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.     

α噪声环境下整体最小平均P-范数IIR自适应滤波算法

当无限冲激响应(IIR)系统输入和输出信号中都存在α稳定噪声干扰,传统的最小平均P-范数算法(LMP)的解会出现较大偏差,本文提出了一种自适应IIR滤波整体最小平均P-范数(IIR_TLMP)算法,算法中整体考虑输入和输出信号的α稳定噪声干扰,将最小化l_p范数Rayleigh商采用随机梯度法得到自适应IIR滤波方程。通过仿真首先考察了特征指数和步长因子等主要参数对TLMP算法性能的影响,最后分别在时不变和时变系统中,将TLMP算法与LMP算法的性能在进行了比较,结果显示TLMP有更快的收敛速度和更小的误差。      

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。      

一种变步长最小平均p范数自适应滤波算法

在p稳定分布脉冲噪声背景下,为解决固定步长最小平均p范数(LMP)不能同时满足快收敛速度和低稳态误差的问题,该文提出一种对脉冲噪声具有鲁棒性的变步长最小平均p范数(VSS-LMP)自适应滤波算法.该算法利用改进的变形高斯函数来调节步长,采用移动平均法构造变步长函数,克服了定步长算法稳态误差高及抗噪性能差的问题.VSS-LMP算法在系统受到脉冲噪声干扰时,能维持步长稳定;当系统逐渐稳定时,能产生小步长以降低稳态误差.系统辨识仿真结果表明,在α稳定分布脉冲噪声下,VSS-LMP算法与固定步长和已有变步长算法相比,具有更快的收敛速度和更强的系统跟踪能力.     

对称稳定分布的相关熵及其在时间延迟估计上的应用

相关熵是一个表示随机变量局部相似性的统计量。该文首先研究对称-稳定SS分布的相关熵的参数表示,利用该参数表示证明了对于位置参数为零的分布SS,最大相关熵准则与最小分散系数准则是等价的。最后将研究结果应用于稳定分布噪声环境下自适应时间延迟估计。仿真实验表明,该文算法性能优于最小均方误差时间延迟估计与最小平均P-范数时间延迟估计。     

α稳定分布下的加权平均最小p-范数算法

该文提出一种新的适用于α稳定分布噪声环境的自适应滤波算法,这种算法通过使加权平均误差函数的p-范数最小来实现自适应滤波.在这种算法的基础上,该文还得到两种新的动量LMP自适应算法.将这些新算法应用于估计AR模型的参数,计算机仿真的结果表明,该文提出的算法的性能比已有LMP算法的性能要更为优越.     

脉冲噪声下数字调制信号的自适应解调

提出基于自适应滤波解调α稳定分布脉冲噪声下的常规数字调制信号的方法。采用归一化最小平均p范数自适应滤波算法的自适应滤波器,跟踪信号任一码元间隔内的单一频率,根据自适应滤波器权值的收敛值可以解调相应的码元。计算机仿真结果表明,此自适应滤波解调方法性能优越,抗脉冲干扰强,同时算法计算速度快,易于实现,具有很好的实用价值。     

利用迁移学习的量化核最小平均P范数算法

在α稳定分布噪声背景下,核最小平均P范数算法(KLMP)的性能显著优于核最小均方算法(KLMS),但KLMP算法的计算量和存储容量都随迭代次数线性增加,不便实际应用。针对此问题,该文应用迁移学习理论,将基于样本实例获得的总滤波器划分为具有局部紧支撑结构的子滤波器之和,每个子滤波器的训练分别受不同的输入驱动,提出了最近实例质心估计核最小平均P范数算法(NICE-KLMP);为进一步减小存储容量,将在线矢量量化应用到该算法中,提出最近实例质心估计量化核最小平均P范数算法(NICE-QKLMP)。α稳定分布噪声背景下的 Mackey-Glass 时间序列预测的仿真结果表明,NICE-KLMP和NICE-QKLMP算法的复杂度显著低于KLMP算法,抗脉冲噪声性能显著强于NICE-KLMS算法,与KLMP算法相当。      

α-稳定分布噪声环境下的非线性回声消除研究

针对广泛存在的非线性回声,以及在非高斯噪声环境下,传统回声消除器中自适应算法性能衰退,继而导致回声消除效果下降的情况,本文提出了一种基于最小离差准则的协同函数链接型自适应滤波回声消除方法.该方法使用归一化最小l_p范数算法更新线性和非线性函数扩展的自适应滤波器的权值,并将输出信号协同组合,以消除非线性回声.仿真实验结果表明,该方法在α-稳定分布噪声且非线性回声存在的情况下比传统回声消除方法具有更高的回声衰减增益.     

