共查询到17条相似文献,搜索用时 203 毫秒
1.
针对混沌通信系统的非线性信道干扰问题,基于混沌信号重构理论和函数型连接神经网络理论,提出了一种横向滤波器与函数型连接神经网络组合(combination of transversal filter and functional link neural network,CFFLNN)的自适应非线性信道均衡器,并给出基于低复杂度归一化最小均方(NLMS)的自适应算法,并对该均衡器的稳定性以及收敛条件进行了分析.该非线性自适应均衡器充分利用了横向滤波器的快速收敛,以及函数型连接神经网络通过增大输入空间提高非线性逼近能力的特点,进一步提高均衡器的收敛速度和降低稳态误差.仿真研究表明:所提出的非线性自适应均衡器能够有效地消除线性和非线性信道干扰,均衡器输出信号能反映出混沌信号的特性,具有良好的抗干扰性能;且该均衡器的结构简单,收敛稳定性较好,易于工程实现.
关键词:
非线性信道
自适应均衡器
混沌吸引子
神经网络 相似文献
2.
3.
针对混沌通信系统中非线性信道干扰问题,基于混沌信号重构理论和Legendre正交多项式结构,提出了一种自适应神经Legendre正交多项式信道均衡器,并给出相应的归一化最小均方算法. 仿真研究表明:所提出的自适应神经Legendre正交多项式信道均衡器能有效地消除线性和非线性信道干扰,均衡器输出信号能反映出混沌信号的特性,具有良好的抗干扰性能.该均衡器的结构简单,权系数参数较少,收敛稳定性较好.
关键词:
Legendre 正交多项式
信道均衡
混沌吸引子
神经网络 相似文献
4.
不需要训练序列的盲均衡技术可以有效地节省水声通信带宽,消除码间干扰,提高水声通信效率和质量。以前馈神经网络(FNN)作为盲均衡器,既适用于最小相位信道,也适用于非最小相位信道,包括非线性信道,但是前馈神经网络在实际的应用中其网络拓扑结构的选取和初始权重的确定缺乏理论依据,且其训练主要依靠BP算法,存在收敛速度慢、容易陷入局部极值及“过学习”的问题。为此,本文提出了一种遗传优化神经网络的水声信道盲均衡算法(GA—BP),对前馈神经网络拓扑结构和网络权重同时优化,有效地克服了传统前馈神经网络盲均衡的缺陷,提高了前馈神经网络盲均衡的泛化性能并加强了跟踪时变信道的能力和对信道突变的适应能力。水池试验结果证明了文中提出的遗传优化神经网络水声信道盲均衡算法的有效性,与直接前馈神经网络盲均衡相比较,均衡性能明显得到了提高。 相似文献
5.
提出了一种基于神经网络的多输入多输出(MIMO)均衡器,并在大容量模分-波分复用通信系统中进行了实验验证。该系统基于6模掺铒光纤放大器实现了16通道波分复用双极化48 Gbaud 16阶正交振幅调制(16QAM),在LP01、LP02、LP11a、LP11b、LP21a、LP21b六种模式上传输了100 km少模光纤(FMF)。为降低非线性的影响,在接收端数字信号处理中,采用基于多标签技术的MIMO神经网络均衡器,能够显著提升系统性能。实验结果表明,经100 km的FMF传输,MIMO神经网络均衡器的强大性能使得系统的比特误码率能满足15%软判决前项纠错阈值要求。 相似文献
6.
针对稀疏水声信道的长时延扩展及梯度下降的权值迭代方案导致的神经网络均衡器收敛速度慢的问题,提出了近似L0范数约束的BP神经网络均衡器。首先在传统BP网络均衡器基础上增加判决反馈项,然后在代价函数中对均衡器输入层到隐含层的权值增加L0范数约束,构造新的代价函数,利用高斯族函数近似L0范数约束,并根据不同隐层神经元节点输出权值的L2范数设定近似参数。仿真结果表明,稀疏信道条件下,本方法相比传统的BP网络均衡器收敛速度更快,误码率更低,可以有效提升神经网络均衡器的性能。 相似文献
7.
