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

37,345 篇 会议
6,886 篇 期刊文献
2 篇 学位论文
1 册 图书

馆藏范围

44,234 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

15,235 篇 工学
- 10,564 篇 电气工程
- 3,828 篇 计算机科学与技术...
- 3,104 篇 信息与通信工程
- 1,612 篇 控制科学与工程
- 1,557 篇 仪器科学与技术
- 889 篇 电子科学与技术（可...
- 767 篇 机械工程
- 703 篇 软件工程
- 446 篇 航空宇航科学与技...
- 397 篇 测绘科学与技术
- 344 篇 生物医学工程（可授...
- 150 篇 交通运输工程
- 90 篇 材料科学与工程（可...
- 87 篇 网络空间安全
- 72 篇 石油与天然气工程
- 51 篇 土木工程
- 49 篇 生物工程
- 48 篇 船舶与海洋工程
- 47 篇 光学工程
2,757 篇 理学
- 1,325 篇 物理学
- 904 篇 系统科学
- 317 篇 数学
- 161 篇 地球物理学
- 53 篇 化学
- 44 篇 生物学
790 篇 医学
- 568 篇 临床医学
- 182 篇 基础医学(可授医学...
393 篇 管理学
- 385 篇 管理科学与工程(可...
73 篇 文学
- 73 篇 新闻传播学
72 篇 农学
- 45 篇 作物学
28 篇 军事学
18 篇 教育学
17 篇 艺术学
2 篇 经济学
2 篇 法学

主题

44,234 篇 signal processin...
9,110 篇 signal processin...
5,947 篇 estimation
5,144 篇 field programmab...
4,768 篇 algorithm design...
4,451 篇 clocks
4,386 篇 ofdm
4,106 篇 modulation
3,956 篇 filtration
3,841 篇 digital signal p...
2,820 篇 hardware
2,492 篇 convergence
1,822 篇 array signal pro...
1,695 篇 feature extracti...
1,669 篇 optimization
1,636 篇 signal to noise ...
1,632 篇 computer archite...
1,551 篇 robustness
1,532 篇 speech processin...
1,530 篇 adaptive filters

机构

46 篇 school of inform...
44 篇 department of el...
43 篇 national mobile ...
38 篇 department of el...
38 篇 xidian univ natl...
37 篇 information syst...
34 篇 philips research...
32 篇 univ chinese aca...
32 篇 school of electr...
32 篇 signal processin...
31 篇 beijing inst tec...
31 篇 ibm thomas j. wa...
28 篇 department of el...
27 篇 hendisli&#x011f
26 篇 department of el...
26 篇 school of comput...
25 篇 department of si...
25 篇 tsinghua univers...
24 篇 institute for in...
24 篇 natl univ singap...

作者

40 篇 lei wang
37 篇 wei liu
35 篇 jun wang
32 篇 danilo p. mandic
30 篇 p. pirsch
28 篇 k. egiazarian
27 篇 marc moonen
26 篇 li li
26 篇 eldar yonina c.
24 篇 poor h. vincent
23 篇 sharon gannot
23 篇 t. kailath
23 篇 kailath t
22 篇 ming li
22 篇 walter kellerman...
21 篇 yui-lam chan
21 篇 jian wang
21 篇 jean-christophe ...
21 篇 christian jutten
20 篇 so hing cheung

语言

42,880 篇 英文
1,113 篇 其他
236 篇 中文

检索条件"主题词=Signal Processing Algorithms"

共 44234 条记录，以下是3921-3930 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：

FedDec: Peer-to-peer Aided Federated Learning

FedDec: Peer-to-peer Aided Federated Learning

引用

IEEE Workshop on signal processing Advances in Wireless Communications (SPAWC)

作者： Marina Costantini Giovanni Neglia Thrasyvoulos Spyropoulos Eurecom Sophia Antipolis France Inria Université Côte d’Azur Sophia Antipolis France Technical University of Crete Crete Greece

ISBN: (数字)9798350393187

ISBN: (纸本)9798350393194

Federated learning (FL) has enabled training machine learning models that exploit the data of multiple agents without compromising privacy. However, FL is known to be vulnerable to data heterogeneity, partial device participation, and infrequent communication with the server, which are nonetheless distinctive characteristics of this framework. While much of the literature has tackled these weaknesses using different tools, only a few works have considered inter-agent communication to improve FL’s performance. In this work, we present FedDec, an algorithm that interleaves peer-to-peer communication and parameter averaging between the local gradient updates of FL. We analyze the convergence of FedDec and show that interagent communication alleviates the negative impact of infrequent communication rounds with the server by reducing the dependence on the number of local updates H from O(H 2 ) to O(H). Furthermore, our analysis reveals that the term improved in the bound vanishes quickly the more connected the network is. We confirm the predictions of our theory in numerical simulations, where we show that FedDec converges faster than FedAvg, and that the gains are greater as either H or the connectivity of the network increase.

