小波分析在信号去噪声中的应用

小波分析是近年来发展起来的一种数学方法,在信号与图象处理中有重要的应用.中值滤波是信号处理中常用的一种非线性滤波器,它能够有效地消除瞬时脉冲干扰,并且能够很好地保持信号的边缘信息,在信号和图象处理中得到广泛应用.对中值滤波器与小波变换的结合进行了比较系统的研究.通过实例说明中值滤波器与小波变换相结合具有比单一滤波器更好的效果.     

基于小波分解和ANFIS模型的CPI统计数据预测

介绍应用小波分析理论解决时间序列统计数据的测量误差消除问题,实例证明借助离散小波分解与重构手段,可有效地从误差干扰的统计数据序列中提取统计数据的原始特征.完成CPI经济序列数据预测,为CPI统计数据的误差消除引入一种有效方法.     

基于小波分析的ARIMA模型对上证指数的分析与预测

股票价格的预测一直受到广泛关注,其预测方法虽然很多,但是往往存在预测精度有限、容易陷入局部极小等问题.为了提高股票价格预测的准确性,提出了基于小波分析的A砒MA模型的股票价格预测方法,同时利用该方法对上证指数收盘价的月平均值进行实例分析,并与其他方法的预测结果进行了比较,结果表明了提出方法的有效性.     

芬兰淡水湖冰下溶解氧浓度变化规律的离散小波分析北大核心

以离散小波变换的多尺度分析理论为依据,用Daubechies系列小波对芬兰Valkea-kotinen淡水湖第二测点自2011年1月13日至5月17日不同深度溶解氧浓度的采集数据进行分解与重构.通过db1-db6小波分解效果比较,发现db4小波的重构效果较好.采用db4小波对该位置各深度溶解氧浓度进行多尺度分析,得到数据的低频和高频重构曲线,分析曲线的变化规律.最后,利用离散小波变换尺度为2的幂次这一特点,给出有利于数据分析的测量时间间隔.     

芬兰淡水湖冰下溶解氧浓度变化规律的离散小波分析

以离散小波变换的多尺度分析理论为依据,用Daubechies系列小波对芬兰Valkea-kotinen淡水湖第二测点自2011年1月13日至5月17日不同深度溶解氧浓度的采集数据进行分解与重构.通过db1-db6小波分解效果比较,发现db4小波的重构效果较好.采用db4小波对该位置各深度溶解氧浓度进行多尺度分析,得到数据的低频和高频重构曲线,分析曲线的变化规律.最后,利用离散小波变换尺度为2的幂次这一特点,给出有利于数据分析的测量时间间隔.     

小波分析及信源熵在股市预测分析中的应用

提出了一种预测股市行情的新指标——信源熵 ,结合小波分析和 MATLAB工具来分析预测股票的未来走势 .并用实例说明了信源熵和小波分析在预测股票的走势上有很大优越性和准确性 .     

小波方法及其力学应用研究进展

小波理论在进行信号处理与函数逼近时体现出非常独特的时频局部性与多分辨分析能力,小波基函数则可兼具正交性、紧支性、低通滤波与插值性等优良的数学性质,这均使得小波分析理论在计算数学与计算力学领域具有很大的应用潜力,也进一步为这些领域的突破性发展带来了新的契机.自20世纪90年代以来,大量的研究已经证明,基于小波理论的数值方...     

对称-反对称多小波的构造

本文从多小波的多分辨分析出发 ,给出了一种由双正交单小波构造对称 反对称多小波的新方法 ,并以传统 9 7单小波为例构造了二重对称 反对称多小波 .     

小波神经网络在高维非线性系统辨识中的应用研究

在建立小波神经网络模型的基础上,提出了利用小波神经网络对高维非线性系统进行辨识的方法,得出了高维非线性系统的辨识算法,并通过实例仿真说明了系统的泛化能力得到有效提高,获得了具有良好自适应能力的小波网络.     

