能量熵与峰值窗口结合去除眼电伪迹研究

为改进传统独立分量分析自动去除眼电伪迹算法中存在识别眼电分量速度慢、需采集同步参考眼电信号、丢失脑电信号问题,提出一种不需要参考眼电信号的眼电伪迹自动识别去除方法。利用FastICA分解出独立分量,计算各独立分量频谱能量熵,以频谱能量熵值作为判据识别出眼电分量;然后使用峰值窗口分离出眼电分量中存在的脑电信号,与其他独立分量进行拼接;利用FastICA逆变换重构出去眼电伪迹的脑电信号。实验结果表明：该方法能准确快速自动地去除眼电伪迹,并较好地保留其他的脑电信号成分;频谱能量熵识别眼电伪迹平均用时为0.01?s,准确率为98％,适用于实时EOG去除。     

改进独立分量算法的眼电伪迹去除方法研究

脑电信号采集过程中易受眼电干扰,给脑电信号分析处理带来极大的不便,由此提出了一种改进独立分量分析（IICA）自动去除眼电伪迹的方法。该方法将水平和垂直眼电信号按照一定的比例混叠成一导新的信号,并与脑电信号一起作为输入;采用基于负熵判据的FastICA算法快速获取各导独立分量;记录此时的负熵判据参数[a],并利用相关系数识别混叠眼电信号独立分量,记录对应的相关系数;[a]加上一定的步长,重复上述步骤至[a]达到阈值时停止;重复多次上述循环,获取均值向量,取出均值向量中最大的相关系数与所对应的[a],根据[a]获取新的独立分量,采用相关系数自动识别混叠眼电独立分量,并置零;再进行ICA逆变换返回到原信号各个电极,即可得到同时去除水平与垂直眼电伪迹后的各导脑电信号。实验结果表明,IICA方法能有效降低去伪迹耗时,极大提高信噪比,减少均方根误差。     

脑电信号中眼电伪迹的自动去除算法

为实现眼电伪迹的自动去除,提高算法的有效性和稳健性,提出一种眼电伪迹自动去除算法。采用样本熵和一种通用的伪迹判决方法对眼电伪迹进行自动识别,通过脑电信号的重构实现眼电伪迹的去除。实验结果表明,对于不同长度的真实脑电信号,该算法均能准确地去除眼电伪迹,较好地保留其他的脑电信号成分,且可以完全自动地去除眼电伪迹,适用于实时场合。     

基于小波变换和FastICA的眼电伪迹去除研究

为了高效去除脑电信号(Electroencephalogram, EEG)中的眼电伪迹,文章提出一种基于小波变换(Wavelet Transform, WT)和快速独立成分分析(Fast Independent Component Analysis, FastICA)相结合的眼电伪迹去除方法。首先,应用小波变换将信号分解成不同频率的小波分量,采用适合的小波基函数和阈值针对高低频噪声做去噪处理;其次,应用FastICA算法分离出各通道的独立成分,获取纯净的脑电信号;最后,对BCI competition IV公共数据集应用融合算法,并输入支持向量机(Support Vector Machine, SVM)进行分类验证。实验结果表明,相较于单一的小波变换和FastICA算法,采用文章提出的融合算法处理后的脑电信号的SVM分类识别率分别提升了18.9%和15.8%,证明该融合算法对去除脑电信号中的眼电伪迹有较好的效果。     

单通道脑电信号眼电伪迹去除算法研究

由眨眼和眼动产生的眼电伪迹（Electrooculography,EOG）信号是脑电信号（Electroencephalography,EEG）中的主要噪声信号之一.目前,多通道脑电信号中眼电伪迹的去除算法已经较为成熟.而在单通道脑电信号的眼电伪迹去除中,由于采集通道数量较少且缺乏参考眼电信号,目前尚无十分有效的去除方法.本文提出一种基于小波变换（Wavelet transform,WT）、集合经验模态分解（Ensemble empirical mode decomposition,EEMD）和独立成分分析（Independent component analysis,ICA）的WT-EEMD-ICA单通道脑电信号眼电伪迹去除算法.实验表明:WT-EEMD-ICA算法有效地解决了单通道WT-ICA算法中的超完备问题,能够有效去除单通道脑电信号中的眼电伪迹,并且分离出的眼电伪迹成分与参考通道采集的眼电信号相关性较强.     

