On the Performance Analysis of the Least Mean M-Estimate and Normalized Least Mean M-Estimate Algorithms with Gaussian Inputs and Additive Gaussian and Contaminated Gaussian Noises

This paper studies the convergence analysis of the least mean M-estimate (LMM) and normalized least mean M-estimate (NLMM) algorithms with Gaussian inputs and additive Gaussian and contaminated Gaussian noises. These algorithms are based on the M-estimate cost function and employ error nonlinearity to achieve improved robustness in impulsive noise environment over their conventional LMS and NLMS counterparts. Using the Price’s theorem and an extension of the method proposed in Bershad (IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP-34(4), 793–806, 1986; IEEE Transactions on Acoustics, Speech, and Signal Processing, 35(5), 636–644, 1987), we first derive new expressions of the decoupled difference equations which describe the mean and mean square convergence behaviors of these algorithms for Gaussian inputs and additive Gaussian noise. These new expressions, which are expressed in terms of the generalized Abelian integral functions, closely resemble those for the LMS algorithm and allow us to interpret the convergence performance and determine the step size stability bound of the studied algorithms. Next, using an extension of the Price’s theorem for Gaussian mixture, similar results are obtained for additive contaminated Gaussian noise case. The theoretical analysis and the practical advantages of the LMM/NLMM algorithms are verified through computer simulations.     

On the Performance Analysis of a Class of Transform-domain NLMS Algorithms with Gaussian Inputs and Mixture Gaussian Additive Noise Environment

This paper studies the convergence performance of the transform domain normalized least mean square (TDNLMS) algorithm with general nonlinearity and the transform domain normalized least mean M-estimate (TDNLMM) algorithm in Gaussian inputs and additive Gaussian and impulsive noise environment. The TDNLMM algorithm, which is derived from robust M-estimation, has the advantage of improved performance over the conventional TDNLMS algorithm in combating impulsive noises. Using Price’s theorem and its extension, the above algorithms can be treated in a single framework respectively for Gaussian and impulsive noise environments. Further, by introducing new special integral functions, related expectations can be evaluated so as to obtain decoupled difference equations which describe the mean and mean square behaviors of the TDNLMS and TDNLMM algorithms. These analytical results reveal the advantages of the TDNLMM algorithm in impulsive noise environment, and are in good agreement with computer simulation results.     

A recursive least M-estimate algorithm for robust adaptive filtering in impulsive noise: fast algorithm and convergence performance analysis

This paper studies the problem of robust adaptive filtering in impulsive noise environment using a recursive least M-estimate algorithm (RLM). The RLM algorithm minimizes a robust M-estimator-based cost function instead of the conventional mean square error function (MSE). Previous work has showed that the RLM algorithm offers improved robustness to impulses over conventional recursive least squares (RLS) algorithm. In this paper, the mean and mean square convergence behaviors of the RLM algorithm under the contaminated Gaussian impulsive noise model is analyzed. A lattice structure-based fast RLM algorithm, called the Huber Prior Error Feedback-Least Squares Lattice (H-PEF-LSL) algorithm is derived. Part of the H-PEF-LSL algorithm was presented in ICASSP 2001. It has an order O(N) arithmetic complexity, where N is the length of the adaptive filter, and can be viewed as a fast implementation of the RLM algorithm based on the modified Huber M-estimate function and the conventional PEF-LSL adaptive filtering algorithm. Simulation results show that the transversal RLM and the H-PEF-LSL algorithms have better performance than the conventional RLS and other RLS-like robust adaptive algorithms tested when the desired and input signals are corrupted by impulsive noise. Furthermore, the theoretical and simulation results on the convergence behaviors agree very well with each other.     

