Convergence analysis of adaptive filtering algorithms with singulardata covariance matrix

The paper provides a rigorous analysis of the behavior of adaptive filtering algorithms when the covariance matrix of the filter input is singular. The analysis is done in the context of adaptive plant identification. The considered algorithms are LMS, RLS, sign (SA), and signed regressor (SRA) algorithms. Both the signal and weight behavior of the algorithms are considered. The signal behavior is evaluated in terms of the moments of the excess output error of the filter. The weight behavior is evaluated in terms of the moments of the filter weight misalignment vector. It is found that the RLS and SRA diverge when the input covariance matrix is singular. The steady-state signal behavior of the LMS and SA can be made arbitrarily fine by using sufficiently small step sizes of the algorithms. Indeed, the long-term average of the mean square excess error of the LMS is proportional to the algorithm step size. The long-term average of the mean absolute excess error of the SA is proportional to the square root of the algorithm step size. On the other hand, the steady-state weight behavior of both the LMS and SA have biases that depend on the weight initialization. The analytical results of the paper are supported by simulations     

Adaptive joint beamforming and B‐MMSE detection for CDMA signal reception under multipath interference

The combination of antenna array beamforming with multiuser detection can effectively improve the detection efficiency of a wireless system under multipath interference, especially in a fast‐fading channel. This paper studies the performance of an adaptive beamformer incorporated with a block‐wise minimum mean square error(B‐MMSE) detector, which works on a unique signal frame characterized by training sequence preamble and data blocks segmented by zero‐bits. Both beam‐former weights updating and B‐MMSE detection are carried out by either least mean square (LMS) or recursive least square (RLS) algorithm. The comparison of the two adaptive algorithms applied to both beamformer and B‐MMSE detector will be made in terms of convergence behaviour and estimation mean square error. Various multipath patterns are considered to test the receiver's responding rapidity to changing multipath interference. The performance of the adaptive B‐MMSE detector is also compared with that of non‐adaptive version (i.e. through direct matrix inversion). The final performance in error probability simulation reveals that the RLS/B‐MMSE scheme outperforms non‐adaptive B‐MMSE by 1–5 dB, depending on the multipath channel delay profiles of concern. The obtained results also suggest that adaptive beamformer should use RLS algorithm for its fast and robust convergence property; while the B‐MMSE filter can choose either LMS or RLS algorithm depending on antenna array size, multipath severity and implementation complexity. Copyright © 2004 John Wiley & Sons, Ltd.     

Stochastic analysis of the LMS algorithm with a saturationnonlinearity following the adaptive filter output

This paper presents a statistical analysis of the least mean square (LMS) algorithm with a zero-memory scaled error function nonlinearity following the adaptive filter output. This structure models saturation effects in active noise and active vibration control systems when the acoustic transducers are driven by large amplitude signals. The problem is first defined as a nonlinear signal estimation problem and the mean-square error (MSE) performance surface is studied. Analytical expressions are obtained for the optimum weight vector and the minimum achievable MSE as functions of the saturation. These results are useful for adaptive algorithm design and evaluation. The LMS algorithm behavior with saturation is analyzed for Gaussian inputs and slow adaptation. Deterministic nonlinear recursions are obtained for the time-varying mean weight and MSE behavior. Simplified results are derived for white inputs and small step sizes. Monte Carlo simulations display excellent agreement with the theoretical predictions, even for relatively large step sizes. The new analytical results accurately predict the effect of saturation on the LMS adaptive filter behavior     

DFT/LMS算法在DSSS中的应用及性能分析

本文分析了直接序列扩频(DSSS)系统中最小错误概率(MPE)意义下的最优滤波器,并依据矩阵求逆引理证明最小均方误差(MMSE)意义下的最优滤波——维纳滤波也是MPE意义下的最优滤波。在DSSS中应用自适应滤波,无须先验已知扩频码的码型和干扰的统计特性,就能一并完成解扩以及有效抑制干扰。离散傅立叶变换/最小均方(DFT/LMS)算法的收敛速度远快于LMS算法,而运算量、稳健性与LMS算法基本相同。基于DFT/LMS算法的自适应滤波大大简化DSSS系统接收机的设计,显著增强系统抗干扰能力,具有很强的实用性。     

