Multilayer perceptron-based DFE with lattice structure

The severely distorting channels limit the use of linear equalizers and the use of the nonlinear equalizers then becomes justifiable. Neural-network-based equalizers, especially the multilayer perceptron (MLP)-based equalizers, are computationally efficient alternative to currently used nonlinear filter realizations, e.g., the Volterra type. The drawback of the MLP-based equalizers is, however, their slow rate of convergence, which limit their use in practical systems. In this work, the effect of whitening the input data in a multilayer perceptron-based decision feedback equalizer (DFE) is evaluated. It is shown from computer simulations that whitening the received data employing adaptive lattice channel equalization algorithms improves the convergence rate and bit error rate performances of multilayer perceptron-based DFE. The adaptive lattice algorithm is a modification to the one developed by Ling and Proakis (1985). The consistency in performance is observed in both time-invariant and time-varying channels. Finally, it is found in this work that, for time-invariant channels, the MLP DFE outperforms the least mean squares (LMS)-based DFE. However, for time-varying channels comparable performance is obtained for the two configurations.     

Neural FIR adaptive Laguerre equalizer with a gradient adaptive amplitude for nonlinear channel in communication systems

To mitigate the linear and nonlinear distortions in communication systems, two novel nonlinear adaptive equalizers are proposed on the basis of the neural finite impulse response (FIR) filter, decision feedback architecture and the characteristic of the Laguerre filter. They are neural FIR adaptive decision feedback equalizer (SNNDFE) and neural FIR adaptive Laguerre equalizer (LSNN). Of these two equalizers, the latter is simple and with characteristics of both infinite impulse response (IIR) and FIR filte...     

Legendre神经网络非线性信道均衡

在分析Chebyshev正交多项式神经网络非线性滤波器的基础上，利用Legendre正交多项式快速逼近的优良特性以及判决反馈均衡器的结构特点，提出了两种新型结构的非线性均衡器，并利用NLMS算法，推导出自适应算法．仿真表明，无论通信信道是线性还是非线性，Legendre神经网络自适应均衡器与Chebyshev神经网络均衡器的各项性能均接近，而Legendre神经网络判决反馈自适应均衡器能够更有效地消除码间干扰和非线性干扰，误码性能也得到较好的改善．     

阶数自适应可变均衡器算法的研究与仿真

自适应判决反馈均衡器（OVE）f~跟踪信道时变响应并自动调整抽头系数,解决数字通信中因信道衰减和噪声引起的符号间干扰问题,从而大大降低通信系统误码率。针对在自适应均衡过程中均衡器阶数难以确定的问题,根据最优估计理论,分析判决反馈均衡器结构,研究DFE的抽头长度对均衡器均方误差性能的影响,在此基础上提出阈值可变动态长度算法,找出最小均方误差与滤波器阶数之间的折中。Matlab分析和仿真结果显示,当信道衰减和符号问干扰较严重时,均衡器阶数收敛在30阶左右,且误差可以收敛在较小范围内跟踪信道响应,并在瞬时累计均方误差准则下收敛到滤波器最优阶数。     

Complex-bilinear recurrent neural network for equalization of adigital satellite channel

Equalization of satellite communication using complex-bilinear recurrent neural network (C-BLRNN) is proposed. Since the BLRNN is based on the bilinear polynomial, it can be used in modeling highly nonlinear systems with time-series characteristics more effectively than multilayer perceptron type neural networks (MLPNN). The BLRNN is first expanded to its complex value version (C-BLRNN) for dealing with the complex input values in the paper. C-BLRNN is then applied to equalization of a digital satellite communication channel for M-PSK and QAM, which has severe nonlinearity with memory due to traveling wave tube amplifier (TWTA). The proposed C-BLRNN equalizer for a channel model is compared with the currently used Volterra filter equalizer or decision feedback equalizer (DFE), and conventional complex-MLPNN equalizer. The results show that the proposed C-BLRNN equalizer gives very favorable results in both the MSE and BER criteria over Volterra filter equalizer, DFE, and complex-MLPNN equalizer.     

