基于HHT运动想象脑电模式识别研究

脑机接口是一种变革性的人机交互, 其中基于运动想象(Motor imagery, MI)脑电的脑机接口是一类非常重要的脑机交互. 本文旨在探索有效的运动想象脑电特征模式提取方法. 采用在时域、频域同时具有很高分辨率的希尔伯特--黄变换(Hilbert-Huang transform, HHT),进而提取自回归(Auto regressive, AR)模型参数并计算运动想象脑电平均瞬时能量,从而构造特征向量, 最后利用能较好地适应运动想象脑电单次试验分类的支持向量机(Support vector machine, SVM)进行分类. 结果表明在Trial的5.5～7.5s期间, HHT特征提取方法平均分类正确率为81.08%, 具有良好的适应性;最高分类正确率为87.86%, 优于传统的小波变换特征提取方法和未经HHT的特征提取方法;在Trial的8～9s期间, HHT特征提取方法显著优于后两种特征提取方法. 本研究证实了HHT对运动想象脑电这一非平稳非线性信号具有很好的特征提取能力, 也再次验证了运动想象事件相关去同步(Event-related desynchronization, ERD)现象, 同时也表明运动想象脑电的脑--机交互系统性能与被试想象心理活动的质量密切相关. 本文可望为基于运动想象脑电的在线实时脑机交互控制系统的研究打下坚实的基础.     

基于眼动辅助脑电信号的手部动作分类方法

提出一种利用小波包变换和支持向量机对手部动作的运动想象脑电信号进行分类的方法。在相关眼动辅助情况下采集想象手部动作时的C3、C4 、P3和P4通道脑电信号,用小波包变换的方法提取4种特征节律波,分别计算每种节律波能量占4种节律波能量之和的比值作为特征,然后将16维特征向量输入支持向量机分类器进行手部动作分类。对上翻、下翻、展拳、握拳4种手部动作的分类实验中平均识别率为82。3%,表明眼动辅助能有效提高运动想象脑电信号可分性。     

感知器算法在运动想象脑电模式识别中的应用

基于脑电(EEG)的脑机接口(BCI)是在人脑和计算机或其它电子设备之间建立不依赖于常规大脑信息输出通路(外周神经和肌肉组织)的全新对外信息交流和控制技术。及时有效地提取和识别与运动想象相关的脑电模式可以帮助严重瘫痪病人控制光标或辅助运动设备以替代其受损的运动功能,建立一种与外界交流沟通的新途径。论文将以EEG(C3,C4)两个通道的mu节律能量作为特征向量,用感知器算法对左右手运动想象脑电模式进行识别,实验结果表明,正确识别率可达87.86%。由于感知器算法计算简单,故可以认为,感知器算法在脑机接口的应用中有较高的实用价值。     

基于图卷积网络的运动想象识别

运动想象识别将大脑的神经活动信号转为编码输出以实现意念控制,是脑机接口的一个重要研究方向.近年来深度学习算法的应用进一步提高了运动想象识别的准确率,但是当前基于深度学习的运动想象分析都将多路脑电信号作为二维矩阵信号,忽视了不同节点的空间关联信息.为了解决这个问题,将图卷积网络算法应用到运动想象分类中,通过多个节点脑电信...     

基于多类运动想象任务的EEG信号分类研究

针对多类运动想象脑电信号个体差异性强和分类正确率比较低的问题,提出了一种时-空-频域相结合的脑电信号分析方法:首先利用小波包对EEG原始信号进行分解,根据EEG信号的频域分布提取出运动想象脑电节律,通过“一对多”共空间模式(CSP)算法对不同运动想象任务的脑电节律进行空间滤波提取特征;然后将特征向量输入到“一对多”模式下的支持向量机(SVM)中,并利用判断决策函数值的方法对SVM的输出结果进行融合;最后通过引入时间窗对脑电信号进行时域滤波,消除运动想象开始和结束时脑电的波动,进一步提高信号信噪比和算法的分类效果;实验结果显示:在时间窗为2 s时,平均最大Kappa系数达到了0.72,比脑机接口竞赛第一名提高了0.15,验证了该算法能够有效减小脑电信号个体差异性影响,提高多类识别正确率。     

基于双树复小波变换和GBDT的运动想象脑电识别

针对脑机接口研究中的脑电信号特征提取与分类问题,提出了一种基于双树复小波变换结合GBDT的想象左右手运动脑电识别的方法。该方法首先深入研究了双树复小波变换相比于小波包变换在脑电信号特征提取方面的优势并验证了ERD/ERS现象;实验数据采用了2003年国际脑机接口竞赛的标准数据集DataSetⅢ,然后,选取了4个典型的时间段进行实验对比,利用双树复小波变换分解与重构提取运动感知节律相关信号分量的能量均值作为特征进行GBDT分类。最后,实验取得了较好的分类准确度,验证了双树复小波变换结合GBDT的方法在脑电信号识别应用中的有效性。     

