α稳定分布下的自适应数据块滤波算法

本文基于分数低阶统计量原理提出了α稳定分布下的自适应数据块LMP和LMAD滤波算法.新算法利用更多的输入信号和误差信号的信息,更准确地估计梯度,调整自适应滤波器权向量增量方向,提高了收敛速度.采用变步长因子改善算法的稳态误差,进一步提高了算法的收敛性能.仿真结果表明,在分数低阶α稳定分布信号条件下,自适应数据块滤波新算法较NLMP算法和NLMAD算法有更好的收敛性能.     

基于小波变换的变步长LMS自适应滤波算法

变步长LMS自适应滤波算法通过构造合适的步长因子有效的解决了传统LMS算法收敛速度和稳态误差相矛盾的问题.变换域LMS自适应滤波算法通过正交变换降低了输入信号矩阵的相关性,提高了算法的收敛速度.将这两种算法相结合,提出了一种新的基于小波变换的变步长LMS自适应滤波算法.仿真结果表明,该算法无论是收敛速度还是稳态误差都有了很大的提高.     

多径衰落信道中一种新的基于CMA的盲多用户检测算法

该文基于 CLSCMA算法提出了一种新的盲自适应多用户检测算法,这种算法适用于多径衰落信道。这种多用户检测算法能很好抵消多址干扰和克服多径衰落,算法的收敛性能和子空间自适应多用户检测算法相当,而稳态性能稍强于子空间多用户检测算法。因而是一种优秀的盲自适应多用户检测算法,具有一定的应用和研究价值。     

一种新的变步长LMS算法及在DSP上实现

最小均方(LMS)自适应滤波算法易于实现,并在很多领域得到了广泛的应用,但它存在着难于同时获取较快的收敛速度与较小的稳态误差这一矛盾,而固定步长LMS算法无法解决.基于这一矛盾,在此提出一种新的变步长LMS自适应滤波算法,用最佳Wiener解和反正切函数建立了步长因子与误差之间一种新的非线性函数关系,该算法具有良好的收敛性能.并通过DSP验证,结果表明该方法实现简单,不依赖模型,具有较强的稳健性.     

稳定分布的水声信号处理新方法

本文依据分数低阶统计信号处理理论和舰船辐射噪声信号特性,提出了水声信号新的噪声模型,分析了常规LMS滤波方法在非高斯稳定分布噪声下性能退化的原因,提出了基于分数低阶p-范数的LMP,NLMP水声信号自适应降噪滤波方法,并分析了参数p值的选取对LMP滤波效果的影响.理论分析和计算机仿真结果表明这种方法在高斯和非高斯稳定分布条件下都具有良好的鲁棒性.     

一种新的CMA盲多用户检测算法

该文提出了一种新的盲自适应多用户检测算法,这种算法的计算复杂度为O(NL),其中N为扩频因子,L为取样数据窗长度。仿真分析表明,该文提出的算法稳态性能好,收敛速度特别快,且能适应环境的变化,是一种较好的多用户检测算法。     

一种新的可变步长LMS自适应滤波算法及其算法分析

在讨论基本LMS．变步长NLMS和LMS／F组合自适应滤波算法的基础上提出一种新的可变步长LMS自适应滤波算法,新算法引入修正系数和遗忘因子．并利用和来产生新的步长参与迭代。计算机仿真结果表明,与基本LMS算法或变步长NLMS、LMS／F组合算法相比,新算法在保持算法简单这一特点的同时进一步加快了收敛速度,并能够收敛到更小且稳定的均方误差(MSE)。     

梯度向量正交的相关函数自适应滤波算法

该文把Asharif(1999)定义的相关函数均方误差(MSE)准则Jr(n)=E「eT(n)Ce(n)」改为时变的遗忘因子指数加权最小二乘误差(LSE)准则Jr(n)=nt=0 n-teT(n)Ce(n),对这一准则利用梯度法,使当前时刻的梯度向量正交于前一时刻的梯度向量而得到一种新的相关函数自适应滤波算法.计算机仿真结果表明新算法的收敛性能优于Asharif提出的ECLMS算法.     