紫外目标探测弱信号处理方法研究

为了提高紫外探测系统性能,研究具有高灵敏性紫外目标探测弱信号处理方法是关键问题之一。首先,在阐述紫外目标探测原理的基础上,分析紫外目标辐射特性。其次,研究自适应噪声抵消信号处理的一般方法,以及基于最小均方误差LMS准则、递推最小二乘RLS准则和线性神经网络ADALINE的三种具体的自适应噪声抵消算法。再次,提出采用功率信噪比来衡量滤波算法的性能。最后,通过仿真计算比较分析这三种算法的滤波效果。结果表明:采用LMS和RLS算法信噪比提高约12.5 dB,且LMS算法比RLS算法略优,而采用ADALINE算法信噪比至少改善26.6 dB,可实现高性能滤波。对于紫外目标探测弱信号处理方法的发展与深入研究具有一定的作用和意义。     

Improvement in adaptive noise canceling using a nonlinear filter based on the pontryagin minimum principle

This paper introduces a new nonlinear filter that is used for adaptive noise canceling. The derivation and convergence properties of the filter are presented. The performance, as measured by the root mean square error between the signal and its estimate, is compared with that of the commonly used least mean square (LMS) algorithm. It is shown, through simulation, that the proposed nonlinear noise canceler has, on the average, better performance than the LMS canceler. The proposed adaptive noise canceler is based on the Pontryagin minimum principle and the method of invariant imbedding. The computational time for the proposed method is about 10% of that of the LMS, in the studied cases, which is a substantial improvement.     

Comparative tracking performance of the LMS and RLS algorithms forchirped narrowband signal recovery

This paper studies the comparative tracking performance of the recursive least squares (RLS) and least mean square (LMS) algorithms for time-varying inputs, specifically for linearly chirped narrowband input signals in additive white Gaussian noise. It is shown that the structural differences in the implementation of the LMS and RLS weight updates produce regions where the LMS performance exceeds that of the RLS and other regions where the converse occurs. These regions are shown to be a function of the signal bandwidth and signal-to-noise ratio (SNR). LMS is shown to place a notch in the signal band of the mean lag filter, thus reducing the lag error and improving the tracking performance. For the chirped signal, it is shown that this produces smaller tracking error for small SNR. For high SNR, there is a region of signal bandwidth for which RLS will provide lower error than LMS, but even for these high SNR inputs, LMS always provides superior performance for very narrowband signals     

Adaptive AR modeling in white Gaussian noise

Autoregressive (AR) modeling is widely used in signal processing. The coefficients of an AR model can be easily obtained with a least mean square (LMS) prediction error filter. However, it is known that this filter gives a biased solution when the input signal is corrupted by white Gaussian noise. Treichler (1979) suggested the γ-LMS algorithm to remedy this problem and proved that the mean weight vector can converge to the Wiener solution. In this paper, we develop a new algorithm that extends works of Vijayan et al. (1990), for adaptive AR modeling in the presence of white Gaussian noise. By theoretical analysis, we show that the performance of the new algorithm is superior to the γ-LMS filter. Simulations are also provided to support our theoretical results     

Comparison of RLS, LMS, and sign algorithms for tracking randomlytime-varying channels

The performance of adaptive FIR filters governed by the recursive least-squares (RLS) algorithm, the least mean square (LMS) algorithm, and the sign algorithm (SA), are compared when the optimal filtering vector is randomly time-varying. The comparison is done in terms of the steady-state excess mean-square estimation error ξ and the steady-state mean-square weight deviation, η. It is shown that ξ does not depend on the spread of eigenvalues of the input covariance matrix, R, in the cases of the LMS algorithm and the SA, while it does in the case of the RLS algorithm. In the three algorithms, η is found to be increasing with the eigenvalue spread. The value of the adaptation parameter that minimizes ξ is different from the one that minimizes η. It is shown that the minimum values of ξ and η attained by the RLS algorithm are equal to the ones attained by the LMS algorithm in any one of the three following cases: (1) if R has equal eigenvalues, (2) if the fluctuations of the individual elements of the optimal vector are mutually uncorrelated and have the same mean-square value, or (3) if R is diagonal and the fluctuations of the individual elements of the optimal vector have the same mean-square value. Conditions that make the values of ξ and η of the LMS algorithm smaller (or greater) than the ones of the RLS algorithm are derived. For Gaussian input data, the minimum values of ξ and η attained by the SA are found to exceed the ones attained by the LMS algorithm by 1 dB independently of R and the mutual correlation between the elements of the optimal vector     