Robust M-estimate adaptive filtering

An M-estimate adaptive filter for robust adaptive filtering in impulse noise is proposed. Instead of using the conventional least-square cost function, a new cost function based on an M-estimator is used to suppress the effect of impulse noise on the filter weights. The resulting optimal weight vector is governed by an M-estimate normal equation. A recursive least M-estimate (RLM) adaptive algorithm and a robust threshold estimation method are derived for solving this equation. The mean convergence performance of the proposed algorithm is also analysed using the modified Huber (1981) function (a simple but good approximation to the Hampel's three-parts-redescending M-estimate function) and the contaminated Gaussian noise model. Simulation results show that the proposed RLM algorithm has better performance than other recursive least squares (RLS) like algorithms under either a contaminated Gaussian or alpha-stable noise environment. The initial convergence, steady-state error, robustness to system change and computational complexity are also found to be comparable to the conventional RLS algorithm under Gaussian noise alone     

Robust proportionate adaptive filter based on maximum correntropy criterion for sparse system identification in impulsive noise environments

Proportionate-type adaptive filtering (PtAF) algorithms have been successfully applied to sparse system identification. The major drawback of the traditional PtAF algorithms based on the mean square error (MSE) criterion show poor robustness in the presence of impulsive noises or abrupt changes because MSE is only valid and rational under Gaussian assumption. However, this assumption is not satisfied in most real-world applications. To improve its robustness under non-Gaussian environments, we incorporate the maximum correntropy criterion (MCC) into the update equation of the PtAF to develop proportionate MCC (PMCC) algorithm. The mean and mean square convergence performance analysis are also performed. Simulation results in sparse system identification and echo cancellation applications are presented, which demonstrate that the proposed PMCC exhibits outstanding performance under the impulsive noise environments.     

Convergence Behavior of NLMS Algorithm for Gaussian Inputs: Solutions Using Generalized Abelian Integral Functions and Step Size Selection

This paper studies the mean and mean square convergence behaviors of the normalized least mean square (NLMS) algorithm with Gaussian inputs and additive white Gaussian noise. Using the Price’s theorem and the framework proposed by Bershad in IEEE Transactions on Acoustics, Speech, and Signal Processing (1986, 1987), new expressions for the excess mean square error, stability bound and decoupled difference equations describing the mean and mean square convergence behaviors of the NLMS algorithm using the generalized Abelian integral functions are derived. These new expressions which closely resemble those of the LMS algorithm allow us to interpret the convergence performance of the NLMS algorithm in Gaussian environment. The theoretical analysis is in good agreement with the computer simulation results and it also gives new insight into step size selection.     

An improved proportionate least mean <Emphasis Type="Italic">p</Emphasis>-power algorithm for adaptive filtering

The least mean p-power error criterion has been successfully used in adaptive filtering due to its strong robustness against large outliers. In this paper, we develop a new adaptive filtering algorithm, named the proportionate least mean p-power (PLMP) algorithm, which uses the mean p-power error as the adaptation cost function. Compared with the standard proportionate normalized least mean square algorithm, the PLMP can achieve much better performance in terms of the mean square deviation, especially in the presence of impulsive non-Gaussian noises. The mean and mean square convergence of the proposed algorithm are analyzed, and some related theoretical results are also obtained. Simulation results are presented to verify the effectiveness of our proposed algorithm.     

Sparse least mean mixed‐norm adaptive filtering algorithms for sparse channel estimation applications

Sparse least‐mean mixed‐norm (LMMN) algorithms are developed to improve the estimation performance for sparse channel estimation applications. Both the benefits of the least mean fourth and least mean square algorithms are utilized to exploit a type of sparse LMMN algorithms. The proposed sparse‐aware LMMN algorithms are implemented by integrating an l ₁‐norm or log‐sum function into the cost function of traditional LMMN algorithm so that they can exploit the sparse properties of the broadband multi‐path channel and achieve better channel estimation performance. The proposed sparse LMMN algorithms are equal to adding an amazing zero‐attractor in the update equation of the traditional LMMN algorithm, which aim to speed up the convergence. The channel estimation performance of the proposed sparse LMMN algorithms are evaluated over a sparse broadband multi‐path channel to verify their effectiveness. Simulation results depict that the sparse LMMN algorithms are superior to the previously reported sparse‐aware least mean square/fourth, least mean fourth and least mean square and their corresponding sparse‐aware algorithms in terms of both the convergence and steady‐state behavior when the broadband multi‐path channel is sparse. Copyright © 2016 John Wiley & Sons, Ltd.     