一种基于最小1-范数准则的TDOA估计算法

针对脉冲噪声条件下利用传统广义互相关法(Generalized Cross-Correlation,GCC)进行时延(TDOA,Time Difference of Arrival)估计性能退化问题,提出一种基于最小1-范数准则的TDOA参数估计算法.对于高斯噪声,传统GCC估计方法能够实现统计最优,但当噪声的统计分布为非高斯分布时,利用传统GCC参数估计方法的估计精度和鲁棒性急剧下降.利用最小1-范数准则,提出一种存在α-稳定分布重尾脉冲噪声环境下的TDOA估计算法.系统仿真实验与结果分析表明,与传统GCC方法和分数低阶矩(Fractional Lower Order Moments,FLOM)方法相比,该算法在鲁棒性和估计精度方面均有明显改善.     

Sparse Least Logarithmic Absolute Difference Algorithm with Correntropy-Induced Metric Penalty

Sparse adaptive filtering algorithms are utilized to exploit system sparsity as well as to mitigate interferences in many applications such as channel estimation and system identification. In order to improve the robustness of the sparse adaptive filtering, a novel adaptive filter is developed in this work by incorporating a correntropy-induced metric (CIM) constraint into the least logarithmic absolute difference (LLAD) algorithm. The CIM as an \(l_{0}\)-norm approximation exerts a zero attraction, and hence, the LLAD algorithm performs well with robustness against impulsive noises. Numerical simulation results show that the proposed algorithm may achieve much better performance than other robust and sparse adaptive filtering algorithms such as the least mean p-power algorithm with \(l_{1}\)-norm or reweighted \(l_{1}\)-norm constraints.     

Robust Multiuser Detection Method Based on Least <Emphasis Type="Italic">p</Emphasis>-Norm State Space Criterion

Alpha stable distribution is better for modeling impulsive noises than Gaussian distribution in wireless communication system. This class of process has no close form of probability density function and finite second order moments. In general, Wiener filter theory is not meaningful in α SG environments because the expectations may be unbounded. We proposed a new adaptive recursive least p-norm State space multiuser detection algorithm based on least p-norm of innovation process with infinite variances. The simulation experiments show that the proposed new algorithm is more robust than the conventional state space multiuser detection algorithm. Daifeng Zha was born in 1971 and received the B.S. degree in electrical engineering from Dalian University of Technology, Dalian, China, in 1995. He was a research engineer at ChineseHelicopter Research and Development Institute, Jingdezhen, China, from 1995 through 2000. He received the Ph.D degree in Dalian University of Technology in 2005. He is currently an associate professor in College of Electronic Engineering from Jiujiang University. His research interests include non-gaussian signal processing, array signal processing, underwater signal processing.     

Sparse LMS/F algorithms with application to adaptive system identification

Standard least mean square/fourth (LMS/F) is a classical adaptive algorithm that combined the advantages of both least mean square (LMS) and least mean fourth (LMF). The advantage of LMS is fast convergence speed while its shortcoming is suboptimal solution in low signal‐to‐noise ratio (SNR) environment. On the contrary, the advantage of LMF algorithm is robust in low SNR while its drawback is slow convergence speed in high SNR case. Many finite impulse response systems are modeled as sparse rather than traditionally dense. To take advantage of system sparsity, different sparse LMS algorithms with l_p‐LMS and l₀‐LMS have been proposed to improve adaptive identification performance. However, sparse LMS algorithms have the same drawback as standard LMS. Different from LMS filter, standard LMS/F filter can achieve better performance. Hence, the aim of this paper is to introduce sparse penalties to the LMS/F algorithm so that it can further improve identification performance. We propose two sparse LMS/F algorithms using two sparse constraints to improve adaptive identification performance. Two experiments are performed to show the effectiveness of the proposed algorithms by computer simulation. In the first experiment, the number of nonzero coefficients is changing, and the proposed algorithms can achieve better mean square deviation performance than sparse LMS algorithms. In the second experiment, the number of nonzero coefficient is fixed, and mean square deviation performance of sparse LMS/F algorithms is still better than that of sparse LMS algorithms. Copyright © 2013 John Wiley & Sons, Ltd.     

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.     

