检索结果-内蒙古大学图书馆

European Signal Processing Conference

作者： Silviu Ciochina Constantin Paleologu Jacob Benesty Steven L. Grant Andrei Anghel University Politehnica of Bucharest INRS-EMT University of Quebec Missouri University of Science and Technology

ISBN: (纸本)9781509018918

The performance of the least-mean-square (LMS) algorithm is governed by its step-size parameter. In this paper, we present a family of optimized LMS-based algorithms (in terms of the step-size control), in the context of system identification. A time-variant system model is considered and the optimization criterion is based on the minimization of the system misalignment. Simulations performed in the context of acoustic echo cancellation indicate that these algorithms achieve a proper compromise in terms of fast convergence/tracking and low misadjustment.

关键词： System identification optimal criterion step size acoustic echo cancellation dimension control family algorithms maladjustment least mean square algorithm

来源：评论

学校读者我要写书评

暂无评论

Variable step-size strategy for distributed parameter estimation of compressible systems in WSNs

Variable step-size strategy for distributed parameter estima...

引用

IEEE International Workshop on Computer-Aided Modeling, Analysis, and Design of Communication Links and Networks, CAMAD

作者： Muhammad Omer Bin Saeed Azzedine Zerguine Muhammad Saqib Sohail Saad Rehman Waleed Ejaz Alagan Anpalagan College of E&ME National Uni. of Sciences & Tech. Pakistan King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia. Hong Kong University of Sciences & Tech. Kowloon Hong Kong. College of E&ME National Uni. of Sciences & Tech. Rawalpindi Pakistan. Ryerson University Toronto Canada.

ISBN: (纸本)9781509025596

The Internet of Things (IoT) paradigm depends on sensor networks to collect data and perform information processing as well as communication tasks to attain a common goal. This work presents the formulation and analysis of a sparsity-based variable step-size distributed least-mean-square algorithm based on the diffusion cooperation scheme in wireless sensor networks. In particular, the scheme is applied to compressible systems of which the sparse systems are a special case. The performance of the algorithm is assessed for compressible systems in comparison with existing algorithms in order to showcase the superiority of the proposed algorithm. The proposed scheme is then applied to diffusion-based wireless sensor networks for estimating a compressible system and steady-state analysis is carried out for the proposed scheme.

关键词： wireless sensor networks cooperative communication Internet of Things least mean squares methods parameter estimation Parameter estimation least squares method Wireless sensor networks Internet of things cooperative communication compressible step size least mean square algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive Iterative Control for Road Simulation Using the Frequency Domain Filtered-X LMS algorithm

Adaptive Iterative Control for Road Simulation Using the Fre...

引用

International Conference on Multimedia Systems and Signal Processing (ICMSSP)

作者： Zhang Yanyan Yang Zhidong School of Mechatronics Engineering Harbin Institute of Technology Harbin China

ISBN: (纸本)9781509045204

For a hydraulic or electro-dynamic shaker test rig, the goal of the iterative control is to reproduce the structural deformations of vehicles, measured under normal operating conditions for a vehicle driven on public roads or test tracks. The approach is based on the correct calculation of the excitation signals applied to the actuators of the multi-axis test rig. The conventional iterative control approach adjusts drive waveforms according to the particular Frequency Response Function (FRF) matrix, measured prior to the test and fixed. To ensure the system stability, the feedback gain should be small, which will lead to a very slow convergence rate. To overcome these defects, an adaptive inverse model based on the filtered-X least mean-square (LMS) algorithm is proposed to continuously improve the identification precision of the inverse characteristic of the FRF, which is called the impedance function of the system under test. And the frequency domain LMS algorithm is introduced to make sure the inverse characteristic is not critical to the iterative gain and thus allow for a bigger feedback gain. The experimental results indicate that the adaptive control strategy can not only solve the system instability problem arising from the improper feedback gain selection in the conventional iteration process, but also has the higher convergence rate.

关键词： adaptive control feedback frequency response iterative methods least mean squares methods matrix algebra road vehicles stability least squares method road vehicles matrix algebra adaptive control iterative methods frequency response least mean square algorithm feedback gain frequency response function impedance function Feedback Land transportation Iterative Gonadotropin-Releasing Hormone excitation signal

来源：评论

学校读者我要写书评

暂无评论

Spectrum handoff based on adaptive weights adjustment

引用

IET COMMUNICATIONS 2015年第5期9卷 674-680页

作者： Zhao Zhi-jin Zhang Lu-ping Wang Hai-quan Hangzhou Dianzi Univ Sch Telecommun Engn Hangzhou 310018 Zhejiang Peoples R China China Elect Technol Corp State Key Lab Informat Control Technol Commun Syst Res Inst 36 Jiaxing 314001 Zhejiang Peoples R China

Spectrum handoff is one of key technologies of cognitive radio. A spectrum handoff strategy based on adaptive weights adjustment is proposed, considering the effect of secondary users' (SUs) transmission power, fading factor, bandwidth and channel availability on the target channel selecting. According to the principle of multi-attribute simple additive weight algorithm (MA-SAW), the expected effect function of each channel is obtained by analysis. Making full use of the change of the various factors in cognitive wireless network, the LMS adaptive algorithm of dynamic weights is put forward. Finally, the dynamic weights are applied to MA-SAW, to determine target channel to switch. The simulation results show that the proposed algorithm can reduce the switching times of SUs, and improve the effective transmission rate.

