Variable-step-size LMS algorithm: new developments and experiments

The variable-step-size least-mean-square (VSLMS) algorithm is explored and adopted for tracking of time-varying environments. Two implementations of the VSLMS algorithm are proposed. The emphasis is on implementations sizes with different step sizes at various taps of the adaptive filter. General analysis of the VSLMS algorithm appears to be somewhat involved. However, for one implementation a limited analysis of the algorithm is found possible. For this implementation it is shown that, when the input samples to the adaptive filter are zero-mean, Gaussian and uncorrelated with one another, the VSLMS algorithm can adapt itself to select the optimum set of step sizes which results in the best-tracking performance. Simulation experiments with the VSLMS algorithm show that, under fairly mild conditions, both of the proposed implementations adapt toward the optimum step sizes     

A Gradient-Based Variable Step-Size Scheme for Kurtosis of Estimated Error

This paper proposes a new variable step-size LMS (VSLMS) algorithm with an approach in which a gradient-based weighted average of a kurtosis of an estimated error signal is used to improve the drawback of a previous algorithm for application to an unknown channel estimation. The proposed scheme leads not only to the enhancement of the convergence rate, but also to robustness in terms of low-SNR environments. It could also lead to obtaining a lower misadjustment error.      

The stability of variable step-size LMS algorithms

Variable step-site LMS (VSLMS) algorithms are a popular approach to adaptive filtering, which can provide improved performance while maintaining the simplicity and robustness of conventional fixed step-size LMS. Here, we examine the stability of VSLMS with uncorrelated stationary Gaussian data. Most VSLMS described in the literature use a data-dependent step-size, where the step-size either depends on the data before the current time (prior step-size rule) or through the current time (posterior step-size rule). It has often been assumed that VSLMS algorithms are stable (in the sense of mean-square bounded weights), provided that the step-size is constrained to lie within the corresponding stability region for the LMS algorithm. For a single tap fitter, we find exact expressions for the stability region of VSLMS over the classes of prior and posterior step-sizes and show that the stability region for prior step size coincides with that of fixed step-size, but the region for posterior step-size is strictly smaller than for fixed step-size. For the multiple tap case, we obtain bounds on the stability regions with similar properties. The approach taken here is a generalization of the classical method of analyzing, the exponential stability of the weight covariance equation for LMS. Although it is not possible to derive a weight covariance equation for general data-dependent VSLMS, the weight variances can be upper bounded by the solution of a linear time-invariant difference equation, after appropriately dealing with certain nonlinear terms. For prior step-size (like fixed step-size), the state matrix is symmetric, whereas for posterior step-size, the symmetry is lost, requiring a more detailed analysis. The results are verified by computer simulations     

新的变步长LMS算法在系统辨识中的应用

在分析最小均方误差(LMS)自适应滤波算法和变步长LMS算法的基础上,提出了一种新的变步长算法,该算法用误差的平均值来控制步长的变化,进一步的解决了收敛速度和稳态误差的矛盾。讲述了新算法的具体改进方式,并将该算法和变步长G-SVSLMS算法以及固定步长算法分别应用到系统辨识中,通过MATLAB进行仿真,结果证实文中提出的算法在明显提高收敛速度的同时,并拥有好的稳态误差。     

一种基于误差相关函数的改进变步长LMS算法

最小均方算法的收敛速度和稳态误差之间存在矛盾,为此人们提出了各种变步长LMS算法,其中E-LMS算法是将步长与瞬时误差平方相关联,R-LMS算法是将步长与误差的相关函数相关联。E-LMS算法的抗噪性能较差,在低信噪比条件下性能明显变差,R-LMS算法对突变系统的跟踪能力较差。为此文中给出了一种改进的,基于误差相关函数的VSS-LMS算法,该方法利用E-LMS算法的控制步长策略提高算法的跟踪能力。计算机仿真结果显示,该算法能够同时满足抗噪和跟踪两种要求。     

一种改进的低复杂度变步长LMS算法

改进型的变步长LMS算法在有效抑制瞬时噪声对经典的变步长LMS算法影响的同时,也增加了算法的计算复杂度,提高了其硬件实现的难度。为降低变步长LMS算法的计算复杂度,提出了一种步长改变因子与前后两个时刻误差的乘积成正比的新的变步长LMS改进算法,在不增加计算复杂度的条件下,有效地抑制了瞬时噪声对迭代步长的影响。仿真结果表明,提出的算法和现有的变步长LMS算法收敛速度相当,但其稳态误差更小,计算复杂度也更低,有利于算法的硬件实现。     