基于不同位置小波变换的盲均衡器研究*

目前引入小波变换的自适应均衡器均是将正交多小波变换放置在均衡器(前向滤波器)之前以加快收敛。以常模判决反馈均衡器(CMA-DFE)为例,根据平衡正交多小波变换是放置在前向滤波器还是反馈滤波器之前,研究了三个均衡器,即常规的基于前馈正交多小波变换常模判决反馈盲均衡器(MWT-CMA-DFE)、基于反馈正交多小波变换的常模判决反馈盲均衡器(FMWT-CMA-DFE)和基于双正交多小波变换的常模判决反馈盲均衡器(DMWT-CMA-DFE),分析了其各自的复杂度。水声信道仿真结果表明:与CMA-DFE、MWT-CMA-DFE和FMWT-CMA-DFE相比,DMWT-CAM-DFE具有更快的收敛速度和跟踪时变信道的能力,且消除了相位旋转。     

基于UKF的自适应DFE信道均衡

针对信道的线性和非线性失真,在分析简化的非线性滤波的基础上,利用判决反馈的结构特点对其进行扩展,提出了基于UKF滤波的判决反馈均衡器,仿真表明,UKF滤波算法能降低系统均方误差性能。     

An adaptive decision feedback equalizer based on the combination of the FIR and FLNN

To compensate the linear and nonlinear distortions and to track the characteristic of the time-varying channel in digital communication systems, a novel adaptive decision feedback equalizer (DFE) with the combination of finite impulse response (FIR) filter and functional link neural network (CFFLNNDFE) is introduced in this paper. This convex nonlinear combination results in improving the convergence speed while retaining the lower steady-state error at the cost of a small increasing computational burden. To further improve the performance of the nonlinear equalizer, we derive here a novel simplified modified normalized least mean square (SMNLMS) algorithm. Moreover, the convergence properties of the proposed algorithm are analyzed. Finally, computer simulation results which support analysis are provided to evaluate the performance of the proposed equalizer over the functional link neural network (FLNN), radial basis function (RBF) neural network and linear equalizer with decision feedback (LMSDFE) for time-invariant and time-variant nonlinear channel models in digital communication systems.     

Pipelined functional link artificial recurrent neural network with the decision feedback structure for nonlinear channel equalization

This paper presents a computationally efficient nonlinear adaptive filter by a pipelined functional link artificial decision feedback recurrent neural network (PFLADFRNN) for the design of a nonlinear channel equalizer. It aims to reduce computational burden and improve nonlinear processing capabilities of the functional link artificial recurrent neural network (FLANN). The proposed equalizer consists of several simple small-scale functional link artificial decision feedback recurrent neural network (FLADFRNN) modules with less computational complexity. Since it is a module nesting architecture comprising a number of modules that are interconnected in a chained form, its performance can be further improved. Moreover, the equalizer with a decision feedback recurrent structure overcomes the unstableness thanks to its nature of infinite impulse response structure. Finally, the performance of the PFLADFRNN modules is evaluated by a modified real-time recurrent learning algorithm via extensive simulations for different linear and nonlinear channel models in digital communication systems. The comparisons of multilayer perceptron, FLANN and reduced decision feedback FLANN equalizers have clearly indicated the convergence rate, bit error rate, steady-state error and computational complexity, respectively, for nonlinear channel equalization.     

基于深度神经网络的高速信道自适应均衡器

高速串行接口是提高高性能互连网络带宽的关键技术,而信道均衡器则是提高信号完整性的核心部件.利用现代数字信号处理(DSP)结构,提出了基于深度神经网络(DNN)的高速信道均衡研究方法,此方法在面向未来50 GB以上的高速信道时,克服了传统判决反馈均衡器(DFE)的判决速度受限于反馈回路的固有缺陷问题.仿真结果表明,在采用...     

