基于EMD法的语音信号特征提取

特征提取是目标识别的关键,如何从有限的测量数据中获取有效、可靠的特征参数,是特征提取中重点考虑的问题。本文采用EMD方法对语音信号进行频率特征提取,可以较好地降低语音信号的冗余度,实验结果表明:EMD方法是处理非平稳信号的有效方法,它运用于语音信号特征提取是可行的。     

基于EMD的SAR与全色影像融合算法

针对传统融合方法不能有效处理非线性、非平稳信号等问题,提出一种基于经验模态分解(EMD)的合成孔径雷达(SAR)与全色影像融合方法。该方法首先对全色影像和降噪后的SAR影像进行EMD分解,然后采用基于区域特征的融合规则分别对高频和低频部分进行融合,最后通过EMD逆变换得到融合图像。该方法可以有效处理非线性、非平稳信号且具有完全自适应性。实验结果表明,基于该算法的融合图像满足图像融合要求,且融合效果优于小波变换法及曲波变换。     

基于DSP的EMD方法的实现

EMD方法是对非平稳、非线性信号进行分析的一种新的时频分析方法。它比小波分析等方法具有更强的特性并能准确地处理非常短的数据序列。由于EMD方法将在未来更多的领域具有广阔的发展前景，因此研究开发了一个基于DSP和PCI的系统来实现EMD方法。     

一种改善EMD端点问题的方法

经验模态分解（EMD）是一种先进的数据处理方法,对脑电信号（EEG）等非线性非平稳信号的处理非常有效。但是其在利用三次样条曲线构造上下包络时,端点附近的包络存在严重的摆动。针对该问题,在镜面延拓算法的基础上,提出了二次延拓算法。根据邻近端点的数据计算出该信号在端点处的拟合函数;利用该拟合函数在左右端点各延拓出一个极值点;采用镜面延拓算法对延拓后的信号进行EMD分解。算法考虑了信号端点处的变化趋势,使得端点处的延拓更加合理,从而使三次样条曲线在端点处不会出现大的摆动。仿真结果表明,该算法能有效地对脑电信号进行分解。     

基于Spark计算框架的高铁振动数据经验模态分解

高铁的安全问题越来越受到人们关注,通过安装在高铁上的传感器可以采集到列车运行过程中的振动信号。分析和处理采集到的振动信号,可以对列车运行过程中出现的故障进行诊断。经验模态分解（EMD）适用于将非线性非平稳的信号分解为若干个固有模态函数之和,它在信号分析和处理领域起着至关重要的作用。但列车在不断运行过程中采集的数据量非常大,信号处理的速度成为了瓶颈。因此,借助大数据处理框架Spark基于分布式的内存运算、弹性式分布式数据集等特点,提出了基于Spark的并行化EMD算法,并利用实际数据进行算法评测,通过Speedup、Sizeup、Scaleup三个指标对实验结果进行分析,得到该并行化方法在三个指标上都有良好的效果,表明该算法可以为大量的振动信号分解提供可靠的解决方案。     

基于EMD的四边域曲面光顺算法

曲面光顺在计算机辅助几何设计（CAGD）中有重要应用,带噪声离散曲面可视为一种非平稳离散几何信号。经验模式分解（EMD）方法是分析非线性、非平稳信号的有效方法。提出了一种空间任意曲线EMD光顺方法和基于2维可分离的EMD曲面光顺方法。针对四边域离散曲面可视为U和V离散曲线构成的网格,且U和V曲线呈现空间任意形态。空间曲线光顺中,首先对数字曲线进行1维参数化,将曲线展开成1维信号;然后采用EMD对展开信号进行多分辨率分解,得到不同尺度下的内蕴模式函数(IMF),去除高频的IMF,重构信号;最后将重构信号逆映射回3维,得到光顺后的曲线。四边域曲面沿每条U,V线进行EMD光顺处理,得到光顺后曲面。实验结果表明,该方法可有效剔除曲面上的随机噪声,达到良好的曲面光顺效果。     