基于Mahalanobis距离的运动意识分类研究

提出基于Mahalanobis距离判别式算法的意识任务分类方法.对被测试者想象左右手运动时脑电信号的mu节律能量变化进行在线动态分析,提取EEG(C3,C4)两个通道的mu节律能量作为特征向量,用Mahalanobis距离判别式算法对左右手运动想象脑电模式进行分类,实验结果表明,正确识别率可达87.86%.     

An improved method to calculate phase locking value based on Hilbert–Huang transform and its application

Phase synchronization analysis has been demonstrated to be a useful method to infer brain function and neural activity based on electroencephalography (EEG) signals. The phase locking value (PLV) is one of the most important tools for phase synchronization analysis. Although the traditional method (TM) to calculate PLV, which is based on the Hilbert transform, has been applied extensively, some of methodological problems of TM have not been solved. To address these problems, this paper proposes an improved method (IM) to calculate the PLV based on the Hilbert–Huang transform. For the IM, the Hilbert–Huang transform, instead of the Hilbert transform, is used to process non-stationary EEG signals and the empirical mode decomposition, not band-pass filter, is used to get target frequency band. The performance of the IM is evaluated by comparing normal and hypoxia EEG signals. The PLVs are used as features for a least squares support vector machine to recognize normal and hypoxia EEG. Experimental results show that the PLVs calculated by the IM can distinguish the EEG signals better than those calculated by TM.     

多类运动想象脑电信号的两级特征提取方法

共同空间模式（Common spatial pattern,CSP）是运动想象脑机接口（Brain-computer interface,BCI）中常用的特征提取方法,但对多类任务的分类正确率却明显低于两类任务.通过引入堆叠降噪自动编码器（Stacked denoising autoencoders,SDA）,提出了一种多类运动想象脑电信号（Electroencephalogram,EEG）的两级特征提取方法.首先利用一对多CSP（One versus rest CSP,OVR-CSP）将脑电信号变换到使信号方差区别最大的低维空间,然后通过SDA网络提取其中可以更好表达类别属性的高层抽象特征,最后使用Softmax分类器进行分类.在对BCI竞赛IV中Data-sets 2a的4类运动想象任务进行的分类实验中,平均Kappa系数达到0.69,表明了所提出的特征提取方法的有效性和鲁棒性.     

异步BCI系统中运动想象诱发脑电特征识别

针对异步运动想象脑机交互（Brain Computer Interface,BCI）系统中空闲状态检测和不同想象任务分类的问题,在小波变换提取脑电信号特征基础上,设计了阈值判别结合支持向量机的二级分类器。由于大脑想象单侧肢体运动时,会导致同侧和对侧运动皮层脑区EEG信号在μ节律上分别出现事件相关同步和去同步,而大脑处于空闲状态时则无此现象。基于大脑活动的这一特性,提出了小波能量阈值判别法,进行空闲状态检测,径向基核函数和交叉检验的支持向量机方法,进行左、右手运动想象任务分类。结果表明该分类器最佳分类正确率达到了80.7%,且整个时间消耗仅为3.0 s,可以较好地满足异步在线运动想象BCI系统的应用。     

面向运动想象脑电图识别的镜卷积神经网络

目的 脑电图（electroencephalogram,EEG）是一种灵活、无创、非侵入式的大脑监测方法,广泛应用于运动想象脑机接口系统中,运动想象脑电图识别精度是决定系统性能的关键因素。然而由于脑电图采集时间长、个体差异大等原因,导致单个受试者可用于模型训练的样本数量少,严重影响了卷积神经网络在脑电图识别任务中的表现。为此,本文提出一种镜卷积神经网络（mirror convolutional neural network,MCNN）模型,使用集成学习与数据扩增方法提高运动想象脑电图识别精度。方法 在训练阶段,基于源脑电通过互换左右侧脑电通道构造镜像脑电,并与源脑电一起用于源卷积网络训练,有效扩增了训练样本;在预测阶段,复制已训练源卷积网络作为镜像卷积网络,将测试集中的源脑电输入源卷积网络,构造的镜像脑电输入镜像卷积网络,集成源卷积网络与镜像卷积网络输出的类别预测概率,形成最终类别预测。结果 为了验证模型的有效性和通用性,基于3种不同运动想象脑电图识别卷积网络模型分别构造镜卷积网络,并在第4届脑机接口大赛2a与2b数据集上进行实验验证。实验结果与原始模型相比,运动想象四分类和二分类准确率分别平均提高了4.83%和4.61%,显著提高了识别精度。结论 本文面向运动想象脑电图识别,提出了镜卷积神经网络模型,通过集成学习与数据扩增方法提高运动想象识别精度,有效改善了运动想象脑机接口性能。     

