参数化自适应图像盲分离算法

针对超高斯与亚高斯图像分离上存在的不足,本文提出一种等权重双高斯概率密度模型,可以有效估计超高斯、亚高斯图像的概率分布,该模型从区分超高斯与亚高斯分布的本质出发,通过在线学习确定模型参数实现盲分离.通过对混合图像的实验,表明该算法比已有算法具有更好的分离性能和收敛性,且方法简单易于工程实现.     

一种改进牛顿法的盲源分离算法

针对盲信号分离中超高斯信号亚高斯信号混叠难以分离的问题,提出一种基于改进牛顿法的盲源分离算法.该方法引入开关准则,利用随机变量的峭度来区分信号的类型,不同的信号选择不同的非线性函数,通过牛顿迭代方法求出分离矩阵,实现同时含有超高斯信号和亚高斯信号的杂系混合信号的盲源分离.仿真实验表明了该方法计算量小,易于实现,对于杂系...     

基于多用户检测的ICA算法

讨论了通信系统中常用的ICA算法,并用性能指数对算法的性能进行了评估.独立分量信号用亚高斯信号、超高斯信号描述,将若干个独立分量信号进行线性混合以此来模拟通信系统中的信号.实验结果显示JADE-ICA的算法性能指数最低,性能最好,是通信系统较好的选择.     

复杂电磁网络环境下的抗干扰技术研究与仿真

在完成复杂网络环境下抗干扰的过程中,各种干扰信号构成的混合信号极为复杂,当前的有关信息最大化的复杂电磁网络环境下抗干扰方法,仅能将复杂信号分离成超高斯分布或亚高斯函数分布信号,无法进一步细化,不能实现复杂网络环境下的抗干扰,提出一种关于波束赋形技术的复杂电磁网络环境下的抗干扰方法,从时域与频域两个角度分析复杂电磁网络环境信号;依据波束形成对空间传感器的采样加权进行求和操作,提高某一特定方向传播波信号,避免其它方向的干扰.对来波方向和阵列法线方向的夹角进行定义,形成波束后的输出信号,给出阵列的方向矩阵以及方向向量,利用Bulter变换矩阵完成阵元域到波束域之间的转换.仿真结果表明,所提方法具有很高的抗干扰能力.     

基于品质函数估计的非线性盲源分离算法

研究非线性盲源信号分离优化问题。由于混合信号同时包含超高斯和亚高斯信号且混合信号具有很强的非线性时,传统的非线性盲源分离算法中对于品质函数的选取一般都是通过经验,现有算法难以取得理想的分离效果。在Pearson模型的基础上提出了一种新的估计品质函数的方法,算法能够成功地估计出次高斯(sub-Gaussian)和超高斯(super-Gaussi-an)混合信号的品质函数,同时克服了Pearson模型对同类信号只能估计得到相同的品质函数的缺陷,提高了算法的估计精度。通过在MATLAB仿真验证了算法的可行性和有效性,成功估计出源信号的品质函数且实现了非线性盲源分离。     

小波域非参数贝叶斯估计图像去噪

提出一类新的非参数贝叶斯估计器,估计器利用正态反高斯(NIG)分布作为先验模型.与广义高斯分布(GGD)、alpha稳定分布和贝塞尔K分布(BKF)相比,正态反高斯分布能更加精确地对图像小波系数分布进行拟合.在二次型贝叶斯规则下,推导出基于正态反高斯分布的后验条件均值估计.最后,对图像进行去噪实验.实验结果表明,与最新提出的算法相比,该方法获得更高的峰值信噪比增益和好的视觉效果.     

