小波滤波与AR模型在脑电信号处理的应用

针对脑-计算机接口技术中的脑电信号处理、事件相关同步和事件相关去同步的特点,提出了一种基于离散小波滤波和AR模型来提取脑电信号特征向量的方法。利用Daubechies类小波函数对脑电信号进行4层分解,然后使用Burg算法提取脑电信号8阶AR模型系数,最后用BP神经网络进行分类和比较。得到最优的正确率为71.64%,小波滤波的效果要优于FIR滤波器。     

小波变换与自适应滤波在脑电信号消噪中的应用

提出了基于AR(自回归)模型的小波变换与LMS(最小均方)自适应滤波相结合的脑电信号分析方法,并利用它来消除脑电信号中的噪声干扰。实验结果表明,利用小波变换与自适应滤波相结合能有效去除脑电信号中的噪声干扰。     

小波变换和AR模型在脑电信号处理中的应用

谈论了基于小波变换和AR模型的(EEG)信号的分析方法,在两种方法相结合的情况下,能有效消去(EEG)信号的噪声。用小波变换对含有瞬态干扰的脑电信号进行多尺度分解,在某些尺度下,瞬态信号特征得以明显增强,用简单的阈值比较就可以有效地检测并消除瞬态干扰。最后在Matlab环境下进行仿真实验,验证了此方法在提取脑电信号中的有效性。     

一种新的基于小波包分解的EEG特征抽取与识别方法研究

为了提高脑思维任务分类精度,提出一种新的脑电特征抽取与识别方法.首先进行小波包分解,然后结合能反映脑电信号在时域与频域上的能量分布特征的小波包熵概念,从小波包库中选择最优小波包基,对各个最优基所对应的小波系数求取统计特性,然后根据不同脑思维任务下左右半脑各导联间的差异性对各个导联对求取不对称率构成分类特征向量,最后利用SVM分类器对其进行分类.实验结果表明:相对于一般的小波包分解,最优小波包基和自回归特征抽取方法,该方法对5类不同脑思维任务的所有10种不同组合任务对的平均分类预测精度可以达到95.41％～99.65％.     

基于DSP Builder的脑电信号小波处理

针对脑电信号非平稳性特点,利用小波变换对采集到的脑电信号进行滤波处理.然而小波变换巨大的计算量限制其在高速实时信号处理领域的应用,FPGA器件兼具并/串行工作方式,具有较高的并行计算能力,在现场数字信号处理领域具有较强的实时性.提出基于FPGA的小波变换系统设计方法,首先利用DB2小波对脑电信号按Mallat算法进行分解,然后采用小波重构算法去噪.试验结果表明,运用小波分解重构算法,可以对脑电信号进行实时滤波.     

基于AR模型的小波变换在脑电信号消噪中的应用

提出了基于自回归模型(ARM)与小波变换的脑电信号分析方法,并利用他来消除脑电信号中的噪声干扰。小波变换是一种多分辨率的时间尺度分析方法,他能够将信号划分为不同频段的子带信号。根据小波变换的这一特性,对采样获得的脑电信号进行各尺度分解及消噪分析,并给出了各尺度分解结果及消噪结果。利用小波变换能有效去除脑电信号中的噪声干扰。     

脑电信号中眼电伪迹自动去除方法的研究

 针对实际采集的脑电信号受眼电干扰较大,提出一种基于离散小波变换(DWT)与独立分量分析(ICA)的自动去除眼电伪迹的方法(DWICA).对采集的多导脑电和眼电信号进行离散小波变换,获取多尺度小波系数,将串接小波系数作为ICA的输入;利用基于负熵判据的FastICA算法实现独立成分的快速获取,引入夹角余弦准则自动识别眼迹成分,并经过ICA逆变换将剔除眼迹后的独立成分投影返回到原脑电信号各个电极;通过DWT逆变换重构信号,即可得到去除眼迹的各导脑电信号.实验结果表明,DWICA方法极大地提高了脑电信号的信噪比,抗噪能力强且实时性好,为脑电信号的在线预处理提供了新思路.     

