运动想象脑电信号的跨域特征学习方法

运动想象脑电信号采集成本高且个体差异大,跨个体域构建脑电信号模式识别模型属于典型的小样本跨域学习任务。针对该任务,提出了一种运动想象脑电信号的跨域特征学习方法。该方法首先选择最优度量方法对齐协方差并提取共同空间模式特征;其次,在该特征基础上采用领域自适应方法学习目标域的最优跨域特征。为验证所提方法的可行性与有效性,采用经典模型识别跨域特征,在两个公开的数据集上进行对比实验。实验结果表明,通过所提方法学习到的跨域特征,在运动想象模式识别中,明显优于现有方法学习到的特征。此外,还详细对比了跨域特征学习方法的各项参数设置、性能及效率。     

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.     

Harmonic Mean of Kullback–Leibler Divergences for Optimizing Multi-Class EEG Spatio-Temporal Filters

The common spatial patterns (CSP) is a classical approach to spatial filtering of electroencephalogram (EEG) used in brain-computer interfaces. The local temporal common spatial patterns (LTCSP) method is a temporal generalization of CSP. Both CSP and LTCSP, however, are only suitable for the two-class paradigm. In this paper, we address this limitation under the framework of Kullback?CLeibler (KL) divergence. We show that CSP is equivalent to maximizing the symmetric KL divergence of two class-conditional probability density functions under the Gaussian assumption. This analysis establishes a probabilistic interpretation for CSP, as well as LTCSP. Based on the KL formulation, we propose a new multi-class extension to optimizing the spatio-temporal filters by maximizing the harmonic mean of all pairs of symmetric KL divergences between the filtered class-conditional densities. Experiments of classification of multiple EEG classes on the data sets of BCI competition show the effectiveness of the proposed methods.     

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.     

多任务运动想象脑电特征的融合分类研究

针对运动想象脑-机交互任务模式单一、识别精度低、实用性较差等问题,采用改进的共空间模式（CSP）的特征提取方法,并利用支持向量机（SVM）与CSP融合分类方法对多类任务运动想象脑电特征进行分类识别。首先,选择特定导联上的脑电信号进行小波分解与重构,去除冗余信息;其次,利用特征参数做差的方法,得到较为明显的脑电特征;最后,通过SVM融合CSP的分类模式,对脑电特征进行多任务分类。利用BCI竞赛数据,对左手,右手,舌和脚四类运动想象任务的脑电进行识别。结果表明：分类正确率最高达到90.9%,平均正确率为86.8%,Kappa系数为0.8867,信息传输速率可达0.68 bit/trial,能够有效的获得脑电特征并较好的实现多任务运动想象脑电识别。     

相异度导引的有监督鉴别分析方法

提出了相异度导引的有监督鉴别分析方法（D-SDA）。结合模式局部信息和全局信息,定义了类内散度权重矩阵[RW]和类间散度权重矩阵[RB],分别表示类内样本的相异度、类间样本的相异度。由[RW]、[RB]导出类内散度矩阵[SW]和类间散度矩阵[SB],根据Fisher鉴别准则函数确定最优变换矩阵。在YALE和AR人脸图像库上的实验验证了这一算法的有效性。     

基于训练样本评估的CSP滤波器增量更新方法

由于脑电图(electro encephalo gram,EEG)能反映不同状态下大脑的思维活动,因此,基于EEG的运动想象识别已经成为一个新的研究热点。为了降低低质量样本对CSP(common spatial pattern)滤波器模型的组间传输性能的影响,提高正确率,提出了一种基于样本筛选的CSP滤波器增量更新方法。首先通过样本筛选的方法对EEG数据进行质量评估,然后剔除低识别率对应的单次训练数据,最后对优化后的样本所设计的CSP滤波器进行增量更新。实验室环境下,对EEG信号进行运动想象识别,其平均正确率达到80.92%,相比传统的CSP方法,五位受试者测试集的平均识别率分别提高了5.4%、5.6%、1.5%、8.6%和7.7%,实验结果验证了所提算法的有效性。     