基于多尺度Lempel-Ziv复杂度的运动想象脑电信号特征分析

运动想象脑电信号特征提取是脑机接口研究领域的重要问题,提出一种基于多尺度Lempel-Ziv复杂度的运动想象脑电信号特征提取算法.该算法是传统二值化Lempel-Ziv复杂度算法的改进,它将脑电信号分成多个不同幅值范围的区域,根据信号在各区域间的上升和下降趋势,对脑电信号进行二值化处理得到Lempel-Ziv复杂度.本...     

基于ERS/ERD的二级共空间模式的运动想象脑电信号特征提取

针对多类运动想象EEG信号在脑-机接口方面存在分类识别率低和被试者差异性的问题,提出了一种基于ERS/ERD现象的二级共空间模式特征提取的方法。首先对全部导联进行特定频段的小波包降噪和分解;其次对分解系数重构后的信号以手(左、右)和脚(脚、舌)这二类进行一级共空间模式获取空间滤波器并对其采用2-范数筛选准则,提取权重系数较大的N个导联;然后以优化导联的投影矩阵对手与脚进行空间滤波后的信号分别作为原始信号进行二级空间模式特征提取;最后采用支持向量机进行分类。采用BCI2005Ⅲa中三位被试者的数据进行仿真验证,得到分类正确率最高达到92.55%。结果表明,该方法对EEG信号的特征提取具有较好的效果。     

双树复小波特征在运动想象脑电识别中的应用

提出了一种基于双树复小波变换的运动想象脑电信号特征提取方法。针对传统离散小波抗混叠性差的缺陷,采用双树复小波变换对脑电信号进行分解与重构,得到各子带信号能量并进行归一化处理,选取α、β节律信号的归一化能量作为想象运动的特征进行SVM分类。通过对仿真信号的分析,证实双树复小波变换具有良好的混叠抑制能力和抗噪性。最后选用国际脑机接口竞赛和实验室实测的运动想象数据进行分类识别。实验结果表明,双树复小波变换是一种有效的特征提取方法,其运动想象特征的识别率要优于常用的特征分析方法。     

基于改进CSP算法的运动想象脑电信号分类方法

For the problem of low classification accuracy and poor real-time performance during the traditional common spatial patterns (CSP) algorithm for motor imagery EEG signal processing, a new analysis method of CSP EEG signal based on time space frequency domain is put forward. Firstly, the wavelet packet is used to decompose the original signal of EEG, the motor imagery EEG rhythm is extracted according to the frequency distribution of EEG signal, and the spatial features of EEG are extracted by improving CSP algorithm. Then, we introduce the time window to filter the EEG signals, and eliminate the influence of EEG fluctuation at the beginning and end of the motion imagery. Lastly, according to the characteristics of the physiological distribution of EEG signals in the brain cortex, the method based on spindle channel is used to process the EEG signal and analyze computational time of different algorithms and the classification results. The experimental results show that, the running time of the algorithm is 1.562 s, which is 67% shorter than the traditional method, and the average classification accuracy is up to 97.5% when the number of spindle channels is 29 and the time window is 2 s. In the meantime, the results show that the proposed method can effectively improve the classification accuracy and the real-time performance of motor imagery EEG.     

Clustering technique-based least square support vector machine for EEG signal classification

This paper presents a new approach called clustering technique-based least square support vector machine (CT-LS-SVM) for the classification of EEG signals. Decision making is performed in two stages. In the first stage, clustering technique (CT) has been used to extract representative features of EEG data. In the second stage, least square support vector machine (LS-SVM) is applied to the extracted features to classify two-class EEG signals. To demonstrate the effectiveness of the proposed method, several experiments have been conducted on three publicly available benchmark databases, one for epileptic EEG data, one for mental imagery tasks EEG data and another one for motor imagery EEG data. Our proposed approach achieves an average sensitivity, specificity and classification accuracy of 94.92%, 93.44% and 94.18%, respectively, for the epileptic EEG data; 83.98%, 84.37% and 84.17% respectively, for the motor imagery EEG data; and 64.61%, 58.77% and 61.69%, respectively, for the mental imagery tasks EEG data. The performance of the CT-LS-SVM algorithm is compared in terms of classification accuracy and execution (running) time with our previous study where simple random sampling with a least square support vector machine (SRS-LS-SVM) was employed for EEG signal classification. We also compare the proposed method with other existing methods in the literature for the three databases. The experimental results show that the proposed algorithm can produce a better classification rate than the previous reported methods and takes much less execution time compared to the SRS-LS-SVM technique. The research findings in this paper indicate that the proposed approach is very efficient for classification of two-class EEG signals.     