基于DSP Builder的脑电信号小波处理

针对脑电信号非平稳性特点,利用小波变换对采集到的脑电信号进行滤波处理。然而小波变换巨大的计算量限制其在高速实时信号处理领域的应用,FPGA器件兼具并／串行工作方式,具有较高的并行计算能力,在现场数字信号处理领域具有较强的实时性。提出基于FPGA的小波变换系统设计方法,首先利用DB2小波对脑电信号按Mallat算法进行分解,然后采用小波重构算法去噪。试验结果表明,运用小波分解重构算法,可以对脑电信号进行实时滤波。     

基于小波包变换的表面肌电信号模式识别

采用小波包变换的方法对表面肌电信号sEMG进行了多尺度分解,并提取小波包分解系数的能量值构建特征矢量,采用四种方法设计多类最小二乘支持向量机（LS-SVM）分类器,对8种表面肌电信号进行了模式分类。实验结果表明,采用四种多类分类方法的LS-SVM分类器对8种表面肌电信号的平均识别率在90%以上,LS-SVM分类准确率明显优于传统的RBF神经网络分类器。     

基于离散小波变换和主分量分析的P300分类算法研究

提出了一种应用离散小波变换(DWT)结合主分量分析(PCA)进行特征提取,然后用支持向量机(SVM)对P300进行分类的算法.该算法首先在一定预处理基础上使用离散小波变换对P300脑电信号分解,然后选取蕴含P300大多数信息的特征尺度进行小波重构,从而达到去噪增强的效果.然后使用PCA进行特征的提取和集中.最后使用支持向量机对提取到的特征分量进行分类.该算法将小波分解和主分量分析结合起来进行特征增强与提取,实验结果表明,该算法能够达到令人满意的正确分类率.     

Multivariate autoregressive models for classification ofspontaneous electroencephalographic signals during mental tasks

This article explores the use of scalar and multivariate autoregressive (AR) models to extract features from the human electroencephalogram (EEG) with which mental tasks can be discriminated. This is part of a larger project to investigate the feasibility of using EEG to allow paralyzed persons to control a device such as a wheelchair. EEG signals from four subjects were recorded while they performed two mental tasks. Quarter-second windows of six-channel EEG were transformed into four different representations: scalar AR model coefficients, multivariate AR coefficients, eigenvalues of a correlation matrix, and the Karhunen-Loeve transform of the multivariate AR coefficients. Feature vectors defined by these representations were classified with a standard, feedforward neural network trained via the error backpropagation algorithm. The four representations produced similar results, with the multivariate AR coefficients performing slightly better and more consistently with an average classification accuracy of 91.4% on novel, untrained, EEG signals     

Multiclass support vector machines for EEG-signals classification.

In this paper, we proposed the multiclass support vector machine (SVM) with the error-correcting output codes for the multiclass electroencephalogram (EEG) signals classification problem. The probabilistic neural network (PNN) and multilayer perceptron neural network were also tested and benchmarked for their performance on the classification of the EEG signals. Decision making was performed in two stages: feature extraction by computing the wavelet coefficients and the Lyapunov exponents and classification using the classifiers trained on the extracted features. The purpose was to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. Our research demonstrated that the wavelet coefficients and the Lyapunov exponents are the features which well represent the EEG signals and the multiclass SVM and PNN trained on these features achieved high classification accuracies.     

Hybrid Fractal-Wavelet Method for Multi-Channel EEG Signal Compression

In this paper, a hybrid method is proposed for multi-channel electroencephalograms (EEG) signal compression. This new method takes advantage of two different compression techniques: fractal and wavelet-based coding. First, an effective decorrelation is performed through the principal component analysis of different channels to efficiently compress the multi-channel EEG data. Then, the decorrelated EEG signal is decomposed using wavelet packet transform (WPT). Finally, fractal encoding is applied to the low frequency coefficients of WPT, and a modified wavelet-based coding is used for coding the remaining high frequency coefficients. This new method provides improved compression results as compared to the wavelet and fractal compression methods.     