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。     

A Normalized Least Mean Square Algorithm Based on the Arctangent Cost Function Robust Against Impulsive Interference

In this paper, a normalized least mean square (NLMS) adaptive filtering algorithm based on the arctangent cost function that improves the robustness against impulsive interference is proposed. Owing to the excellent characteristics of the arctangent cost function, the adaptive update of the weight vector stops automatically in the presence of impulsive interference. Thus, this eliminates the likelihood of updating the weight vector based on wrong information resulting from the impulsive interference. When the priori error is small, the NLMS algorithm based on the arctangent cost function operates as the conventional NLMS algorithm. Simulation results show that the proposed algorithm can achieve better performance than the traditional NLMS algorithm, the normalized least logarithmic absolute difference algorithm and the normalized sign algorithm in system identification experiments that include impulsive interference and abrupt changes.     

Partial-Update L∞ -Norm Based Algorithms

The computational complexity of an adaptive filtering algorithm increases with increasing the filter tap length and therefore, the use of such a filter can become prohibitive for certain applications, especially for real-time implementation. In this paper, we develop low-complexity adaptive filtering algorithms by incorporating the concept of partial updating of the filter coefficients into the technique of finding the gradient vector in the hyperplane based on the L_infin-norm criterion. Two specific partial update algorithms based on the sequential and M-Max coefficient updating are proposed. The statistical analyses of the two algorithms are carried out, and evolution equations for the mean and mean-square of the filter coefficient misalignment as well as the stability bounds on the step size are obtained. It is shown that the proposed partial update algorithm employing the M-Max coefficient updating can achieve a convergence rate that is closest to that of the full update algorithm. Finally, simulations are carried out to validate the theoretical results and study the convergence rate of the proposed algorithms     

一种适用于强脉冲噪声下的对数型恒模盲均衡算法

针对脉冲噪声下恒模算法(Constant Modulus Algorithm,CMA)失败的问题,通过分析脉冲噪声的影响,提出了一种基于最小均方（Least Mean Square,LMS）准则的对数型恒模算法（Logarithmic-type CMA,LT-CMA）。LT-CMA利用对数函数的非线性变换特性自适应地抑制强脉冲噪声对误差函数的影响,并且利用l2-范数进行信号归一化处理以增强算法的稳健性。仿真结果表明,所提出的LT-CMA可以适应于高斯噪声环境和脉冲噪声环境;与经典自适应均衡算法相比,在收敛速度和稳健性两方面上,所提出的LT-CMA都有显著的提升。     

A robust past algorithm for subspace tracking in impulsive noise

The PAST algorithm is an effective and low complexity method for adaptive subspace tracking. However, due to the use of the recursive least squares (RLS) algorithm in estimating the conventional correlation matrix, like other RLS algorithms, it is very sensitive to impulsive noise and the performance can be degraded substantially. To overcome this problem, a new robust correlation matrix estimate, based on robust statistics concept, is proposed in this paper. It is derived from the maximum-likelihood (ML) estimate of a multivariate Gaussian process in contaminated Gaussian noise (CG) similar to the M-estimates in robust statistics. This new estimator is incorporated into the PAST algorithm for robust subspace tracking in impulsive noise. Furthermore, a new restoring mechanism is proposed to combat the hostile effect of long burst of impulses, which sporadically occur in communications systems. The convergence of this new algorithm is analyzed by extending a previous ordinary differential equation (ODE)-based method for PAST. Both theoretical and simulation results show that the proposed algorithm offers improved robustness against impulsive noise over the PAST algorithm. The performance of the new algorithm in nominal Gaussian noise is very close to that of the PAST algorithm.     