基于汉语音位发音想象的脑机接口研究

该文提出了一个基于汉语音位发音想象的脑机接口系统框架,使得受试者使用脑机接口系统时能更加自然和流畅。三名受试者参与了本实验研究,实验过程中受试者被要求想象四个汉语元音和四个辅音音位的发音部位及语音发音,以及一个不作想象任务的控制条件,同时记录其脑电数据。在数据处理阶段,本文对采集到的头皮脑电数据进行了频域、时域、空域分析,以提取出音位发音想象效应最优化的特征向量用于提高每两个条件间的配对分类效果。实验结果表明,音位发音想象效应的最优脑电频段为2~10Hz,时段为刺激呈现后300~500ms,头皮空间分布主要集中在感觉运动皮层区域。音位发音想象任务和控制条件相比具有较高的分类正确率,最高可达83%,为基于音位发音想象的汉语脑机接口系统研究提供了理论基础。此外,刺激材料间的Jaccard距离和分类正确率的高度相关性表明,音位发音想象任务可被视为复杂的发音器官运动想象任务,并且可由人脑感觉运动皮层区域的脑电信号来解码预测。     

分层向量自回归的多通道脑电信号的特征提取研究

有效的特征提取方法能提高脑机接口（Brain-computer interface,BCI）系统对脑电（Electroencephalogram,EEG）信号的识别率.因脑电信号都是多通道的,本文将分层向量自回归（Hierarchical vector autoregression,HVAR）模型用于脑电信号的特征提取,并结合传统的线性支持向量机（Support vector machine,SVM）用于脑电信号识别.该模型不仅克服了自回归（Autoregression,AR）模型只能用来提取单通道特征的局限性,而且不再采用传统VAR（Vector autoregression）模型所有通道共用一个时滞的处理方法.创新之处在于在传统的VAR模型基础上添加正则化思想,有效地压缩参数空间,实现合理的分层结构.本文首次将HVAR模型用于由Keirn等采集并整理的脑电数据中.实验结果证明HVAR模型在阶数较小的情况下（2阶）与阶数较大（6阶）的AR模型效果相当,可见低阶的HVAR能很好地刻画脑电信号的时空关联关系,这说明HVAR可能是刻画EEG信号的一种新颖的方法,这对其他多通道时间序列分析都有借鉴意义.     

Event-related (De)synchronization (ERD/ERS) during motor imagery tasks: Implications for brain-computer interfaces

The primary aims of this research were to examine (1) mu and beta event-related desynchronization/synchronization (ERD/ERS) during motor imagery tasks with varying movement duration and (2) the potential impacts of movement duration on ERD/ERS patterns. Motor imagery tasks included brief and continuous imagined hand movements. During an imagery task, participants imagined an indicated movement for 1 s (i.e., brief movement imagery) or 5 s (i.e., continuous movement imagery). The results of the study support (1) that mu and beta ERD/ERS patterns are elicited during imagined hand movements and (2) that movement duration affects ERS and does not affect ERD patterns, during motor movement imagery. Additionally, brief movement imagery had a greater impact on mu and beta ERD; continuous movement imagery had a greater impact on mu and beta ERS. This research will be useful for designing future brain-computer interfaces as it provides valuable insight into the dynamics of electroencephalographic (EEG) oscillatory changes during motor imagery tasks with varying movement duration.

Relevance to industry

: Brain-computer interfaces (BCIs) have gained considerable interests by both research and industry communities who want to improve the quality of life for those who suffer from severe motor disabilities, such as amyotrophic lateral sclerosis (ALS), brainstem stroke, and cerebral palsy (CP). The results of this study should be applied to EEG-based BCI system design in order to enhance accuracy and classification performance for BCI system control.     

Classifying mental tasks based on features of higher-order statistics from EEG signals in brain-computer interface

In order to characterize the non-Gaussian information contained within the EEG signals, a new feature extraction method based on bispectrum is proposed and applied to the classification of right and left motor imagery for developing EEG-based brain-computer interface systems. The experimental results on the Graz BCI data set have shown that based on the proposed features, a LDA classifier, SVM classifier and NN classifier outperform the winner of the BCI 2003 competition on the same data set in terms of either the mutual information, the competition criterion, or misclassification rate.