经验模态分解法在大气时间序列预测中的应用

介绍了一种可以提高非平稳时间序列预测精度的新方法, 该方法应用 Hilbert-Huang 变换的核心内容---经验模态分解法 (Empirical mode decomposition, EMD) 对非平稳时间序列进行分解, 以降低被预测信号中的非平稳性, 利用神经网络对分解后的各分量进行预测, 再将预测结果叠加. 利用该方法对石家庄市年逐月降水量进行预测, 预测结果显示, 其预测精度比直接用神经网络预测的预测精度有较明显的提高.     

双变量EMD分析的平面离散曲线光顺方法

曲线的光顺在计算机辅助设计及其相关制造业中都有着重要作用.通过把平面离散曲线当作非平稳信号来处理,提出了一种双变量经验模式分解(EMD)的平面数字曲线光顺方法.方法首先将平面数字曲线的各个变量分离,参数化为两个一维信号;然后运用一维EMD方法对一维化的信号进行滤波处理,去除高频噪声;最后对两个处理好的信号进行合成,得到...     

基于经验模态分解和SVM的脑电信号分类方法

脑电信号的非线性、非平稳性造成对运动想象脑电信号的分类识别存在特征提取困难、可区分性低以及分类识别性能差等问题。本文提出一种基于经验模态分解(Empirical Mode Decomposition, EMD)和支撑向量机(Support Vector Machine, SVM)的运动想象脑电信号分类方法,充分利用EMD算法在处理非线性、非平稳信号的自适应性以及SVM在小样本条件的高识别性能和强泛化能力。首先利用EMD算法将C3、C4导联信号分解为一系列本征模函数(Intrinsic Mode Function, IMF),然后从IMF的信息和能量等维度提取特征将脑电信号转换至区分性更强的特征域,最后利用SVM进行分类识别。采用国际BCI竞赛2003中的Graz数据进行验证,所提方法可以得到94.6%的正确识别率,为在线脑-机接口系统的研究提供了新的思路。     

基于改进小波阈值函数的风洞连续信号降噪方法

在暂冲式高速风洞中进行连续变迎角测力试验时,由于高频信号与低频信号相互交织、难以分离,传统的低通滤波方法会在剔除噪声干扰的同时丢失风洞连续信号中的高频有效部分、难以真实反映飞行器气动力非线性或突变区域的信号特征;为此,在常规软、硬阈值函数的基础上,提出一种基于改进阈值函数的风洞信号降噪方法,采用该方法对风洞连续变迎角试验数据进行处理;结果表明,该方法与传统软、硬阈值函数方法相比具有明显的优越性,处理后的结果与原信号的相似度更高,降噪效果更好,在降低噪声影响的同时,较好地保留了飞行器模型气动力非线性或突变区域信号的非局部平稳特性。     

基于EMD的脉冲星信号消噪算法

为了提高脉冲星辐射信号的信噪比,提出了一种基于经验模态分解(EMD)的脉冲星信号去噪算法。利用经验模态分解将信号分解为一组固有模态函数(IMF)。针对EMD阈值消噪算法性能不稳定这一问题,该算法滤除固有模态函数噪声时,利用相邻信号标准差作为噪声水平的判断准则,并采用自适应阈值,对于噪声含量较高的信号采用低通滤波器消噪。实验结果表明,与EMD阈值消噪方法相比,该算法能获得更高的信噪比,并具有较好的稳定性。     