OFDM系统双选择性慢衰落信道的压缩感知估计

为了增强压缩感知框架里Sl0(Smoothedl0-norm)重构算法的抗噪性能,该文在其目标函数里添加一个误差容允项,并提出了一种改进型重构算法l2-Sl0(Smoothed l0-norm regularized least-square)。另外通过对多径信道的时延和多普勒频移参数构成的时频2维有界区域进行量化,将OFDM时频双选择性慢衰落信道估计问题建模为压缩感知理论中的稀疏信号重构问题,提出了一种采用l2-Sl0估计信道时频参数的方法。仿真结果表明在相同的噪声环境里,l2-Sl0的重构性能优于Sl010 dB左右;运用l2-Sl0的信道估计方法可获得接近于理想最小二乘法的估计性能,且该方法在低信噪比的场景里也能获得较高的估计准确度。     

Low complexity scalable MIMO sphere detection through antenna detection reordering

This paper describes a novel low complexity scalable multiple-input multiple-output (MIMO) detector that does not require preprocessing and the optimal squared l ²-norm computations to achieve good bit error (BER) performance. Unlike existing detectors such as Flexsphere that use preprocessing before MIMO detection to improve performance, the proposed detector instead performs multiple search passes, where each search pass detects the transmit stream with a different permuted detection order. In addition, to reduce the number of multipliers required in the design, we use l ¹-norm in place of the optimal squared l ²-norm. To ameliorate the BER performance loss due to l ¹-norm, we propose squaring then scaling the l ¹-norm. By changing the number of parallel search passes and using norm scaling, we show that this design achieves comparable performance to Flexsphere with reduced resource requirement or achieves BER performance close to exhaustive search with increased resource requirement.     

Sparse least mean p-power algorithms for channel estimation in the presence of impulsive noise

The least mean p-power (LMP) is one of the most popular adaptive filtering algorithms. With a proper p value, the LMP can outperform the traditional least mean square \((p=2)\), especially under the impulsive noise environments. In sparse channel estimation, the unknown channel may have a sparse impulsive (or frequency) response. In this paper, our goal is to develop new LMP algorithms that can adapt to the underlying sparsity and achieve better performance in impulsive noise environments. Particularly, the correntropy induced metric (CIM) as an excellent approximator of the \(l_0\)-norm can be used as a sparsity penalty term. The proposed sparsity-aware LMP algorithms include the \(l_1\)-norm, reweighted \(l_1\)-norm and CIM penalized LMP algorithms, which are denoted as ZALMP, RZALMP and CIMLMP respectively. The mean and mean square convergence of these algorithms are analysed. Simulation results show that the proposed new algorithms perform well in sparse channel estimation under impulsive noise environments. In particular, the CIMLMP with suitable kernel width will outperform other algorithms significantly due to the superiority of the CIM approximator for the \(l_0\)-norm.     

An improved sparsity-aware normalized least-mean-square scheme for underwater communication

Underwater communication (UWC) is widely used in coastal surveillance and early warning systems. Precise channel estimation is vital for efficient and reliable UWC. The sparse direct-adaptive filtering algorithms have become popular in UWC. Herein, we present an improved adaptive convex-combination method for the identification of sparse structures using a reweighted normalized least-mean-square (RNLMS) algorithm. Moreover, to make RNLMS algorithm independent of the reweighted $l_1$-norm parameter, a modified sparsity-aware adaptive zero-attracting RNLMS (AZA-RNLMS) algorithm is introduced to ensure accurate modeling. In addition, we present a quantitative analysis of this algorithm to evaluate the convergence speed and accuracy. Furthermore, we derive an excess mean-square-error expression that proves that the AZA-RNLMS algorithm performs better for the harsh underwater channel. The measured data from the experimental channel of SPACE08 is used for simulation, and results are presented to verify the performance of the proposed algorithm. The simulation results confirm that the proposed algorithm for underwater channel estimation performs better than the earlier schemes.     

模拟电路故障诊断L1估计及其神经网络解法

基于精确罚函数法,提出了新的求解L₁范致问题最优解的神经网络方法,它避免了Kennedy和Chua(1988)网络罚因子较大时性态变坏问题。对Bandler(1982)提出的模拟电路故障诊断L₁范数法进行了改进,将线性约束L₁问题转化为非线性约束L₁问题,并用新的神经网络方法求解,计算量小。模拟实验表明,所提神经网络方法和改进的模拟电路故障诊断L₁范数方法是可行的。