一种基于KS距离的OFDM子载波数估计法

针对正交频分复用(OFDM)信号子载波数估计的问题,利用OFDM信号的高斯性,提出一种基于KS距离的子载波数估计法。侦收端DFT模块输出的KS距离在DFT点数与发射端匹配时最小。理论分析及仿真结果证明,该方法能区分高斯分布与非高斯分布,正确估计OFDM信号的子载波数。     

在线提高卡尔曼滤波跟踪精度的参数研究

为了在线提高卡尔曼滤波算法（KF）的跟踪精度,对随机序列进行高斯度的定义,将随机序列的分布分为超高斯、高斯、次高斯和非高斯,找出KF可以工作的范围。针对噪声服从次高斯分布时,KF跟踪精度不高,介绍了两个可以判断KF使用过程中设定的噪声协方差与实际是否一致的参数。提出了参数自适应的方法,使设定的噪声协方差与实际值可以自适应地一致,从而提高了KF的跟踪精度。实验结果表明,噪声服从高斯和超高斯分布时,KF跟踪精度很高;噪声服从次高斯分布时,若噪声协方差的设定值与实际值不一致,跟踪误差会很大,对此使用了参数自适应法,可以大大提高KF的跟踪精度。     

涡街流量计信号的高阶统计量特征

涡街信号的正确分析和有效处理是实现涡街流量计准确测量的先决条件之一.为研究涡街信号的非高斯性,提出了一种基于高阶统计量方法的涡街流量计信号分析的新方法.通过对涡街管壁差压信号的双谱分析,提取了不同流量下信号的非高斯特征.以信号的双谱幅度最大值作为特征参数,对不同流量下涡街信号偏离高斯分布的程度进行了定量估计.实验结果表明:涡街信号的非高斯性随着流量的增大而不断增加.这一研究结果为深入理解涡街现象、进一步优化涡街流量计的设计提供了有力的参考.     

数字水印容量简化分析及模型优化

根据图像数字水印基本原理和水印信道的构造及生成方式,从信息论的角度,对基于高斯噪声信道的数字水印容量进行探索。针对高斯信源分布具有最大的不确定性、能够在所有的二阶随机分布中提供最大信息熵的特点,分析在高斯分布情况下的整个水印信道通信过程,并引入平均互信息理论,给出基于高斯的水印信道容量的最大通信速率。同时分析加性噪声信道下的容量问题,将高斯分布扩展到非高斯分布,优化容量计算表达式,利用Matlab软件工具给出非高斯信源水印容量与受限失真度的2D和3D关系仿真曲线,并结合实际给出结果分析。     

Multiplicative neural noise can favor an independent components representation of sensory input

Arguments have been advanced to support the role of principal components (e.g., Karhunen-Loéve, eigenvector) and independent components transformations in early sensory processing, particularly for color and spatial vision. Although the concept of redundancy reduction has been used to justify a principal components transformation, these transformations per se do not necessarily confer benefits with respect to information transmission in information channels with additive independent identically distributed Gaussian noise. Here, it is shown that when a more realistic source of multiplicative neural noise is present in the information channel, there are quantitative benefits to a principal components or independent components representation for Gaussian and non-Gaussian inputs, respectively. Such a representation can convey a larger quantity of information despite the use of fewer spikes. The nature and extent of this benefit depend primarily on the probability distribution of the inputs and the relative power of the inputs. In the case of Gaussian input, the greater the disparity in power between dimensions, the greater the advantage of a principal components representation. For non-Gaussian input distributions with a kurtosis that is super-Gaussian, an independent components representation is similarly advantageous. This advantage holds even for input distributions with equal power since the resulting density is still rotationally asymmetric. However, sub-Gaussian input distributions can lead to situations where maximally correlated inputs are the most advantageous with respect to transmitting the greatest quantity of information with the fewest number of spikes.     

Cumulant-based inverse filters for blind deconvolution

Blind deconvolution of linear time-invariant (LTI) systems has received wide attention in various fields such as data communication and image processing. Blind deconvolution is concerned with the estimation of a desired input signal from a given set of measurements. This paper presents a technique for reconstructing the desired input from only the available corrupted data. The estimator is given in terms of an autoregressive moving average (ARMA) innovation model. This technique is based on higher order statistics (HOS) of a non-Gaussian output sequence in the presence of additive Gaussian or non-Gaussian noise. The algorithm solves a set of overdetermined linear equations using third-order cumulants of the given non-Gaussian measurements in the presence of additive Gaussian or non-Gaussian noise. The inverse filter is a finite impulse response (FIR) filter. Simulation results are provided to show the effectiveness of this method and compare it with a recently developed algorithm based on maximizing the magnitude of the kurtosis of estimate of the input excitation.     