基于新型组合算法的语音降噪系统

在研究VSLMS和子空间降噪原理的基础上,分析了两种算法的优缺点,提出了一种组合降噪算法,并进行了硬件实现。组合降噪算法试图寻找一个语音信号的分解点,利用子空间算法分离出带噪信号,作为自适应算法的输入,最后由VSLMS算法对带噪信号进行增强处理。硬件实现在该组合降噪算法的基础上,利用SOPC技术在FPGA芯片中搭建嵌入式语音降噪系统。实验结果表明,该方法能够优于传统降噪算法,使用硬件结构加快了算法的收敛速度。     

Improved variable step-size LMS algorithm based on hyperbolic tangent function

In order to improve that the LMS algorithm for determining step size cannot satisfy both rapid convergence and low steady-state misalignment errors,a variable step size algorithm (IVSSLMS) based on an improved hyperbolic tangent function was proposed.The step size feedback factor and the correlation value of the error signal were used to adjust the step size,and the problems of slow convergence speed and poor anti-noise ability of the fixed-step size algorithm was overcame.The performance and parameters settings of the proposed algorithm were analyzed.The simulation results show that IVSSLMS has a faster convergence rate,lower steady-state error and better system tracking capability than the existing variable step size algorithms under high and low SNR conditions.     

一种改进的变步长LMS自适应算法

传统的最小均方误差(LMS)算法难以同时获取较快的收敛速度和较小的稳态误差,而变步长LMS算法可获得二者之间的平衡。对已有的一些变步长LMS算法进行了分析,在变系数步长(VFSS)算法的基础上,引入输入信号因子,并建立步长因子与误差信号之间新的非线性函数关系,提出一种改进的变步长LMS算法,该算法不仅继承了VFSS算法在低信噪比环境下抗噪声性能好的特点,而且能够快速跟踪系统的变化,仿真结果表明改进算法的性能优于现有算法。     

改进的变步长变换域最小均方算法

变换域是一种在强相关信号输入时加快自适应算法收敛的方法,但仍然存在收敛速度的要求与稳态失调的要求相矛盾的问题。本文在变换域最小均方误差算法（transform domain LMS, TDLMS）的基础上提出了一种改进的变步长方案,其变步长因子受到误差自相关的控制,消除了不相关的观测噪声的影响。本文分别在平稳和非平稳状态下,对算法的收敛和稳态性能进行理论分析,并给出了最佳的算法参数。仿真设置相同的稳态误差,结果表明本文算法在平稳状态下比固定步长的算法提前1300点收敛,在非平稳状态下提前1400点收敛,且与文献中其它变步长的算法相比收敛速度均有提升。      

基于变步长等变化自适应盲源分离算法

对于基于梯度自适应的盲源分离算法，认真选择步长参数以达到好的分离性能是非常必要的。如果为加快收敛速度而增大步长因子，将会导致大的稳态误差，甚至引起算法发散，因此固定步长因子无法解决收敛速度和稳态误差之间的矛盾。本文为EASI算法提出了一种变步长的解决方案。通过建立步长因子与分离矩阵相互差异之间的非线性关系，加快了收敛速度，减小了失调误差。计算机仿真结果与理论分析相一致，证实了该算法明显优于传统的EASI算法。     

一种约束稳定性最小均方噪声对消算法

研究了最小均方误差(LMS)算法、归一化的最小均方(NLMS)算法及变步长NLMS算法在自适应噪声干扰抵消器中的应用,针对目前这些算法在噪声对消器应用中的缺点,将约束稳定性最小均方(CS-LMS)算法应用到噪声处理中,并进一步结合变步长的思想提出来一种新的变步长CS-LMS算法。通过MATLAB进行仿真分析,结果证实提出的算法与其他算法相比,能很好地滤除掉噪声从而得到期望信号,明显的降低了稳态误差,并拥有好的收敛速度。     

一种基于均方偏差分析的通用最小均方算法

无论是传统的定步长还是最近新提出的变步长最小均方(LMS)算法,在处理特定数学特征的信号时需要对算法参数进行先验的估计才能达到较好的效果。但在实际信号处理过程中,算法参数的估计本就是一个很困难的过程。该文分析了LMS算法的均方偏差及收敛特性,并提出一种以相对误差为变量的变步长LMS算法,能够实现步长控制参数的自估计;可以自适应不同数学特征的信号,具体算例表明新算法有更快的收敛速度和较小的均方误差。     