关键词： cognitive radio mobility management (mobile radio) radio spectrum management radio networks fading channels least mean squares methods adaptive weight adjustment cognitive radio SU power transmission spectrum handoff strategy secondary user bandwidth availability channel fading factor target channel selection multiattribute simple additive weight algorithm cognitive wireless network LMS adaptive algorithm dynamic weight MA-SAW least mean square algorithm

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of least mean square Sample Matrix Inversion algorithm for Smart Antenna System

Performance Analysis of Least Mean Square Sample Matrix Inve...

引用

Loughborough Antennas and Propagation Conference (LAPC)

作者： Ali, Weal A. E. Mohamed, Darwish A. E. Hassan, Adel H. G. Arab Acad Sci & Technol Dept Elect & Commun Engn Alexandria Egypt

ISBN: (纸本)9781479900916

Beamforming is a signal processing technique that has the ability to direct the main beam toward signal-of-interest and the null toward signal-of-not-interest without moving antenna array. This technique is achieved by using algorithms which change the amplitude and phase of array pattern continuously. This paper presents hybrid algorithm that is a combination of two algorithms, least mean square algorithm and sample matrix inversion algorithm. The hybrid algorithm (least mean square/sample matrix inversion) is applied on an array of dipoles to overcome the shortcomings of existing algorithms for a robust smart antenna system. To focus the main beam toward the desired direction and place the null in the direction of the interference signals, the weights of the inversion matrix in sample matrix inversion are calculated and these weights will be the initial weights in least mean square algorithm. The merit of this approach solves the convergence speed problem of the least mean square algorithm as well as the computation intensive exists in sample matrix inversion algorithm and decreases the least mean square error. The simulation results indicate the analyses of least mean square, sample matrix inversion and hybrid algorithm performances. These techniques are compared and verified using MATLAB.

关键词： smart antenna least mean square algorithm sample matrix inversion algorithm Beamforming

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Adaptive IIR Filter Using Sign algorithm in LabVIEW 2

Performance Analysis of Adaptive IIR Filter Using Sign Algor...

引用

2nd International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Sharma, Divya Kaur, Rashpinder Chitkara Univ Rajpura India

ISBN: (纸本)9789380544168

In real time adaptive filter applications, the realization of adaptive filtering algorithms on hardware devices such as digital signal processing targets, FPGA devices, and application-specific integrated circuits (ASICs) is required. These devices need a clarified description of the standard LMS algorithm. This paper presents the execution of adaptive IIR filter using Sign least mean square algorithm in LabVIEW. The responses are obtained to compare the functioning of the sign algorithm with least mean square algorithm and normalized least mean square algorithm. The results show that Sign LMS algorithm has moderate rate of convergence with small steady state errors.

关键词： Adaptive IIR Filter Convergence Speed LabVIEW mean squared error least mean square algorithm Sign LMS algorithm

来源：评论

学校读者我要写书评

暂无评论

Learning architectures with enhanced capabilities and easier training 19

Learning architectures with enhanced capabilities and easier...

引用

19th IEEE International Conference on Intelligent Engineering Systems (INES)

作者： Wilamowski, Bogdan M. Korniak, Janusz Auburn Univ Auburn AL 36849 USA Univ Informat Technol & Management Rzeszow Poland

ISBN: (纸本)9781467379397

Although discovery of the Error Back Propagation (EBP) learning algorithm was a real breakthrough, this is not only a very slow algorithm, but it also is not capable of training networks with super compact architecture. The most noticeable progress was done with an adaptation of the LM algorithm to neural network training. The LM algorithm is capable of training networks with 100 to 1000 fewer iterations, but the size of the problems are significantly limited. Also, the LM algorithm was adopted primarily for traditional MLP architectures. More recently two new revolutionary concepts were developed: Support Vector Machine and Extreme Learning Machines. They are very fast, but they train only shallow networks with one hidden layer. It was shown that these shallow networks have very limited capabilities. It has already demonstrated much higher capabilities of super compact architectures having 10 to 100 times more processing power than commonly used learning architectures For example, such a shallow MLP architecture with 10 neurons can solve only a Parity-9 problem, but a special deep FCC (Fully Connected Cascade) architecture with the same 10 neurons can solve as large a problem as a Parity-1023. Unfortunately, with the vanishing gradient problem], deep architectures are very difficult to train. By introducing additional connections across layers it was possible to efficiently train deep networks using the powerful NBN algorithm. Our early results show that there is a solution for this difficult problem.