基于CEEMDAN-ICA的单通道脑电信号眼电伪迹滤除方法

传统盲源分离法不能解决欠定问题,且分离信号与源信号对应关系不确定.提出一种基于自适应噪声完备经验模态分解(CEEMDAN)和独立成分分析(ICA)相结合的脑电信号眼电伪迹自动去除方法.该方法首先将含伪迹脑电信号自适应分解成多维本征模态函数(IMF),以满足盲源分离方法对信号正定或超定要求,再对本征模态函数用ICA方法构建多维源信号,最后利用模糊熵阈值判据判别多维源信号中的伪迹信号,完成滤波并重构脑电信号.该方法相比于其他算法,能更好的去除眼电伪迹并保留原始信息,适合单通道脑电信号预处理.     

结合PCA和JADE的EEG眼电伪迹去除研究

眼电伪迹干扰是脑电信号中的常见干扰,严重影响到有用脑电信号的提取和分析。提出一种基于主分量分析(PCA)和特征矩阵联合相似对角化(JADE)算法相结合的眼电伪迹去除方法,并探讨了主分量分析对伪迹去除的影响。实验结果表明了该算法的有效性及稳健性,并且其时间开销小。此外该算法还可以有效去除其他脑电伪迹及干扰成分。     

一种基于EWT-ICEEMDAN的单通道脑电信号眼电伪迹去除算法

脑电信号和眼电信号存在频谱混叠，目前的单通道脑电信号中眼电伪迹去除方法容易造成脑电信号失真。提出一种基于经验小波变换(EWT)和改进的自适应噪声完备经验模态分解(ICEEMDAN)的单通道脑电信号眼电伪迹去除算法。首先使用EWT将单通道脑电信号分解为δ频段和高频段信号，再用ICEEMDAN将δ频段信号自适应分解为多维本征模态函数(IMFs),设置样本熵阈值自动去除眼电伪迹信号，最后重构得到滤波后的脑电信号。基于半模拟脑电数据和真实脑电数据开展实验，结果表明所提算法相比于已有算法能够在去除眼电伪迹的同时更好地保留原始脑电信息。     

基于独立分量分析的脑电中眼电伪迹消除

利用独立分量分析的方法对脑电中眼电伪迹成分进行剔除。运用负熵最大算法将脑电信号分解成独立分量,利用伪迹脑地形图的特征,将伪迹分量分离,得到不含伪迹的脑电信号。实验结果表明,该算法具有较强的稳健性和实用性。     

基于CuBICA算法的EEG伪迹去除方法

在高阶累积量和独立分量分析的基础上,提出一种基于CuBICA算法的脑电信号伪迹去除方法。针对脑电信号中常含有的眼电、心电等伪迹问题,利用小波包方法对原始脑电信号去噪,并进行中心化和白化处理,运用CuBICA算法对消噪后的脑电信号进行盲源分 离。分析分离后各信号间相关性,结果表明,CuBICA算法能成功分离脑电、眼电与心电信号,有效去除纯脑电信号中的各种伪迹。     

Wavelet-based envelope features with automatic EOG artifact removal: Application to single-trial EEG data

In this study, we propose an analysis system for single-trial classification of electroencephalogram (EEG) data. Combined with automatic EOG artifact removal and wavelet-based amplitude modulation (AM) features, the support vector machine (SVM) classifier is applied to the classification of left finger lifting and resting. Automatic EOG artifact removal is proposed to eliminate the EOG artifacts automatically by means of independent component analysis (ICA) and correlation coefficient. The features are then extracted from the discrete wavelet transform (DWT) data by the AM method. Finally, the SVM is used for the discriminant of wavelet-based AM features. Compared with EEG data without EOG artifact removal, band power features and LDA classifier, the proposed system achieves promising results in classification accuracy.     