Iterative Filtering Decomposition Based on Local Spectral Evolution Kernel

The synthesizing information, achieving understanding, and deriving insight from increasingly massive, time-varying, noisy and possibly conflicting data sets are some of most challenging tasks in the present information age. Traditional technologies, such as Fourier transform and wavelet multi-resolution analysis, are inadequate to handle all of the above-mentioned tasks. The empirical model decomposition (EMD) has emerged as a new powerful tool for resolving many challenging problems in data processing and analysis. Recently, an iterative filtering decomposition (IFD) has been introduced to address the stability and efficiency problems of the EMD. Another data analysis technique is the local spectral evolution kernel (LSEK), which provides a near prefect low pass filter with desirable time-frequency localizations. The present work utilizes the LSEK to further stabilize the IFD, and offers an efficient, flexible and robust scheme for information extraction, complexity reduction, and signal and image understanding. The performance of the present LSEK based IFD is intensively validated over a wide range of data processing tasks, including mode decomposition, analysis of time-varying data, information extraction from nonlinear dynamic systems, etc. The utility, robustness and usefulness of the proposed LESK based IFD are demonstrated via a large number of applications, such as the analysis of stock market data, the decomposition of ocean wave magnitudes, the understanding of physiologic signals and information recovery from noisy images. The performance of the proposed method is compared with that of existing methods in the literature. Our results indicate that the LSEK based IFD improves both the efficiency and the stability of conventional EMD algorithms.     

Low-complexity sinusoidal-assisted EMD (SAEMD) algorithms for solving mode-mixing problems in HHT

In recent years, Hilbert–Huang Transform (HHT) is widely used to analyze nonlinear and non-stationary signals in various applications, such as seismic and biomedical signal processing. In HHT, the Empirical Mode Decomposition (EMD) is the key component for decomposing natural signals into intrinsic mode functions (IMFs). Since the EMD suffers from mode-mixing problem, in which some fast intermittent signals riding on a slow-oscillating wave, the Ensemble-EMD (EEMD) is proposed to solve this problem with the aids of noise. However, the EEMD requires high computational complexity in ensemble and is unsuitable for some real-time applications, such as ultrasound systems. In this paper, intermittent signals are modeled in mathematical forms for IMF decomposition. We then propose sinusoidal-assisted EMD (SAEMD) for efficient and effective HHT computation to solve mode-mixing problems. The type I of SAEMD (SAEMD-I) is initially proposed to solve the mode-mixing problem with very low computational complexity. However, if the maximum frequency of data is unknown in some real-world applications, the SAEMD-I may encounter estimation error caused by imprecise locations of extrema. For practical data, the type II of SAEMD (SAEMD-II) is proposed to solve the sampling rate issue. Compared with the ensemble-100 EEMD, the SAEMD-II can have 11–13 times improvement in terms of computation speed in El Niño application and comparable correlation coefficient (−0.95 at IMF 8). Hence, the proposed SAEMD-II scheme is a good candidate of implementing cost-effective HHT when computational complexity and real-time data processing are of major concern.     

Partial ensemble approach to resolve the mode mixing of extreme-point weighted mode decomposition

Empirical mode decomposition (EMD) is an effective tool for breaking down components (modes) of a nonlinear and non-stationary signal. Recently, a newly adaptive signal decomposition method, namely extreme-point weighted mode decomposition (EWMD), was put forward to improve the performance of EMD, in particular, to resolve the over- or undershooting issue associated with the large amplitude variations. However, similar to EMD, EWMD also suffers the mode mixing problem caused by intermittence or noisy signals. In this paper, inspired by complementary ensemble EMD (CEEMD), a noise-assisted data analysis method called partial ensemble extreme-point weighted mode decomposition (PEEWMD) is proposed to eliminate the mode mixing problem and enhance the performance of EWMD. In the proposed PEEWMD method, firstly white noises in pairs are added to the targeted signal and then the noisy signals are decomposed using the EWMD method to obtain the intrinsic mode functions (IMFs) in the first several stages. Secondly, permutation entropy is employed to detect the components that cause mode mixing. The residual signal is obtained after the identified components are separated from the original signal. Lastly, the residual signal is fully decomposed by using the EWMD method. The proposed PEEWMD method is compared with original EWMD, ensemble EWMD (EEWMD) and CEEMD using simulated signals. The results demonstrate that PEEWMD can effectively restrain the mode mixing issue and generates IMFs with much better performance. Based on that the PEEWMD and envelope power spectrum based fault diagnosis method was proposed and applied to the rubbing fault identification of rotor system and the fault diagnosis of rolling bearing with inner race. The result indicates that the proposed method of fault diagnosis gets much better effect than EMD and EWMD.     