在高速相干光通信系统中,完全使用电子色散补偿时会引入均衡增强相位噪声.本文提出在已有10Gbit/s光纤通信链路上使用电子色散补偿来补偿残留色散的混合色散补偿方案,实现了特定通道100Gbit/s以上高速数据传输.使用虚拟光学仪器软件仿真了在112Gbit/s相干光通信系统中,分别采用有限脉冲响应均衡器和重叠频域均衡器对现有光纤信道进行残留色散补偿后的系统性能.仿真结果表明:相同的抽头长度下,有限脉冲响应均衡器相比重叠频域均衡器有更好的残留色散补偿能力,并且有限脉冲响应均衡器均衡性能更稳定而且计算复杂度更低.因而,有限脉冲响应均衡器相较于重叠频域均衡器更适于混合色散补偿. 相似文献
8.
9.
水声信道的典型特点为多普勒频移严重、可利用带宽窄以及强多径干扰。空间分集均衡技术是相干水声通信中克服信道多径干扰,消除码间干扰的一种有效手段。为了极大化地输出阵增益,结合无源相位共轭方法和多通道均衡算法,本文设计了组合信噪干比的全新信道评价方法。利用改进的Sigmoid函数对各通道接收信号的幅度进行加权处理;采用二阶锁相环跟踪各通道信号的相位变化,实现各通道信号同相累加。将各通道低通滤波后的信号能量归一化,采用了分数阶-判决反馈分集均衡器,加入各通道权重系数实现了水声通信系统的分集均衡接收。仿真结果和湖试数据处理结果均表明,优化的幅相加权分集均衡接收算法能抵消多径和噪声的干扰,性能优于等增益合并接收算法。湖试数据处理结果误码率降低了1.8%。 相似文献
10.
针对盲均衡算法收敛速度较慢的问题,提出一种结合改进支持向量机和常数模算法的水声信道盲均衡算法。该算法首先利用具有优异小样本学习能力的支持向量机进行盲均衡器权系数初始化,在完成初始化后切换至运算量较小的常数模算法。考虑到支持向量机本身非自适应运算的限制,在时变水声信道条件下利用经典支持向量机获得的均衡器初始权向量与切换后的信道仍然存在失配。因此,本文导出时变条件下的改进支持向量机用于盲均衡器初始化,改善算法切换时的权系数失配,并结合分数间隔结构和内嵌数字锁相环进一步提高盲均衡算法性能。仿真和湖试实验结果表明:在时变水声信道条件下,本文算法的收敛性能优于经典支持向量机盲均衡算法。 相似文献
11.
We investigate underwater acoustic (UWA) channel equalization and introduce hierarchical and adaptive nonlinear (piecewise linear) channel equalization algorithms that are highly efficient and provide significantly improved bit error rate (BER) performance. Due to the high complexity of conventional nonlinear equalizers and poor performance of linear ones, to equalize highly difficult underwater acoustic channels, we employ piecewise linear equalizers. However, in order to achieve the performance of the best piecewise linear model, we use a tree structure to hierarchically partition the space of the received signal. Furthermore, the equalization algorithm should be completely adaptive, since due to the highly non-stationary nature of the underwater medium, the optimal mean squared error (MSE) equalizer as well as the best piecewise linear equalizer changes in time. To this end, we introduce an adaptive piecewise linear equalization algorithm that not only adapts the linear equalizer at each region but also learns the complete hierarchical structure with a computational complexity only polynomial in the number of nodes of the tree. Furthermore, our algorithm is constructed to directly minimize the final squared error without introducing any ad-hoc parameters. We demonstrate the performance of our algorithms through highly realistic experiments performed on practical field data as well as accurately simulated underwater acoustic channels. 相似文献
12.
13.
The balanced steady-state free precession (bSSFP) MR sequence is frequently used in clinics, but is sensitive to off-resonance effects, which can cause banding artifacts. Often multiple bSSFP datasets are acquired at different phase cycling (PC) angles and then combined in a special way for banding artifact suppression. Many strategies of combining the datasets have been suggested for banding artifact suppression, but there are still limitations in their performance, especially when the number of phase-cycled bSSFP datasets is small. The purpose of this study is to develop a learning-based model to combine the multiple phase-cycled bSSFP datasets for better banding artifact suppression. Multilayer perceptron (MLP) is a feedforward artificial neural network consisting of three layers of input, hidden, and output layers. MLP models were trained by input bSSFP datasets acquired from human brain and knee at 3T, which were separately performed for two and four PC angles. Banding-free bSSFP images were generated by maximum-intensity projection (MIP) of 8 or 12 phase-cycled datasets and were used as targets for training the output layer. The trained MLP models were applied to another brain and knee datasets acquired with different scan parameters and also to multiple phase-cycled bSSFP functional MRI datasets acquired on rat brain at 9.4T, in comparison with the conventional MIP method. Simulations were also performed to validate the MLP approach. Both the simulations and human experiments demonstrated that MLP suppressed banding artifacts significantly, superior to MIP in both banding artifact suppression and SNR efficiency. MLP demonstrated superior performance over MIP for the 9.4T fMRI data as well, which was not used for training the models, while visually preserving the fMRI maps very well. Artificial neural network is a promising technique for combining multiple phase-cycled bSSFP datasets for banding artifact suppression. 相似文献
14.