ANC Schemes for the Enhancement of EEG Signals in the Presence of EOG Artifacts

One of the most important applications of adaptive systems is in noise cancellation using adaptive filters. In this paper, we propose adaptive noise cancellation schemes for the enhancement of EEG signals in the presence of EOG artifacts. The effect of two reference inputs is studied on simulated as well as recorded EEG signals and it is found that one reference input is enough to get sufficient minimization of EOG artifacts. This has been verified through correlation analysis also. We use signal to noise ratio and linear prediction spectra, along with time plots, for comparing the performance of the proposed schemes for minimizing EOG artifacts from contaminated EEG signals. Results show that the proposed schemes are very effective (especially the one which employs Newton's method) in minimizing the EOG artifacts from contaminated EEG signals.     

Reliable EOG signal-based control approach with EEG signal judgment

This article proposes a reliable EOG signal-based control approach with EEG signal judgment. In this method, raw bio-neurological signals (including EOG and EEG) are first extracted and segmented in the pre-processing stage. The processed bio-neurological signals will then be evaluated by calculating the feature parameters of these signals. Since the feature parameters in bio-neurological signals may be contaminated by various kinds of artifacts, some artifacts of bio-neurological signals can be indicated by means of the feature parameters of bio-neurological signals. Therefore, the bio-neurological signals contaminated with artifacts cannot be adopted to generate control signals or to judge the correctness of control signals. In the proposed method, in order to generate a reliable control signal based on the EOG signal, the EEG signal is adopted to assist in making a judgment about the validity of the EOG signal. With the proposed method, an EOG signal-based control software platform has been implemented. By using this platform, simulation work has been carried out to control the behavior of a robot. The simulation results verified the effectiveness of the proposed method.     

A deep wavelet sparse autoencoder method for online and automatic electrooculographical artifact removal

Electrooculographical (EOG) artifacts are problematic to electroencephalographical (EEG) signal analysis and degrade performance of brain–computer interfaces. A novel, robust deep wavelet sparse autoencoder (DWSAE) method is presented and validated for fully automated EOG artifact removal. DWSAE takes advantage of wavelet transform and sparse autoencoder to become a universal EOG artifact corrector. After being trained without supervision, the sparse autoencoder performs EOG correction on time–frequency coefficients collected after brain wave signal wavelet decomposition. Corrected coefficients are then used for wavelet reconstruction of uncontaminated EEG signals. DWSAE is compared with five other methods: second-order blind identification, information maximization, joint approximation diagonalization of eigen-matrices, wavelet neural network (WNN) and wavelet thresholding (WT). Experimental results on a visual attention task dataset, a mental state recognition dataset and a semi-simulated contaminated EEG dataset show that DWSAE is capable of suppressing EOG artifacts effectively, while preserving the nature of background EEG signals. The mean square error of signals before and after correction by DWSAE on a semi-simulated contaminated EEG segment of 30 s is the lowest (65.62) when compared to the results produced by WNN and WT. DWSAE addresses limitations posed by these methods in three ways. First, DWSAE can be performed automatically and online in a single channel of EEG data; this has advantages over independent component analysis-based methods. Second, its results are robust and stable in comparison with those of other wavelet-based methods. Third, as an unsupervised learning scheme, DWSAE does not require the off-line training that is necessary for WNN and other supervised learning machine learning-based methods.

     

Real-time removal of ocular artifacts from EEG based on independent component analysis and manifold learning

Frequent occurrence of ocular artifacts leads to serious problems in interpreting and analyzing the electroencephalogram (EEG). In the present paper, a novel and robust technique is proposed to eliminate ocular artifacts from EEG signals in real time. Independent Component Analysis (ICA) is used to decompose EEG signals. The features of topography and power spectral density of those components are extracted. Moreover, we introduce manifold learning algorithm, a recently popular dimensionality reduction technique, to reduce the dimensionality of initial features, and then those new features are fed to a classifier to identify ocular artifacts components. A k-nearest neighbor classifier is adopted to classify components because classification results show that manifold learning with the nearest neighbor algorithm works best. Finally, the artifact removal method proposed here is evaluated by the comparisons of EEG data before and after artifact removal. The results indicate that the method proposed could remove ocular artifacts effectively from EEG signals with little distortion of the underlying brain signals and be satisfied the real-time application.