一种变步长LMS算法在远程水声通信中的研究应用

在远距离水声通信中,信道时变多径干扰严重,相位波动大,信噪比低;采用传统的固定步长自适应算法的通信系统性能不稳定;为了更好地解决这一问题,提出了自适应变步长判决反馈均衡器联合二阶锁相环的自适应LMS算法;利用32kHz的采样频率信号进行采样,并进行能量归一化处理,随后,进行相干解调和低通滤波,对信号进行抽样;对比分析了两种不同的接收机,试验结果表明文中提出的算法优于传统的固步长LMS算法,并且在远距离水声通信中是可行的。     

OFDM系统中基于CE-BEM信道建模的低复杂度均衡*

在移动正交频分复用（OFDM）系统中,时变信道引起子载波间干扰（ICI）,从而导致系统性能严重下降。均衡作为消除ICI的主要手段而被广泛采用,但是大多数情况下,由于需要进行高阶矩阵的求逆运算,导致均衡面临着运算复杂度过高的问题。提出采用复指数基扩展模型（CE-BEM）对时变信道进行建模,并利用估计得到的模型系数直接构造判决反馈均衡器（DFE）,从而避免了矩阵求逆运算,大大降低了运算复杂度。同时,该DFE通过理论分析和仿真实践均被证明具有良好的均衡效果,能有效地消除ICI并改善系统性能。     

Using recurrent neural networks for adaptive communication channelequalization

Nonlinear adaptive filters based on a variety of neural network models have been used successfully for system identification and noise-cancellation in a wide class of applications. An important problem in data communications is that of channel equalization, i.e., the removal of interferences introduced by linear or nonlinear message corrupting mechanisms, so that the originally transmitted symbols can be recovered correctly at the receiver. In this paper we introduce an adaptive recurrent neural network (RNN) based equalizer whose small size and high performance makes it suitable for high-speed channel equalization. We propose RNN based structures for both trained adaptation and blind equalization, and we evaluate their performance via extensive simulations for a variety of signal modulations and communication channel models. It is shown that the RNN equalizers have comparable performance with traditional linear filter based equalizers when the channel interferences are relatively mild, and that they outperform them by several orders of magnitude when either the channel's transfer function has spectral nulls or severe nonlinear distortion is present. In addition, the small-size RNN equalizers, being essentially generalized IIR filters, are shown to outperform multilayer perceptron equalizers of larger computational complexity in linear and nonlinear channel equalization cases.     

Blind equalization using parallel Bayesian decision feedback equalizer

The purpose of this paper is to propose a new method for blind equalization using parallel Bayesian decision feedback equalizer (DFE). Blind equalization based on decision-directed algorithm, including the previous proposed Chen’s blind Bayesian DFE, cannot give the correct convergence without the suitable initialization corresponding to the small inter-symbol interference. How to find the suitable initialization becomes the key for the correct convergence. Here, the “start” vector with several states is used to obtain several channel estimates which are the initial channel estimates in proposed method. In these initial channel estimates, the best one which has converged toward the correct result in some degree must exist. The decision-directed algorithm for parallel blind Bayesian DFE is purchased from these initial channel estimates respectively. Evaluating the Bayesian likelihood which is defined as the accumulation of the natural logarithm of the Bayesian decision variable, the correct channel estimates corresponding to the maximum Bayesian likelihood can be found. Compared with Chen’s blind Bayesian DFE, the proposed method presents better convergence performance with less computational complexity. Furthermore, the proposed algorithm works satisfactorily even for channel with severe ISI and in-band spectral null, while Chen’s blind Bayesian DFE fails.     