基于小波基函数插值的界面裂纹分析方法

利用小波的高分辨率和具有紧支性的特点将小波插值基函数引入到界面裂纹分析 ,针对裂纹面的应力奇异特点 ,采用了不同分辨率的插值方法 ,提出了基于广义变分原理的小波计算格式 ,并通常计算实例对所提方法进行验证     

一种构造正交小波基的新方法

本文给出了构造正交小波基的一种新的方法,主要是通过改造钟形函数来构造有具体表达式的小波母函数,在光滑性,局部性等性质上优于一般的构造方法,其收敛于零的阶数可达到O(|t|~(-N)),N≥4。而且更进一步在S空间上构造出收敛更快的小波母函数。     

紧支撑多重向量值正交小波包的性质

给出紧支撑多重向量值正交小波包的定义及构造方法.运用矩阵理论与积分变换,研究了多重向量值正交小波包的性质,得到三个正交性公式.进而,得到空间L2(R,Cr)的一个新的规范正交基.     

Irregular Sampling in Wavelet Subspaces

As a particular wavelet subspace, the Paley-Wiener space has both regular and irregular sampling theorems. A regular sampling theorem in general wavelet subspaces has been established for several years. In this paper, we discuss the irregular sampling problem in wavelet subspaces.     

Asymptotic solution of a non-linear wave motion in an electron plasma

The theory of high-frequency waves has been used to calculate first and second-order asymptotic solutions for the propagation of non-linear waves in a cylindrical symmetric flow of an electron plasma. The behaviour of acceleration waves and weak shock waves has been analysed through these solutions and Whitham's rule for a weak shock wave on any wavelet has been confirmed through the first-order solution. The appearance of a weak shock wave on any wavelet has been determined and its strength, the location, and the speed of propagation have been found from the asymptotic solution presented in this paper. © 1997 by B. G. Teubner Stuttgart–John Wiley & Sons Ltd.     

On Haar wavelet operational matrix of general order and its application for the numerical solution of fractional Bagley Torvik equation

In the present analysis, the motion of an immersed plate in a Newtonian fluid described by Torvik and Bagley’s fractional differential equation [1] has been considered. This Bagley Torvik equation has been solved by operational matrix of Haar wavelet method. The obtained result is compared with analytical solution suggested by Podlubny [2]. Haar wavelet method is used because its computation is simple as it converts the problem into algebraic matrix equation.     

向量值正交小波包

引进对应于2尺度向量值尺度函数的多分辨分析和向量值小波的概念.给出向量值小波包的定义及其构造算法,研究了向量值正交小波包的正交性,并讨论了空间L2(R,CN)的正交分解.     

过抽样M通道小波星图去噪方法研究

小波图像去噪已经成为目前图像去噪的主要方法之一,在分析了小波变换的基本理论和小波变换的多尺度分析基础上,根据多尺度小波变换的多分辨特性,提出了过抽样M通道小波变换去噪方法,并将此方法用于星图降噪处理中,收到良好的效果.     

Quasi-interpolation and approximation via nonseparable scaling function

Quasi-interpolation has been audied in many papers, e.g. , [5]. Here we introduce nonseparable scal-ing function quasi-interpolation and show that its approximation can provide similar convergence propertiesas scalar wavelet system. Several equivalent statements of accuracy of nonseparable scaling function are alsogien. In the numerical experiments, it appears that nonseparable scaling function interpolation has betterconvergonce results than scalar wavelet systems in some cases.     

QUASI—INTERPOLATION AND APPROXIMATION VIA NONSEPARABLE SCALING FUNCTION

Quasi-interpolation has been studied in many papers,e.g.,[5].Here we introduce nonseparable scaling function quasi-interpolation and show that its approximation can provide similar convergence properties as scalar wavelet system.Several equivalent statements of accuracy of nonseparable scaling function are also given.In the numerical experiments,it appears that nonseparable scaling function interpolation has better convergence results than scalar wavelet systems in some cases.     

The properties of a class of biorthogonal vector-valued nonseparable bivariate wavelet packets

In this paper, we introduce a class of vector-valued wavelet packets of space L²(R²,C^κ), which are generalizations of multivariate wavelet packets. A procedure for constructing a class of biorthogonal vector-valued wavelet packets in higher dimensions is presented and their biorthogonality properties are characterized by virtue of matrix theory, time–frequency analysis method, and operator theory. Three biorthogonality formulas regarding these wavelet packets are derived. Moreover, it is shown how to gain new Riesz bases of space L²(R²,C^κ) from these wavelet packets. Relation to some physical theories such as the Higgs field is also discussed.