自适应调节滤波强度的SAR图像非局部平均抑斑算法

为提升对SAR图像乘性相干斑的抑制水平与边缘保护性能,该文提出了一种可自适应调节滤波强度(AFS)的SAR图像非局部平均(NLM)抑斑新算法(AFS-NLM).该算法利用Frost滤波图像计算的局部均值与方差来改善SAR图像场景参量的估计,形成了一种能更好刻画SAR图像同质区与边缘区的改进Kuan滤波系数.利用局部均值比与改进Kuan滤波系数分别作为新的相似性测量参量与自适应衰减因子,构建了一种更适应SAR图像乘性噪声特性的改进NLM滤波.利用偏平滑参数与偏边缘保护参数控制下的改进NLM滤波,分别替代经典Kuan滤波模型中的像素局部均值与自身灰度值作为加权项,并采用由改进Kuan滤波系数构建的自适应调节因子对二者进行加权平均,从而形成了一种可自适应调节滤波强度的加权滤波新模型.实验表明,该文算法与近期多种先进算法相比,具有更好的相干斑抑制与边缘保护性能.     

一种变步长LMS自适应滤波算法及分析

本文对变步长自适应滤波算法进行了讨论,建立了步长因子μ与误差信号e(n)之间另一种新的非线性函数关系.该函数比已有的Sigmoid函数简单,且在误差e(n)接近零处具有缓慢变化的特性,克服了Sigmoid函数在自适应稳态阶段步长调整过程中的不足.由此函数本文得出了另一种新的变步长自适应滤波算法,并且分析了参数α,β的取值原则及对算法收敛性能的影响.该算法有较好的收敛性能且计算量少.计算机仿真结果与理论分析相一致,证实了该算法的收敛性能优于已有的算法.     

Adaptive estimation of latency change in evoked potentials bydirect least mean p-norm time-delay estimation

Evoked potentials (EP) have been widely used to quantify neurological system properties. Changes in EP latency may indicate impending neurological injury. Traditional EP analyses are developed under the condition that the background noise in EP analysis are Gaussian distributed. This paper proposes a latency change detection and estimation algorithm under α-stable noise condition, a generalization of Gaussian noise assumption. An analysis shows that the α-stable model fits the noises found in the impact acceleration experiment under study better than the Gaussian model. The robustness of the proposed algorithm is demonstrated through computer simulations and experimental data analysis under both Gaussian and α-stable noise environments     

一种α稳定分布下的变抽头长度LMP算法

针对无法事先知道滤波器抽头长度,且系统中存在“稳定分布噪声的情况,提出了一种α稳定分布背景下的变抽头长度自适应算法,采用3个并行的滤波器,比较数据段内其平均P阶误差大小,每K点数据段更新一次抽头长度,数据段内滤波器权值采用LMP算法调整。算法仿真表明,算法在不同特征指数的α稳定分布下都具有很强的韧性,能自适应调整到最优抽头长度,达到最优抽头长度的LMP算法的稳态误差。     

一种自适应全局最小平均p-范数算法

本文给出了适应于α-稳定噪声环境中自适应滤波和系统辨识的全局最小平均p-范数算法,其是总体最小二乘方法在脉冲噪声中的推广.本文还定义了全局l_p模误差和推导了点到直线的l_p距离,并在此基础上导出了全局最小平均p-范数算法.对所给算法进行了仿真实验研究,结果显示其性能优于著名的LMP算法.     