关键词： Wireless communication Training Performance evaluation Federated learning signal processing algorithms signal processing Prediction algorithms Peer-to-peer computing Servers Convergence

来源：评论

学校读者我要写书评

暂无评论

An Improved Shadow Detection Algorithm Based on Multi-features

An Improved Shadow Detection Algorithm Based on Multi-featur...

引用

signal processing and Intelligent Computing (SPIC), International Conference on

作者： Ruina Wang Shiqing Ren Fang Zhao School of Information Science and Engineering Shenyang Ligong University Shenyang China Guangzhou College of Technology and Business Guangzhou China

ISBN: (数字)9798350368888

ISBN: (纸本)9798350368895

Aiming at the problem of low accuracy of traditional shadow feature-based detection methods, an automatic shadow detection method fusing multiple features is proposed, which combines a multi-scale pyramid, Mean Shift segmentation, and SVM classifier. Firstly, a multi-scale image pyramid is constructed and the images are preprocessed with weighted median filtering to reduce noise and improve image quality. Then, Mean Shift segmentation is performed on all the images to split them into multiple sub-regions, features are extracted for each sub-region and these features and their corresponding labels are put into an SVM classifier for training to obtain the final shaded regions. The method incorporates an image pyramid mechanism, which reduces the image resolution through downsampling operations, decomposes the original image into sub-images at multiple scales while retaining the main information of the image, and improves the accuracy and robustness of the algorithm by increasing the accuracy and robustness of feature extraction. The experimental results show that the proposed shadow detection method obtains good performance and has a wide range of applications.

关键词： Support vector machines Image quality Image segmentation Accuracy Image resolution Noise signal processing algorithms Lighting Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

Autonomous Ground Vehicle Navigation with GNSS/5G Integration

Autonomous Ground Vehicle Navigation with GNSS/5G Integratio...

引用

IEEE International Conference on Information Communication and signal processing (ICICSP)

作者： Jun Yu Yuan Zhang College of Electronics and Information Engineering Tongji University Shanghai China

ISBN: (数字)9798350355895

ISBN: (纸本)9798350355901

In this paper, we introduce a novel integrated navigation system that merges the capabilities of the global navigation satellite systems (GNSS) and fifth-generation (5G) wireless technology to deliver precise location-based services. Our approach entails the development of an integrated navigation framework adept at addressing nonlinear implicit constraints and multipath environments, resulting in a highly resilient and accurate navigation solution. The framework concurrently assesses the vehicle's position, velocity, and acceleration states, alongside determining the disparity between the dynamic stochastic clock error states (bias and drift) of the vehicle-mounted receiver and the generation Node B (gNB) clock. Within this framework, we propose a practical adaptive iterative extend Kalman filter (AIEKF) method that efficiently manages nonlinear implicit constraints and multipath propagation within a 5G environment. Simulation outcomes demonstrate the superiority of our AIEKF method over the traditional IEKF method, particularly in handling 5G multipath scenarios. Our results underscore that the proposed GNSS/5G method markedly enhances navigation accuracy in both urban junctions and highway scenarios, showcasing a 61.71% and 47.51% reduction in RMSE, respectively, compared to the 5G-only navigation solution.

关键词： Wireless communication Global navigation satellite system Accuracy 5G mobile communication signal processing algorithms Switches Kalman filters Iterative methods Vehicle dynamics Clocks

来源：评论

学校读者我要写书评

暂无评论

Fully Automatic Bayesian Method for Trainable Activation Function and Deep Neural Networks

Fully Automatic Bayesian Method for Trainable Activation Fun...

引用

European signal processing Conference (EUSIPCO)

作者： Mohamed Fakhfakh Lotfi Chaari Toulouse INP IRIT University of Toulouse France

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

In this study, we introduce a novel technique that incorporates an MCMC-based algorithm within a Bayesian framework to estimate the parameters of trainable activation functions and model weights in deep neural networks. This approach aims to enhance network performance by effectively tackling the challenges of parameter learning and reducing the risk of overfitting. Our method leverages an efficient sampling process to accelerate convergence times. The efficacy of the proposed activation function is demonstrated through experiments on two datasets within the remote sensing domain. These experiments reveal that our approach enables neural networks to achieve high levels of accuracy, reaching up to 92%, while keeping the model complexity low. This suggests that the proposed method could offer significant benefits for deep learning applications, particularly in fields requiring precise and reliable predictive modeling.