Narrowband acoustic Doppler volume backscattering signal .II. Spectral centroid estimation

For pt.I see ibid., vol.50, p.2644-2655 (2002). This paper proposes a novel algorithm to estimate the time-varying spectral centroid of the narrowband Doppler volume backscattering signal. It is constructed in a semi-parametric way, that is, modeling parametrically the local narrowband evolutionary spectrum using an AR(2) and nonparametrically adapting its time-varying coefficients using the wavelet shrinkage. The improved performance is gained by the underlying linear prediction function of the AR(2) and the minimax optimality of the unknown smoothness adaptation of the wavelet shrinkage procedure.     

Forecasting generalized epileptic seizures from the EEG signal bywavelet analysis and dynamic unsupervised fuzzy clustering

Dynamic state recognition and event-prediction are fundamental tasks in biomedical signal processing. The authors present a new, electroencephalogram (EEG)-based, brain-state identification method which could form the basis for forecasting a generalized epileptic seizure. The method relies on the existence in the EEG of a preseizure state, with extractable unique features, a priori undefined. The authors exposed 25 rats to hyperbaric oxygen until the appearance of a generalized EEG seizure. EEG segments from the preexposure, early exposure, and the period up to and including the seizure were processed by the fast wavelet transform. Features extracted from the wavelet coefficients were inputted to the unsupervised optimal fuzzy clustering (UOFC) algorithm. The UOFC is useful for classifying similar discontinuous temporal patterns in the semistationary EEG to a set of clusters which may represent brain-states. The unsupervised selection of the number of clusters overcomes the a priori unknown and variable number of states. The usually vague brain state transitions are naturally treated by assigning each temporal pattern to one or more fuzzy clusters. The classification succeeded in identifying several, behavior-backed, EEG states such as sleep, resting, alert and active wakefulness, as well as the seizure. In 16 instances a preseizure state, lasting between 0.7 and 4 min was defined. Considerable individual variability in the number and characteristics of the clusters may postpone the realization of an early universal epilepsy warning. Universality may not be crucial if using a dynamic version of the UOFC which has been taught the individual's normal vocabulary of EEG states and can be expected to detect unspecified new states     

基于C-LSTM模型的端到端多粒度运动想象脑电信号分析方法

脑电信号（Electroencephalography, EEG）是人的大脑在不同状态下产生的生物电信号。运动想象脑电信号是其中较为典型的一类信号，广泛应用于脑机接口技术中。对运动想象脑电信号分析的研究由来已久，目前主要采用公共空间模式等特征提取方法，对于如何提取更加有效的脑电信号特征以及如何对时序信息进行建模仍然是需要解决的问题。因此，本文设计了基于C-LSTM（Convolutional-Long Short Term Memory）模型的端到端多粒度脑电分析方法。并利用空间信息以及小波脑网络方法进行了改进，在BCI2008数据集上，相较传统方法提高了近10%，到达了93.6%的识别率。      

基于小波分析的EEG信号自适应去噪的应用研究

介绍了小波变换应用于EEG信号消噪处理中的原理及自适应噪声抵消器的原理。根据短时动态信号与平稳背景噪声的特征区别,对输入混合信号进行白化预处理,以时间序列的AR模型理论为依据,导出背景噪声白化滤波器的结构;将小波变换与自适应滤波相结合,对经白化处理后的信号进行自适应去噪,将去噪后信号及平均信号做了功率谱估计比较,实验结果表明该方法能有效地去除弱信号中的噪声。     

单通道脑电信号中眼电干扰的自动分离方法

当前主流的眼电(EOG)去除方法需要利用多通道脑电的相关性,难以在单通道的便携式脑机接口(BCI)中应用。该文提出一种基于长时差分振幅包络与小波变换的眼电干扰自动分离方法。首先在原脑电信号的长时差分振幅包络上实施双门限法来精确检测眼电的起止点,然后利用sym5小波对脑电进行分解并引进Birg_Massart策略来自适应地确定小波重构系数阈值,最后通过小波重构精确地估计眼电,实现单通道上眼电与脑电的自动分离。大量实验证明,该方法与主流的平均伪迹回归分析和基于独立成分分析(ICA)的方法相比,能够获得更好的估计眼电与原眼电的相关性,保证更高的校正信噪比和较强的实时性,能够满足脑机接口多方面的需要。