经验模式分解回顾与展望

经验模式分解EMD打破了Fourier变换、小波分解等传统数据分析方法需要预先设定基函数的局限,是一种完全由数据驱动的自适应非线性非平稳时变信号分解方法,可以将数据从高频到低频分解成具有物理意义的少数几个固有模态函数分量和一个余量。首先介绍了原始EMD方法的原理和算法;接着,总结归纳了EMD当前的研究现状,分析了EMD存在的端点效应、模态混叠、运行速度问题及其在二维情况下的问题并对国内外学者解决这些问题的方法进行了概述和比较;最后结合EMD研究存在的难题指出了EMD进一步研究与应用的发展方向。     

基于EMD-GAELM-ARIMA算法的大坝变形预测

In view of the fact that it is difficult for statistical models to make good predictions of nonlinear and non-stationary dam deformation, artificial intelligence algorithms are induced. The empirical mode decomposition method (EMD), genetic algorithm (GA) optimized extreme learning machine (ELM), and ARIMA error correction model were used to construct a dam deformation prediction model. First this paper uses EMD to decompose and reconstruct the monitoring data to stabilize it and obtain eigenmode functions and residual sequences with physical significance; then uses GAELM to analyze and predict the decomposition results; finally, uses ARIMA model to correct errors. Taking a concrete rockfill dam as an example, the dam deformation prediction model constructed by the optimization algorithm is used to analyze and predict it. The analysis results show that the EMD-GAELM-ARIMA model algorithm has higher prediction accuracy than the traditional single algorithm. It is feasible in dam deformation prediction.     

Simulation Analysis and Application of SAR Target Motion Parameters based on EMD-RSPWVD Algorithm

When processing multi-component SAR moving target echo data by traditional time-frequency analysis method, there is serious cross-term influence and poor time-frequency clustering. A new time-frequency analysis algorithm named EMD-RSPWVD is proposed. It combines the improved Empirical Mode Decomposition (EMD) algorithm and Reassigned Smoothing Pseudo-Wigner-Ville Distribution (RSPWVD) algorithm. The improved EMD algorithm is used to decompose the multi-component SAR moving target echo signal into independent signal components. Then the time-frequency analysis of independent components which based on RSPWVD algorithm is performed to eliminate cross-terms and obtain high time-frequency resolution. Finally, simulated echo data and real echo data are used to analyze the performance of this algorithm for multi-component SAR motion echo data. The results show that the algorithm has good anti-noise ability, moving target detection ability and high-precision motion parameter estimation performance.     

基于EMD-RSPWVD算法的SAR目标运动参数仿真分析与应用研究

针对传统时频分析方法处理多分量SAR运动目标回波数据时出现的交叉项影响严重和时频聚集性差等问题,提出一种融合改进的经验模式分解（Empirical Mode Decomposition, EMD）算法和重排平滑伪维格纳维尔分布（Reassigned Smoothing Pseudo-Wigner-Ville Distribution, RSPWVD）算法的新时频分析算法——EMD-RSPWVD算法。利用改进的EMD算法将多分量SAR动目标回波信号分解为彼此独立信号分量,然后对独立分量分别做基于RSPWVD算法的时频分析,以消除交叉项和获得高的时间—频率分辨率。分别利用模拟回波信号数据和真实回波信号数据,探究该算法对于多分量SAR运动回波数据的分析性能。结果表明,该算法具有良好的抗噪性和运动目标检测能力,以及高精度的运动参数估计性能。