediction and control of nonlinear dynamical systems in the Koopman framework. In eDMD a compression of the lifted system dynamics on the space spanned by finitely many observables is computed, in which the original space is embedded as a low-dimensional manifold. While this manifold is invariant for the infinite-dimensional Koopman operator, this invariance is typically not preserved for its eDMD-based approximation. Hence, an additional (re-)projection step is often tacitly incorporated to improve the prediction capability. We propose a novel framework for consistent reprojectors respecting the underlying manifold structure. Further, we present a new geometric reprojector based on maximum-likelihood arguments, which significantly enhances the approximation accuracy and preserves known finite-data error bounds.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Virtual Machine Migration Technique for Cloud Computing 15

Optimizing Virtual Machine Migration Technique for Cloud Com...

引用

15th International conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Singh, Davinder Paul Kumar, Divesh Prajapati, Harshad N. Sivaraman, R. Dwivedi, Meenakshi Das, Nripendra Narayan Pandit Deen Dayal Energy University School of Technology Dept. of Cse Gujarat Gandhinagar India Graphic Era Hill University Department of Ece Uttarakhand Dehradun India Sankalchand Patel University Scjp College of Computer Studies Gujarat Visnagar India D.G. Vaishnav College Department of Mathematics Chennai India M.J.P. Rohilkhand University Department of Education Bareilly India Manipal University Jaipur Department of Information Technology India

ISBN: (纸本)9798350370249

Virtual Machine (VM) migration in cloud environments is essential for maintaining high availability, load balancing, and efficient resource utilization. Pre-copy VM migration, a prevalent technique, often faces challenges like high data transfer volumes, extended migration times, and noticeable downtime. This study proposed a compression-based pre-copy VM migration technique that employs Characteristic-Based compression (CBC) to address these challenges. Our approach significantly reduces data transferred by analyzing and compressing memory pages based on their characteristics, thereby decreasing total migration time and minimizing service disruption. Experimental results demonstrate that our technique outperforms traditional pre-copy methods by reducing data transfer by up to 69% and migration time by 33.33% while diminishing downtime by 4 2%. © 2024 ieee.

关键词： Cloud computing compression hypervisor virtualization VM migration

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms for Secure and Efficient compression of Genomic Sequence data 3

Deep Learning Algorithms for Secure and Efficient Compressio...

引用

3rd ieee International conference on Technology, Engineering, Management for Societal Impact using Marketing, Entrepreneurship and Talent, TEMSMET 2023

作者： Gudodagi, Raveendra Thirumala Akash, K. Ahmed, Mohammed Riyaz REVA University School of Electronics and Communication Engineering Bangalore560064 India

ISBN: (纸本)9798350397819

The idea that DNA encodes the human body is uncontested. Everything about a person, including behaviour and physical characteristics, is influenced by genetic information. Genomic data is a rich source of information when it is analysed, genomic data has a significant potential for use in disease diagnosis. Despite the fact that One size does not fit all, the medical advice is usually generic. The intelligent machine may provide us with additional human body knowledge on the contrary to build intelligent robots. The ongoing development of genomic data is either beneficial for engineering as well as medical research. Our search for personalised medicine may have a solution in the overlapping fields of engineering and medicine. The introduction of new emergent multimedia applications with an increase in demand and consumption of genetic data, as well as the invasion of digital media into every aspect of diagnosis and prognosis, are compelling new challenges for next-generation sequencing. The processing of genomic data is intended to meet hitheito unrecognised requirements, including compression, robustness, security, unambiguity, and the prediction of future anomalies, in addition to delivering individualised treatment. Deep neural network based deep learning has been intensively researched in recent years as one of the possible methods for overcoming these difficulties. Because digital data must be maintained effectively, with very high quality, and shouldn't be easily modified by computer standards. The goal is to develop a safe genome compression method that significantly outperforms existing sequencing methods in terms of all performance parameters. © 2023 ieee.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Onboard Science data Retrieval Algorithms on the Snapdragon Platform

Benchmarking Onboard Science Data Retrieval Algorithms on th...