Near optimal detection of signals in impulsive noise modeled with asymmetric α-stable distribution

There has been great interest in symmetric α-stable distributions which have proved to be very good models for impulsive noise. However, most of the classical non-Gaussian receiver design techniques cannot be extended to the symmetric α-stable noise case since these techniques require an explicit compact analytical form for the probability density function (PDF) of the noise distribution which α-stable distributions do not possess. A new analytical representation has been suggested for the symmetric α-stable PDF which is based on scale mixtures of Gaussians. Based on this new analytical representation, this paper introduces a novel near-optimal receiver for the detection of signals in symmetric α-stable noise. The performance of the new receiver is very close to the locally optimum receiver and is significantly better than the performance of previously suggested sub-optimum receivers. The new technique has important potential in radar, sonar, and other applications     

α 稳定分布噪声下基于核方法的非线性信道均衡算法

为了提高α稳定分布噪声下非线性信道均衡器的性能,本文利用核方法处理非线性问题,结合最小平均p范数算法的核心思想,构造了α稳定分布噪声下基于核方法的非线性均衡器,提出并推导了α稳定分布噪声下核最小平均p范数均衡算法。首先,通过核函数将接收信号映射到高维特征空间;然后,在高维特征空间中利用LMP算法对信号进行均衡;最后,将均衡器的输出信号表示为内积形式并利用核函数将其转化到输入空间进行计算。理论分析和仿真实验结果表明,与核最小均方算法和最小平均p范数算法相比,新算法在保证收敛速度的前提下降低了稳态误差,能够更好地对α稳定分布噪声下的非线性信道失真进行补偿。      

Parameter estimation and blind channel identification in impulsivesignal environments

New methods for parameter estimation and blind channel identification in impulsive signal environments are presented, where the signals/noise are modeled as symmetric α-stable (SαS) processes. First, we present methods for estimating the parameters (characteristic exponent α and dispersion γ) of a SαS distribution from a time series. The fractional lower order moments, with both positive and negative orders, and their applications to signal processing are introduced. Then we present a new algorithm for blind channel identification using the output fractional lower order moments, and the α-Spectrum, a new spectral representation for impulsive signals, is introduced. From the α-Spectrum, we establish the blind identifiability conditions of any FIR channel (mixed-phase, unknown order) with i.i.d. SαS (α>1) input. As a byproduct, a simple algorithm for recovering the phase of any type of a signal from the magnitude of its z-transform is presented. The novelty of our paper is in parameter estimation and blind identification of the FIR channel based on fractional lower order moments of its output data. Monte Carlo simulations clearly demonstrate the performance of the new methods     

Power-law shot noise and its relationship to long-memoryα-stable processes

We consider the shot noise process, whose associated impulse response is a decaying power-law kernel of the form t^β/2-1 . We show that this power-law Poisson model gives rise to a process that, at each time instant, is an α-stable random variable if β<1. We show that although the process is not α-stable, pairs of its samples become jointly α-stable as the distance between them tends to infinity. It is known that for the case β>1, the power-law Poisson process has a power-law spectrum. We show that, although in the case β<1 the power spectrum does not exist, the process still exhibits long memory in a generalized sense. The power-law shot noise process appears in many applications in engineering and physics. The proposed results can be used to study such processes as well as to synthesize a random process with long-range dependence     

脉冲噪声环境下基于分数低阶循环相关的MUSIC算法

该文以稳定分布作为噪声模型,研究了脉冲噪声环境下循环平稳信号的波达方向估计问题。针对在脉冲噪声环境中基于传统2阶循环相关的算法效果显著退化的问题,该文提出了基于分数低阶循环相关的分数低阶循环MUSIC算法(FLOCC-MUSIC)。将分数低阶循环相关与MUSIC算法相结合,可以有效抑制脉冲噪声的同频带干扰。计算机仿真表明了此算法可有效完成高斯噪声和脉冲噪声条件下的波达方向估计,其性能优于传统的基于2阶循环相关的Cyclic-MUSIC。     

The minimum error entropy based robust wireless channel tracking inimpulsive noise

This article concerns the problem of adaptive wireless channel tracking in the non-Gaussian α-stable noise. By assuming a primitive Cauchy distribution for the estimate error and minimizing the entropy of error, we develop the least entropy of error (LEE) based wireless channel tracking algorithm and the second-order LEE (SOLEE) algorithm. Simulation results show that both algorithms are robust to impulsive noise and such robustness can be achieved without any performance loss in the Gaussian noise