关键词： Accuracy Computational modeling signal processing algorithms Artificial neural networks signal processing Predictive models Bayes methods Reliability Standards Remote sensing

来源：评论

学校读者我要写书评

暂无评论

On Gradient Based Descent algorithms for Joint Diagonalization of Matrices

On Gradient Based Descent Algorithms for Joint Diagonalizati...

引用

European signal processing Conference (EUSIPCO)

作者： Erik Troedsson Marcus Carlsson Herwig Wendt Centre for Mathematical Sciences Lund University Lund Sweden CNRS IRIT Université de Toulouse Toulouse France

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

Joint diagonalization of collections of matrices, i.e. the problem of finding a joint set of approximate eigenvectors, is an important problem that appears in many applicative contexts. It is commonly formulated as finding the minimizer, over the set of all possible bases, for a certain non-convex functional that measures the size of off-diagonal elements. Many approaches have been studied in the literature, some of the most popular ones working with approximations of this cost functional. In this work, we deviate from this philosophy and instead propose to directly attempt to find a minimizer making use of the gradient and Hessian of the original functional. Our main contributions are as follows. First, we design and study gradient descent and conjugate gradient algorithms. Second, we show that the intricate geometry of the functional makes it beneficial to change basis at each iteration, leading to faster convergence. Third, we conduct large sets of numerical experiments that indicate that our proposed descent methods yield competitive results when compared to popular methods such as WJDTE.

关键词： Geometry Gradient methods Philosophical considerations signal processing algorithms signal processing Linear programming Size measurement Harmonic analysis Robustness Convergence

来源：评论

学校读者我要写书评

暂无评论

Adaptive Random Fourier Features Gaussian Kernel Normalized LMS Algorithm

Adaptive Random Fourier Features Gaussian Kernel Normalized ...

引用

IEEE International Conference on signal processing, Communications and Computing (ICSPCC)

作者： Wentao Shi Mingqi Jin Yuhao Qiu Wei Gao Lihan Zheng Lianyou Jing Ocean Institute Northwestern Polytechnical University Taicang China School of Marine Science and Technology Northwestern Polytechnical University Xi'an China School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China

ISBN: (数字)9798350366556

ISBN: (纸本)9798350366563

In this paper, we propose an adaptive stochastic Fourier feature Gaussian kernel normalized LMS (ARFF-GKNLMS). Similar to many kernel adaptive filtering algorithms that use stochastic gradient descent, the ARFF-GKNLMS algorithm uses more flexible stochastic Fourier features to reduce computation intensity. The difference is that the algorithm can adjust the inherent core bandwidth online, thereby solving the problem of selecting the core bandwidth in advance to a certain extent. In addition, the ARFF-GKNLMS algorithm has fast convergence performance, low steady-state error and good tracking ability, especially in non-stationary environment with low signal-to-noise ratio or strong noise, which has good robustness and tracking performance. The simulation results show that compared with other kernel adaptive filters with preset core bandwidths, the performance of this method is significantly improved in terms of convergence speed, steady-state error and tracking ability in both transient and steady state.

关键词： Simulation signal processing algorithms Adaptive filters Bandwidth Robustness Steady-state Kernel Transient analysis Convergence signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Fast Fourier Transforms Using Binary Signed Digit Number System

Performance Analysis of Fast Fourier Transforms Using Binary...

引用

International Conference on Power, Energy, Control and Transmission Systems (ICPECTS)

作者： A. Mary Joy Kinol Bommi. R M Uganya G M. Nalini Institute of ECE Saveetha School of Engineering SIMATS Chennai India Department of ECE Chennai Institute of Technology Chennai India Department of Electronics and Communication Eengineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of EIE Sri Sairam Engineering College Chennai India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508852

It is a very efficient way to implement the Fast Fourier Transform (FFT) and is in use for various applications, such as radar communication, biomedical signal processing, and multicarrier modulation systems. A butterfly step can be implemented as a repetitive multiplier followed by an adder of complex numbers. The current work has made an enormous effort to improve the speed and computational complexity of arithmetic operations occurring inside the butterfly unit by a detailed investigation of different adders and multipliers. A new method to design adder and multiplier for the computation of butterfly is proposed, in which the carry propagation is directed out effectively through a format Binary Signed Digit (BSD). When such two unit results were compared, it was found that the BSD based floating-point butterfly performs much better, giving considerable gains in processing speed and efficiency.

关键词： Performance evaluation Power demand Fast Fourier transforms signal processing algorithms Throughput Radar signal processing Radar applications Power dissipation Adders Arithmetic

来源：评论

学校读者我要写书评

暂无评论

Distributed MIMO Two-Coordinate Radar signal-Level Fusion Algorithm Based on Dynamic Programming

Distributed MIMO Two-Coordinate Radar Signal-Level Fusion Al...