Robust Regularization for Normalized LMS Algorithms

We present a novel normalized least mean square (NLMS) algorithm with robust regularization. The proposed algorithm dynamically updates the regularization parameter that is fixed in the conventional$epsilon $-NLMS algorithms. By exploiting the gradient descent direction we derive a computationally efficient and robust update scheme for the regularization parameter. Through experiments we demonstrate that the proposed algorithm outperforms conventional NLMS algorithms in terms of the convergence rate and the misadjustment error.     

A class of order statistic LMS algorithms

Conventional gradient-based adaptive filters, as typified by the well-known LMS algorithm, use an instantaneous estimate of the error-surface gradient to update the filter coefficients. Such a strategy leaves the algorithm extremely vulnerable to impulsive interference. A class of adaptive algorithms employing order statistic filtering of the sampled gradient estimates is presented. These algorithms, dubbed order statistic least mean squares (OSLMS), are designed to facilitate adaptive filter performance close to the least squares optimum across a wide range of input environments from Gaussian to highly impulsive. Three specific OSLMS filters are defined: the median LMS, the average LMS, and the trimmed-mean LMS. The properties of these algorithms are investigated and the potential for improvement demonstrated. Finally, a general adaptive OSLMS scheme in which the nature of the order-statistic operator is also adapted in response to the statistics of the input signal is presented. It is shown that this can facilitate performance gains over a wide range of input data types     

Enhanced-Convergence Normalized LMS Algorithm

Least mean square (LMS) algorithms have found great utility in many adaptive filtering applications. This article shows how the traditional constraints placed on the update gain of normalized LMS algorithms are overly restrictive. We present relaxed update gain constraints that significantly improve normalized LMS algorithm convergence speed.     

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     

抗脉冲干扰的分布式仿射投影符号算法

递增式和扩散式仿射投影算法收敛较快,但在脉冲噪声环境下这两种分布式估计算法收敛性较差或容易发散.本文采用受网络节点的权值向量更新约束的后验误差向量?₁范数最小化方法,提出了两种抗脉冲干扰的分布式估计算法,即递增式和扩散式仿射投影符号算法.仿真结果表明,与分布式仿射投影算法相比,分布式仿射投影符号算法在脉冲噪声环境下具有更好的鲁棒性.     

A family of adaptive filter algorithms with decorrelatingproperties

Although the normalized least mean square (NLMS) algorithm is robust, it suffers from low convergence speed if driven by highly correlated input signals. One method presented to overcome this problem is the Ozeki/Umeda (1984) affine projection (AP) algorithm. The algorithm applies update directions that are orthogonal to the last P input vectors and thus allows decorrelation of an AR(P) input process, speeding up the convergence. This article presents a simple approach to show this property, which furthermore leads to the construction of new algorithms that can handle other kinds of correlations such as MA and ARMA processes. A statistical analysis is presented for this family of algorithms. Similar to the AP algorithm, these algorithms also suffer a possible increase in the noise energy caused by their pre-whitening filters     

Adaptive zero-tracking complemented by LMS weight update forguaranteed convergence

A low-complexity zero-tracking algorithm with fast and guaranteed convergence behavior is proposed and investigated. The algorithm implements a zero-tracking algorithm and a least mean square (LMS) weight update algorithm in parallel, with the former adjusting the zeros of the array in a time-multiplexed manner to achieve fast asymptotic and tracking behavior, while the latter improves the initial transient behavior of the algorithm and guarantees its convergence to the global optimum. By comparing their output powers, the relative performances of the two component algorithms are monitored, and re-initialization of one algorithm by the other may occur periodically. This gives the algorithm both fast and guaranteed convergence behavior, even though the zeros are directly available and the implementation complexity is only two times that for the conventional LMS algorithm