Higher-Order Asymptotics of Mutual Information for Nonlinear Channels with Non-Gaussian Noise

Nonlinear channels with non-Gaussian noise where the transmitted signal is a random function of the input signal are considered. Under some assumptions on smoothness and the behavior of tails of the noise density function, higher-order asymptotics of the mutual information between the input and output signals in such channels is obtained, as the mean power of the input signal (or, equivalently, the signal-to-noise ratio) goes to zero.     

Stochastic Distribution Control of Singular Systems: Output PDF Shaping

This paper presents a new algorithm designed to control the shape of the output probability density function (PDF) of singular systems subjected to non-Gaussian input. The aim is to select a control input uk such that the output PDF is made as close as possible to a given PDF. Based on the B-spline neural network approximation of the output PDF, the control algorithm is formulated by extending the developed PDF control strategies of non-singular systems to singular systems. It has been shown that under certain conditions the stability of the closed-loop system can be guaranteed. Simulation examples are given to show the effectiveness of the proposed control algorithm.     

FIR system identification using fourth-order cumulants withapplication to channel equalization

Three algorithms for finite impulse response (FIR) system identification from output measurements, using fourth-order cumulants, are described. The impulse response is assumed to be complex, and the input is a complex independent and identically distributed (i.i.d) non-Gaussian sequence. The algorithms are based on a certain low-rank matrix constructed from the output cumulants. An application of the algorithms to blind equalization of digital communication channels is discussed and illustrated by some examples     

Nonlinear filtering for discrete-time linear systems withnon-Gaussian initial data

The optimal minimum mean-square error filtering problem is discussed for a linear system with non-Gaussian initial distribution. An input/output realization is derived using an absolutely continuous change of probability measure. A representation result is presented which facilitates the derivation of optimal filter realization     

Performance analysis of linear regulators with non-Gaussian Markovian disturbances†

Due to the complexity of non-Gaussian design, most control systems are designed via assumptions of Gaussian disturbances, oven for cases of non-Gaussian disturbances. Similarly, performance evaluations of systems designed via a Gaussian assumption when inputted with non-Gaussian disturbances are most difficult and rarely made. The present paper therefore presents a method for analysing such performances by deriving output probability structures for cases of input disturbances belonging to a class of non-Gaussian Markovian processes that are common to many chemical engineering processes. The analysis is based on considering the Chapman—Kolmogorov and the Fokker-Planck equations related to a two-state Markov process and its results are compared with the ease of Gaussian disturbances to facilitate the determination of the discrepancy between the performance expected by the Gaussian assumption and the actual performance.     

阈值阵列模型下的超阈值随机共振信噪比增益

研究了阈值阵列模型和超阈值随机共振现象.对该模型进行剖析,认为阈值阵列系统可以分解为单个阈值系统与集总平均器的级联.为了研究周期输入下的超阈值随机共振现象,理论分析了周期输入下的阈值阵列模型输出随机过程的统计特性,以输出信噪比增益作为随机共振的测度,固定输入信噪比,观测输出信噪比增益相对于阈值噪声方差的变化规律.证实当输入噪声为高斯噪声时,在阈值阵列系统中加入统计独立的高斯白噪声可使输出信噪比增益大于1,当输入噪声为非高斯噪声时,可获得更高的输出信噪比增益.     

Elementary quantum gates with Gaussian states

We study the question of converting initially Gaussian states into non-Gaussian ones by two- and three-photon subtraction to improve non-classical properties of the conditional optical fields. We show the photon subtraction may effectively generate non-Gaussian states only in case of small values of the mean values of the position and momentum operators. In particular, the photon-subtracted state can be made arbitrary close to Gaussian state in limiting case of large initial amplitude of displacement. Use of initial displacement in input Gaussian states opens wider prospects to manipulate them. In particular, realization of probabilistic Hadamard gate with input Gaussian states is discussed where photon subtraction is motive force able unevenly to increase measure of non-classicality of the output state. Subtraction of larger number of photons enables to increase fidelity and non-classical measure of the conditional states.