引用

International Conference on signal processing Proceedings (ICSP)

作者： Zhengshuai An Feilin Qi Jue Wang Yuan Tian Xi'an Research Institute of Navigation Technology Xi'an China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Distributed MIMO radar cooperative detection system has the advantages of anti-target RCS fluctuation and high accuracy of parameter estimation, so it has become a research hotspot for scholars at home and abroad in recent years. At present, the distributed MIMO radar cooperative detection information fusion method mainly focuses on the data level, which can effectively improve the stability of target tracking, and can't improve the detection distance of the radar. In view of the above shortcomings, this paper proposed a distributed MIMO two-coordinate radar signal-level fusion algorithm based on dynamic programming. Firstly, the orthogonal matched filtering is used for separating different channels data from the radar echo signals, and the signals among different channels received by a single radar are respectively processed, which completes the Doppler filtering, space coordinate transformation and non-coherent integration based on dynamic programming between different channels. Then, the processed result of each radar is transmitted to fusion center to further realize the secondary non-coherent integration between multiple radars by using dynamic programming and then achieve the target detection, which can greatly improve the SNR to achieve effective detection of low observable targets. Finally, the performance of the two-stages non-coherent signal-level fusion integration algorithm proposed in this paper is theoretically analyzed. Simulations show the robustness and feasibility of the algorithm.

关键词： Radar cross-sections Heuristic algorithms MIMO radar Spaceborne radar signal processing algorithms Radar detection Robustness Doppler radar Dynamic programming signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

GM-LPC Based Multiband Analysis and Enhancement of Pathological Voice

GM-LPC Based Multiband Analysis and Enhancement of Pathologi...

引用

International Symposium on Chinese Spoken Language processing

作者： Yaqin Wu Yan Chang Yanzhang Geng Xiaofeng Cao Jiawei Zhao Software College Shanxi Agricultural University Taigu School of Electrical Automation and Information Engineering Tianjin University Tianjin

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

An automated method for enhancing and repairing pathological voice can be considered a potential clinical tool in healthcare. Aiming to improve the intelligibility of pathological voices, this paper designs and implements a multi-band analysis and enhancement algorithm based on Gammatone Mean cosine similarity-Linear Predictive Coding (GM-LPC). First, the Gammatone filter bank is employed to simulate the auditory characteristics of human ears for multi-band analysis, achieving hierarchical frequency division processing of voice data. Then, MCS parameters are introduced to quantitatively measure the differences between normal and pathological voice spectra and track the changes in the pathological voice spectrum. Finally, The LPC analysis method is used to cross-synthesize voice signals with normal voice as a reference, completing the enhancement process and better preserving the individual voice characteristics of patients. The experiment demonstrates that the algorithm presented in this paper achieves objective evaluation scores of 0.570 and 2.913 for STOI and PESQ, respectively. Subjective analysis from the perspectives of time-domain and frequency-domain shows that the enhanced voice signal has less distortion, exhibits more concentrated and clear spectral characteristics, and significantly improves the quality of the voice signal.

关键词： Pathology Machine learning algorithms signal processing algorithms Filter banks Medical services Predictive coding Prediction algorithms Time-domain analysis Speech processing Spectrogram

来源：评论

学校读者我要写书评

暂无评论

A Reversible Data Hiding Scheme for ECG signals Using CNN-PEE

A Reversible Data Hiding Scheme for ECG Signals Using CNN-PE...

引用

Intelligent signal processing and Effective Communication Technologies (INSPECT), IEEE International Conference on

作者： Mohammad Okasha Anjum Siddharth Bhalerao Irshad Ahmad Ansari Department of Information Technology ABV-Indian Institute of Information Technology and Management Gwalior India Department of Computer Science and Engineering Gyan Ganga Institute of Technology and Sciences Jabalpur India Department of Electrical and Electronics Engineering ABV-Indian Institute of Information Technology and Management Gwalior India

ISBN: (数字)9798350379525

ISBN: (纸本)9798350379532

The security of biomedical signals is the highest priority of any medical or clinical setup. The electrocardiogram (ECG) signals are very crucial in assessing heart health and their security is of utmost importance. A reversible data hiding scheme based on prediction error expansion (PEE) has been proposed in this work. The patient's personal data acts as a watermark and is embedded in the ECG signal. A 1D CNN based predictor has been used to obtain the sample predictions. The signals obtained from the MIT-BIH arrhythmia dataset have been utilized for training and testing the CNN model. The CNN-based predictor ensures superior performance and a high value of performance parameters.

关键词： Training Heart signal processing algorithms Watermarking Electrocardiography signal processing Prediction algorithms Communications technology Classification algorithms Testing

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 << < 389 390 391 392 393 394 395 396 397 398 > >>

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：