改进变步长LMS算法在系统辨识中的应用及性能分析

提出一种改进的自适应变步长最小均方（LMS）算法,该算法利用e^4（n）和遗忘因子λ（n）共同调整步长,同时具有在初始阶段和未知系统时变阶段自适应步长增大而稳态时步长变小的特点,更好地解决了稳态误差与收敛时间之间的矛盾。将该算法应用到系统辨识中,与一般的变步长算法相比,改进算法具有更快的参数辨识速度和更小的稳态误差,同时还具有很好地跟踪多时变系统的能力。     

改进的变步长维纳系统盲源分离方法

基于非线性盲源分离的维纳系统算法中,采用固定步长导致算法的收敛速度和稳态误差之间存在矛盾,直接影响分离算法的性能。为了解决该问题,提出了基于非线性函数的变步长维纳系统盲源分离方法。该方法将更新的步长以非线性函数的形式引入到分离算法中,使得稳态时参数更新的步长尽可能小,以避免发生振荡。变步长算法在分离过程中的每次更新都会使步长自动进行合理的调整,使得收敛速度提高了53%,误差减小了45%。实验仿真表明,相对原算法,提出的维纳系统盲源分离方法可以更好地分离出信源信号,而且具有较小的误差和较快的收敛速度。     

一种新型自适应最小均方算法

针对最小均方(LMS)算法应用于功率放大器时存在收敛速度与收敛精度相矛盾的问题,提出了基于步长比较的最小均方算法。在带有P因子的变步长最小均方算法的基础上,采用简化的Sigmoid函数对步长进行改进,通过对前后两次步长的比较来确定是否更新权系数,以误差的自相关时间均值及均方误差的时间均值来调节算法步长,可以加快算法的收敛速度,降低算法的计算量。仿真结果表明,与最小均方算法相比,经过自适应预失真处理后,该算法的误差向量幅度(EVM)值提高了2.653 2%,系统邻信道功率比(ACPR)减少了4 dB。     

基于自适应系统辨识的收发隔离技术研究

收发隔离是机载干扰机不可避免的难题。如果收发隔离问题解决不好,轻则削弱干扰机效率,重则造成自发自收,形成自激励。固定步长的归一化最小均方误差(NLMS)算法在解决基于自适应系统辨识的收发隔离的问题时,由于精度不够,隔离效果很不理想。针对此问题提出一种基于先验误差的变步长NLMS算法,该算法依据相邻时刻先验误差的相关系数改变步长因子,改变后的步长因子能够在算法收敛过程中削弱噪声的影响,提高算法精度。理论分析和仿真结果证明:基于文中的变步长NLMS算法的收发隔离方案与基于其他最小均方误差算法的隔离方案相比,隔离性能有较大的改善。     

A New Normalized Subband Adaptive Filter Algorithm with Individual Variable Step Sizes

Proposed is a novel variable step size normalized subband adaptive filter algorithm, which assigns an individual step size for each subband by minimizing the mean square of the noise-free a posterior subband error. Furthermore, a noniterative shrinkage method is used to recover the noise-free priori subband error from the noisy subband error signal. Simulation results using the colored input signals have demonstrated that the proposed algorithm not only has better tracking capability than the existing subband adaptive filter algorithms, but also exhibits lower steady-state error.     

一种改进的变步长LMS自适应滤波算法

传统的固定步长的LMS算法难于同时获取较快的收敛速度与较小的稳态误差,基于这一矛盾,将变步长算法与变换域算法相结合,提出一种改进的LMS自适应算法以获得较快的收敛速度和较小的稳态误差。仿真结果表明,此算法在收敛速度与稳态误差的性能上均不同程度地优于其他同类算法,尤其是在低信噪比的情况下,其性能的优越性更为突出。     

改进的变步长LMS改进算法

在基于Lorentzian函数的变步长LMS自适应滤波算法的基础上,进行进一步改进,提出了一种新的自适应LMS滤波算法,通过建立新的误差信号e(n)与变步长因子μ(n)之间的关系,消除不相关噪声的影响。并用Matlab对其进行仿真验证,表明该算法解决了收敛速度和稳态误差之间的矛盾,在保证算法的计算复杂度较低的同时,使得算法的抗干扰能力进一步提高,适用于低信噪比条件下的信号提取及滤波,为实际应用提供了更大的灵活性。