Preisig JC 《The Journal of the Acoustical Society of America》2005,118(1):263-278
Equations are derived for analyzing the performance of channel estimate based equalizers. The performance is characterized in terms of the mean squared soft decision error (sigma2(s)) of each equalizer. This error is decomposed into two components. These are the minimum achievable error (sigma2(0)) and the excess error (sigma2(e)). The former is the soft decision error that would be realized by the equalizer if the filter coefficient calculation were based upon perfect knowledge of the channel impulse response and statistics of the interfering noise field. The latter is the additional soft decision error that is realized due to errors in the estimates of these channel parameters. These expressions accurately predict the equalizer errors observed in the processing of experimental data by a channel estimate based decision feedback equalizer (DFE) and a passive time-reversal equalizer. Further expressions are presented that allow equalizer performance to be predicted given the scattering function of the acoustic channel. The analysis using these expressions yields insights into the features of surface scattering that most significantly impact equalizer performance in shallow water environments and motivates the implementation of a DFE that is robust with respect to channel estimation errors. 相似文献
15.
Artificial Neural Networks are developed as an important technique for equalization and have been widely used to mitigate the nonlinear effects in coherent optical systems. For the compensation of nonlinearities in coherent optical orthogonal frequency division multiplexing technique, the most popular artificial neural network model is a multilayer perceptron (MLP), as it is able to perform complex mapping between input and output spaces with significant success. However due to the complexity of multilayer perceptron nonlinear equalizer (MLP-NLE) model training of neural network is difficult. To overcome computational complexity issues of MLP-NLE, a single neuron based functional link artificial neural network nonlinear equalizer (FLANN-NLE) has been developed in this paper. Better performance of an equalizer is attributed to the usage of aPSO-BP algorithm for training the FLANN-NLE. The proposed FLANN-NLE surpasses the existing works both in terms of Q-Factor and computational complexity. For a fiber length of 1000 km and at launch power of ?6 dBm, the improvement in Q-Factor is approximately equal to 3.3 and 1 dB in contrast to the previously reported values of approximately 3 and 0.7 dB at bit rate of 40 and 80 Gbps respectively. 相似文献
16.
We realized a wavelength tunable optical filter based on a fiber Bragg grating using multilayer piezoelectric transducers (MLP). The Bragg wavelength of the filter can be easily tuned in proportion to an applied low DC voltage. The tuning range efficiency was as high as 0.2 nm/V. We realized a 10 nm Bragg wavelength shift by applying as low as 50 V to the MLP. The MLP was also used in a higher order dispersion equalizer which consists of a pair of nonlinearly chirped gratings. A zero dispersion wavelength shift of 7 nm was successfully realized for the equalizer. 相似文献
17.
Hui Cao Junqiang Sun Guojie Chen Weicheng Chen Dexiu Huang 《Fiber and Integrated Optics》2006,25(4):279-286
In this article, we propose a novel superstructure fiber Bragg grating (SFBG)-based comb gain equalizer for fiber-optical parametric amplifiers (FOPAs). The target spectrum of the gain equalizer is obtained by two steps. Initially, we calculate the spectrum according to the inverse of the gain spectrum of the FOPA. Then we apply a channel-by-channel windowing method to shape each channel and adopt a Gaussian hypergeometric function to describe the rising and descending edges of each channel. The SFBG is finally synthesized with layer-peeling inverse scattering technique. Using the designed SFBG, the gain variation of the FOPA is flattened to be within ±0.4 dB for 16 ITU channels and the best channel isolation is as high as 35 dB. It should be pointed out that the proposed method could also be used to design gain equalizers for other optical amplifiers. 相似文献