关键词： backpropagation neural nets support vector machines EBP learning algorithm FCC architecture LM algorithm MLP architecture NBN algorithm error back propagation learning algorithm extreme learning machine fully connected cascade architecture learning architecture neural network training support vector machine Artificial neural networks Biological neural networks Computer architecture FCC Neurons Support vector machines Training Support Vector Network least mean square algorithm Biological neural networks Neural network back propagation ARCHITECTURE Computer Architecture Federal Communications Commission (FCC) Functional training Learning machines Artificial neural networks Neurons Training

来源：评论

学校读者我要写书评

暂无评论

MAI Plus Noise-Constrained LMS-based algorithm for MIMO-CDMA DFE Systems 12

MAI Plus Noise-Constrained LMS-based Algorithm for MIMO-CDMA...

引用

International Multi-Conference on Systems, Signals and Devices (SSD)

作者： Mahmood, Khalid Asad, Syed Muhammad Zerguine, Azzedine Moinuddin, Muhammad Elect & Elect Engn Technol Unit Hafar al Batin Saudi Arabia KFUPM Dept Elect Engn Dhahran Saudi Arabia King Abdulaziz Univ Ctr Excellence Intelligent Engn Syst Jeddah Saudi Arabia

ISBN: (纸本)9781479917587

In this work, a decision feedback equaliser (DFE) is implemented based on a constrained least mean square (LMS) algorithm for multiple input multiple output code division multiple access (MIMO-CDMA) systems. The proposed algorithm is equipped with the knowledge of the number of subscribers, the spreading sequence length, the noise variance as well as the variance of the multiple access interference (MAI) plus noise. Unlike previous works, here the MAI is introduced as a constraint as well. The introduction of these two constraints gives the proposed algorithm an excellent performance. Finally, simulation results conducted to support the theoretical findings show that the proposed algorithm outperforms various constrained implementations of the LMS algorithm.

关键词： GSTZ1 gene least mean square algorithm decision feedback equalisers Noise multiple input multiple output systems Variance Code division multiple access CDMA mobile communications Simulation results

来源：评论

学校读者我要写书评

暂无评论

Gradient compared p-LMS algorithms for sparse system identification 27

Gradient compared p-LMS algorithms for sparse system identif...

引用

27th Chinese Control and Decision Conference, CCDC 2015

作者： Feng, Yong Wu, Jiasong Zeng, Rui Luo, Limin Shu, Huazhong School of Biological Science and Medical Engineering Southeast University Nanjing China Laboratory of Image Science and Technology Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China

ISBN: (纸本)9781479970179

In this paper, we propose two novel p-norm penalty least mean square (p-LMS) algorithms as supplements of the conventional p-LMS algorithm established for sparse adaptive filtering recently. A gradient comparator is employed to selectively apply the zero attractor of p-norm constraint for only those taps that have the same polarity as that of the gradient of the squared instantaneous error, which leads to the new proposed gradient compared p-norm constraint LMS algorithm (pGC-LMS). We explain that the pGC-LMS can achieve lower mean square error than the standard p-LMS algorithm theoretically and experimentally. To further improve the performance of the filter, the pNGC-LMS algorithm is derived using a new gradient comparator which takes the sign-smoothed version of the previous one. The performance of the pNGC-LMS is superior to that of the pGC-LMS in theory and in simulations. Moreover, these two comparators can be easily applied to other norm constraint LMS algorithms to derive some new approaches for sparse adaptive filtering. The numerical simulation results show that the two proposed algorithms achieve better performance than the standard LMS algorithm and p-LMS algorithm in terms of convergence rate and steady-state behavior in sparse system identification settings. © 2015 IEEE.

关键词： least mean square algorithm New Gradient Comparator Sparse System Identification p Norm Constraint

来源：评论

学校读者我要写书评

暂无评论

Gradient Compared lp-LMS algorithms for Sparse System Identification

Gradient Compared lp-LMS Algorithms for Sparse System Identi...

引用

第27届中国控制与决策会议

作者： Yong Feng Jiasong Wu Rui Zeng Limin Luo Huazhong Shu School of Biological Science and Medical Engineering Southeast University Laboratory of Image Science and Technology the Key Laboratory of Computer Network and Information IntegrationSoutheast University

ISBN: (纸本)9781479970186

In this paper,we propose two novel p-norm penalty least mean square（l-LMS） algorithms as supplements of the conventional l-LMS algorithm established for sparse adaptive filtering recently.A gradient comparator is employed to selectively apply the zero attractor of p-norm constraint for only those taps that have the same polarity as that of the gradient of the squared instantaneous error,which leads to the new proposed gradient compared p-norm constraint LMS algorithm（lGC-LMS）.We explain that the lGC-LMS can achieve lower mean square error than the standard l-LMS algorithm theoretically and *** further improve the performance of the filter,the lNGC-LMS algorithm is derived using a new gradient comparator which takes the sign-smoothed version of the previous *** performance of the l NGC-LMS is superior to that of the lGC-LMS in theory and in ***,these two comparators can be easily applied to other norm constraint LMS algorithms to derive some new approaches for sparse adaptive *** numerical simulation results show that the two proposed algorithms achieve better performance than the standard LMS algorithm and l-LMS algorithm in terms of convergence rate and steady-state behavior in sparse system identification settings.

关键词： least mean square algorithm p Norm Constraint Sparse System Identification New Gradient Comparator

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：