引用

ieee Aerospace conference

作者： Lightholder, Jack Donitz, Benjamin Castillo-Rogez, Julie Sheldon, Douglas CALTECH Jet Prop Lab 4800 Oak Grove Dr Pasadena CA 91109 USA

ISBN: (纸本)9781665490320

The coming decade of planetary missions will have stringent data requirements. Optimizing limited bandwidth is a major motivation for the use of onboard science data analysis algorithms for deep space missions. Under the traditional mission operations paradigm, all data is sent to Earth before follow-on activities are planned by ground operators. This operational model creates challenges for time and bandwidth constrained mission events. The Near Earth Asteroid Scout (NEAScout) mission is a prime example of a mission with these challenges. NEAScout is an interplanetary CubeSat manifested on Artemis-1. The mission will use a solar sail to navigate to a Near Earth asteroid and perform flyby reconnaissance imaging. Vehicle size, configuration, trajectory and distance from Earth all impose bandwidth constraints. To minimize these limitations, the Project decided to move image processing capabilities onboard the spacecraft. This onboard science software enables image calibration, image coaddition, image subtraction, data compression, downsampling and cropping all onboard the spacecraft. The goal is to reduce the data downlink, without compromising science contents. NEAScout utilizes the SPHINX computing platform, whose processing performance is akin to the RAD750, but tailored for CubeSat resources. Although sufficient to enable these sorts of algorithms, the SPHINX takes multiple minutes per image, which diminishes the prospect of using image content for rapid response reasoning. This effort ported, characterized and benchmarked the performance of the NEAScout science software on the Snapdragon platform, a next-generation higher performing processor. Between 10x and 200x processing time speedup was achieved, depending on the image processing algorithm, with a 50x speedup for a notional image processing pipeline. This work highlights new performance baselines for onboard science data processing algorithms which missions could expect to achieve with modern computing hardw

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Generalizable Communication: Beyond the Information Bottleneck 59

Multi-Task Generalizable Communication: Beyond the Informati...

引用

59th Annual ieee International conference on Communications (ieee ICC)

作者： Leung, Cheuk Ting Ghosh, Rohan Motani, Mehul Natl Univ Singapore Dept Elect & Comp Engn Singapore Singapore N1 Inst Hlth Inst Digital Med Inst Data Sci Singapore Singapore

ISBN: (纸本)9781728190549

Conventional communication systems focus on recovering the messages sent by the transmitter at the receiver, by undoing the errors introduced by the channel. In semantic communication, the goal is instead to preserve the semantics (i.e., meaning) of the intended message X. A well-known framework adopted by the literature in modelling semantic communication is task-oriented communication. There, an encoder generates a feature representation Z (e.g., a trained neural network) to transmit across the channel to fulfill a certain task (e.g., classification with labels Y). This naturally leads to the study of the information bottleneck (IB) principle - which proposes reducing the mutual information I(X;Z) (compression) while simultaneously maximizing I(Z;Y) (fitting). Although this objective seems initially meaningful, we posit that both the standard task-oriented setting for studying semantic communication and the IB approach may not be optimal. In this paper, we first propose a novel paradigm of multi-task generalizable communication, where, at test time, the messages may originate from a different unseen classification task compared to those during training. We intuitively reason that the multi-task generalizable setting is more feasible and relevant in the context of real-world semantic communication, compared to task-oriented communication. Next, we propose a Reconstruction Loss Aware (RLA) approach, which yields better feature encodings that are more generalizable towards unseen tasks. We empirically observe that, in the proposed paradigm, the IB principle is not optimal. We also demonstrate that RLA is better (15%-20% higher accuracy) compared to a benchmark approach for task-oriented communication, for diverse nonoverlapping unseen tasks.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Optimizing Real-Time ECG data Transmission in Constrained Environments

Optimizing Real-Time ECG Data Transmission in Constrained En...

引用

ieee International conference on Communications (ICC)

作者： Ouda, Hebatalla Badr, Ahmed Rashwan, Abeulmonem Hassanein, Hossam S. Elgazzar, Khalid Ontario Tech Univ Oshawa ON Canada Queens Univ Kingston ON Canada

ISBN: (数字)9781538683477

ISBN: (纸本)9781538683477

ECG monitoring systems have a significant role in detecting cardiovascular diseases and reducing the rate of sudden cardiac deaths. One of the critical factors to support real-time ECG tracking is to guarantee monitoring system availability. Hence, this work targets battery life expansion for a 12 Lead ECG patch. ECG patch operational hours are extended by reducing Bluetooth Low Energy (BLE) communication airtime, hence reducing the overall transmission power and extending the battery life. Huffman, delta, and base-delta compression techniques are implemented on a Texas Instruments CC2650 Microcontroller Unit using different sampling rates and cardiac conditions such as normal, ventricular tachycardia, and ventricular fibrillation state. The performance of each encoding algorithm is evaluated in terms of compression ratio, the execution time, and power consumption of the ECG patch. Our findings show that the base-delta encoding technique outperforms other techniques and achieves 70% data compression on normal ECG data, 41% on ventricular fibrillation, and 44% on ventricular tachycardia. The execution time of base-delta encoding takes less than 25 ms execution time and saves up to 36 % of the power consumption on the MCU environment.

关键词： Power demand Target tracking Fibrillation data compression Electrocardiography Encoding Real-time systems

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 << < 93 94 95 96 97 98 99 100 101 102 > >>

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：