A new system identification method for fast echo cancelerinitialization

Proposes a new recursive version of an earlier technique for fast initialization of data-driven echo cancelers (DDECs). The speed of convergence and the covariance of the estimate of the proposed technique are comparable to the recursive least squares (RLS) algorithm, however, the computational complexity is no greater than the least mean square (LMS) algorithm. Analysis of computational complexity and the estimation error is also provided. Simulation results based on both floating-point and fixed-point arithmetic illustrate a remarkable improvement in terms of speed of convergence and steady-state error over the computationally comparable LMS algorithm     

A hybrid array minimizing the effects of the random weight vectorerrors in the LMS array and the Applebaum array

A hybrid adaptive array that combines the least mean square-error (LMS) array and the Applebaum array is presented. The array minimizes the effect of the random errors in the weight vectors of the LMS and Applebaum arrays. These weight vectors containing random errors are scaled and combined to yield a novel weight vector. The mean square error (MSE) is used as a measure of performance to derive optimal weighting factors. An algorithm is devised to adjust the weighting factors automatically by an iterative procedure based on the complex LMS algorithm to achieve the optimum weighting factors. It is shown that the hybrid array performs better than the Applebaum array or the LMS array. In addition, it is less sensitive to the random weight vector errors     

The multi-user detection under fading channel

This paper proposes a method of blind multi-user detection algorithm based on signal sub-space estimation under the fading channels in the present of impulse noise. This algorithm adapts recursive least square (RLS) filter that can estimate the coefficients using only the signature waveform. In addition, to strengthen the ability of resisting the impulse noise, a new suppressive factor is induced, which can suppress the amplitude of the impulse, and improve the ability of convergence speed. Simulation results show that new RLS algorithm is more robust against consecutive impulse noise and have better convergence ability than conventional RLS. In addition, Compared to the least mean square (LMS) detector, the new robust RLS sub-space based method has better multi-address-inference (MAI) suppressing performance, especially, when channel degrades.     

A Nonlinear Acoustic Echo Canceller Using Sigmoid Transform in Conjunction With RLS Algorithm

Nonlinearity of amplifiers and/or loudspeakers gives rise to nonlinear echo in acoustic systems, which seriously degrades the performance of speech and audio communications. Many nonlinear acoustic echo cancellation (AEC) methods have been proposed. In this paper, a simple yet efficient nonlinear echo cancellation scheme is presented by using an adaptable sigmoid function in conjunction with a conventional transversal adaptive filter. The new scheme uses the least mean square (LMS) algorithm to update the parameters of sigmoid function and the recursive least square (RLS) algorithm to determine the coefficient vector of the transversal filter. The proposed AEC is proved to be convergent under some mild assumptions. Computer simulations show that the proposed scheme gives a superior echo cancellation performance over the well known Volterra filter approach when the echo path suffers from the saturation-type nonlinear distortion. More importantly, the new AEC has a much lower computational complexity than the Volterra-filter-based method.      

Adaptive algorithms for non-Gaussian noise environments: the orderstatistic least mean square algorithms

Convergence properties are studied for a class of gradient-based adaptive filters known as order statistic least mean square (OSLMS) algorithms. These algorithms apply an order statistic filtering operation to the gradient estimate of the standard least mean square (LMS) algorithm. The order statistic operation in OSLMS algorithms can reduce the variance of the gradient estimate (relative to LMS) when operating in non-Gaussian noise environments. A consequence is that in steady state, the excess mean square error can be reduced. It is shown that when the input signals are iid and symmetrically distributed, the coefficient estimates for the OSLMS algorithms converge on average to a small area around their optimal values. Simulations provide supporting evidence for algorithm convergence. As a measurement of performance, the mean squared coefficient error of OSLMS algorithms has been evaluated under a range of noise distributions and OS operators. Guidelines for selection of the OS operator are presented based on the expected noise environment     

Optimal tracking of time-varying channels: a frequency domainapproach for known and new algorithms