一种减小DTV接收机DFE误差传播的新算法

对于减少基于残留边带调制（VSB）的数字电视（DTV）接收机的符号间干扰（ISI），尽管判决反馈均衡器（DFE）是一种非常有效的方案，但这种方案由于受误差传播的影响而降低了接收质量。为减少误差传播，提出了一种使用软判决的DFE算法。该优化算法在判决器中使用了双曲正切函数，以改善DFE对抗误差传播的能力。此外，为了加快误差传播的仿真过程，还对反馈部分的抽头权值更新过程做了一个简单而有效的修改。计算机仿真结果表明，新算法对抗误差传播的性能远优于疑符算法，与理想DFE具有近似的表现。     

基于判决反馈结构的自适应均衡算法仿真研究

在数字通信中,接收信号通常会受到码间干扰的影响,尤其是在多径衰落无线信道环境中,这种现象更为严重。采用自适应均衡技术可以对信道响应进行补偿。由于在数字通信系统中,信道往往为非最小相位系统,此时线性均衡器性能不佳,因此该文对比研究了非线性结构的自适应波特间隔判决反馈均衡器和自适应分数间隔判决反馈均衡器,并对其性能进行了计算机仿真。仿真结果表明,对于非最小相位信道,自适应分数间隔判决反馈均衡器的性能优于波特间隔判决反馈均衡器。     

采用LMS算法的频域均衡技术研究

LMS(最小均方)算法是一种经典自适应算法,最初应用于时域均衡.本文采用LMS算法,根据信道的特性来更新频域均衡器的均衡系数,实验结果表明该算法可明显改善频域均衡系统的性能.     

基于SCFNN之PAM非线性信道均衡器成效研究

自组织型模糊类神经网络(SCFNN)可依据一定的法则自我构建神经网络的组织结构,从而适用于当前控制对象;多层神经元是传统的类神经网络,广泛应用于各个领域;倒传递学习法与最陡坡降法相结合,可使以上两种类神经网络进行有效的融合;目前,信道均衡器上的系统架构种类非常多,各种类神经网络应用于信道均衡器也颇为普遍;在研究SCFNN的基础上,将其应用于通道均衡器确实可行,效果良好;比较了SCFNN与MLP在通道均衡器的成效;仿真表明,在相同通道环境下,SCFNN的训练收敛速度、位错误率与系统敏感度优于MLP,完成结构学习后SCFNN的结构也颇为精简。     

基于MBER准则的变阶长自适应均衡器

提出了基于最小误比特率（MBER）准则的变阶长自适应均衡算法--FT-MBER算法。变阶长自适应均衡是未知多径信道均衡的重要技术,准确估计自适应均衡器最佳阶长能同时实现低复杂度和较好的均衡性能,而传统的最小均方误差（MMSE）算法稳态误比特率性能不理想。FT-MBER算法以最小化BER为代价函数,把不同阶长均衡器产生的误比特率之差作为因子调节伪分数阶长,当伪分数阶长变化大于阈值时更新阶长。仿真结果表明该算法比MMSE算法能更有效抑制码间干扰并能准确估计MBER准则下的均衡器最佳阶长。     

Adaptive MMSE decision feedback equalizer for asynchronous CDMA with erasure algorithm

Adaptive decision feedback equalizer with erasure algorithm (E-DFE) is proposed for asynchronous code division multiple access (CDMA) transmission, which not only combats intersymbol interference (ISI) and multiple access interference (MAI) but also reduces the effects of error propagation in the presence of Gaussian background noise. To reduce the possibility of feeding back the wrong decisions, the output of the feedforward filter of the E-DFE is processed before it is fed back to the feedback filter. Specifically, the focus is on the performance of E-DFE using soft-slicer based on a novel erasure algorithm. In addition, the fully connected feedback filter of E-DFE has been used to eliminate ISI due to other active users. Comparison of the performance of conventional decision feedback equalizer (C-DFE) and E-DFE over slowly varying frequency selective fading channel is presented to show the advantages of E-DFE in terms of reduced average bit error rate performance. Simulation results are also presented to show the substantial improvement in its performance under near-far situations and the sudden change in the signal power of the desired user.