In this paper, we developed a systematic frequency domain approach to analyze adaptive tracking algorithms for fast time-varying channels. The analysis is performed with the help of two new concepts, a tracking filter and a tracking error filter, which are used to calculate the mean square identification error (MSIE). First, we analyze existing algorithms, the least mean squares (LMS) algorithm, the exponential windowed recursive least squares (EW-RLS) algorithm and the rectangular windowed recursive least squares (RW-RLS) algorithm. The equivalence of the three algorithms is demonstrated by employing the frequency domain method. A unified expression for the MSIE of all three algorithms is derived. Secondly, we use the frequency domain analysis method to develop an optimal windowed recursive least squares (OW-RLS) algorithm. We derive the expression for the MSIE of an arbitrary windowed RLS algorithm and optimize the window shape to minimize the MSIE. Compared with an exponential window having an optimized forgetting factor, an optimal window results in a significant improvement in the h MSIE. Thirdly, we propose two types of robust windows, the average robust window and the minimax robust window. The RLS algorithms designed with these windows have near-optimal performance, but do not require detailed statistics of the channel     

采用归一化最小均方误差准则的LM-BP算法

传统神经网络通常以最小均方误差(LMS)或最小二乘（RLS）为收敛准则,而在自适应均衡等一些应用中,使用归一化最小均方误差（NLMS）准则可以使神经网络性能更加优越。本文在NLMS准则基础上,提出了一种以Levenberg-Marquardt（LM）训练的神经网络收敛算法。通过将神经网络的误差函数归一化,然后采用LM算法作为训练算法,实现了神经网络的快速收敛。理论分析和实验仿真表明,与采用最速下降法的NLMS准则和采用LM算法的LMS准则相比,本文算法收敛速度快,归一化均方误差更小,应用于神经网络水印系统中实现了水印信息的盲提取,能更好的抵抗噪声、低通滤波和重量化等攻击,性能平均提高了4%。      

一种改进的解相关变步长LMS算法

讨论了一类针对传统LMS算法进行改进的变步长自适应算法,分析其性能,对原有算法进行改进,并针对输入信号高度相关时算法收敛速度下降导致性能下降的问题,引入了解相关原理,用输入向量的正交分量来更新滤波器权系数,有效加快了算法的收敛速度,并保持了原算法的良好性能。     

An adaptive algorithm for differentially coherent detection in the presence of intersymbol interference

An adaptive equalization method is proposed for use with differentially coherent detection of M-ary differential phase-shift keying (DPSK) signals in the presence of unknown carrier frequency offset. A decision-feedback or a linear equalizer is employed, followed by the differentially coherent detector. The equalizer coefficients are adjusted to minimize the post-detection mean squared error. The error, which is a quadratic function of the equalizer vector, is used to design an adaptive algorithm of stochastic gradient type. The approach differs from those proposed previously, which linearize the post-detection error to enable the use of least mean squares (LMS) or recursive least squares (RLS) adaptive equalizers. The proposed quadratic-error (Q) algorithm has complexity comparable to that of LMS, and equal convergence speed. Simulation results demonstrate performance improvement over methods based on linearized-error (L) algorithm. The main advantages of the technique proposed are its simplicity of implementation and robustness to carrier frequency offset, which is maintained for varying modulation level.     

自适应MPAM解调方法研究

提出了一种新型的基于自适应滤波器权系数解调多进制幅度调制(MPAM)信号的方法.文中以常用的最小均方误差自适应算法(LMS)为例,讨论了新型的MPAM自适应解调的过程及其性能.该解调算法不需要自适应滤波器完成收敛,从而降低了采样频率和处理速度.给出的理论性能与仿真结果表明,MPAM自适应解调的误码率仿真结果与理论值吻合非常好;而且该方法具有抗干扰性能强、输出响应快、便于数字信号处理(DSP)技术实现等特点,在相同的采样频率下其误码率优于相关解调的误码率.     

一种自适应时延估计的新方法

最小均方（LMS）算法可用来进行时延估计。当算法收敛后,可以根据滤波器权系数最大值的位置估计整数倍采样周期的时延。为了估计非整数倍采样周期的时延,常用SINC函数插值法和约束自适应方法。利用SINC函数的特点和拉格朗日条件极值,对自适应时延估计的滤波器权系数做了改进,提出了新的约束自适应时延估计方法。仿真实验表明,提出方法的性能优于传统的自适应时延估计算法。