重叠特征策略与参数优化的运动想象脑电模式识别

针对运动想象脑电信号的非线性、非平稳特性,提出重叠特征策略与参数优化方法.通过重叠频带滤波(OFB)进行预处理,在滤波后的信号上提取共同空间模式特征(CSP).将OFB-CSP特征输入鲁棒支持矩阵机,完成模式识别,在模式识别中通过校正粒子群算法(CPSO)动态调整被试个体最优参数.在两个公开数据集上进行实验,分别验证OFB预处理可提升CSP特征区分度,CPSO可为个体寻找最优的鲁棒支持矩阵机分类参数.文中方法提升运动想象识别率,样本和计算资源需求较小,适合脑机接口的实际应用.     

中心线邻域鉴别嵌入算法及其在人脸识别中的应用*

针对边界费舍尔分析在特征提取过程中存在的不足,提出中心线邻域鉴别嵌入(CLNDE)算法,并应用于人脸识别中.CLNDE首先利用样本到类中心线的距离分别构造类内相似矩阵与类间相似矩阵;然后利用构造的相似矩阵计算样本的类间局部散度与类内局部散度;最后在最大化样本的类间局部散度的同时最小化类内局部散度,寻求最优投影矩阵.在人脸数据库上实验验证算法的优越性.     

多通道三维视觉指导运动想象脑电信号特征选择算法

针对基于三维视觉指导的运动想象脑机接口多通道冗余信息较多、分类准确率差的问题,提出了一种基于小波包分解（WPD）—共空间滤波（CSP）—自适应差分进化（ADE）的模式脑电信号特征提取与选择分类方法。首先,对采集的多通道运动想象脑电信号进行WPD变化,划分出精细的子频带;然后,分别将WPD变换后的每个子空间作为CSP的输入,得到对应的特征向量;最后,使用ADE算法对特征向量进行选择,选择出用于分类的最佳特征子集。采用WPD-CSP-ADE模式进行特征提取与选择,较经典的WPD-CSP方法在分类正确率、特征个数方面有着更好的表现。同时,所提算法分类性能明显优于遗传算法、粒子群算法。实验结果表明,WPD-CSP-ADE方法能够有效地提高分类正确率,同时减少了用于分类的特征个数。     

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。     

近邻类鉴别分析方法

提出一种近邻类鉴别分析方法,线性鉴别分析是该方法的一个特例。线性鉴别分析通过最大化类间散度同时最小化类内散度寻找最佳投影,其中类间散度是所有类之间散度的总体平均;而近邻类鉴别分析中类间散度定义为各个类与其k个近邻类之间的平均散度。该方法通过选取适当的近邻类数,能够缓解线性鉴别降维后造成的部分类的重叠。实验结果表明近邻类鉴别分析方法性能稳定且优于传统的线性鉴别分析。     

基于近似熵与CSP的异步BCI空闲状态检测方法

针对异步脑机接口（BCI）中空闲状态难以检测的问题,提出将近似熵与公共空间模式（CSP）综合的方法来处理. 在采用二级分类策略的前提下,通过近似熵与CSP方法分别从时间复杂度和空间模式上提取不同类型的脑电特征,利用这些特征训练出不同的分类器,然后使用多分类器投票的方法将它们综合以提高判断空闲状态的正确率. 将本文的方法运用到BCI竞赛数据中,得到最终具体想象任务的命中率（TPR）普遍比通过阈值法得到的结果要高. 数据处理的结果说明了本文方法对空闲状态检测的有效性.     

Mutual information-based optimization of sparse spatio-spectral filters in brain–computer interface

Recently, neuro-rehabilitation based on brain–computer interface (BCI) has been considered one of the important applications for BCI. A key challenge in this system is the accurate and reliable detection of motor imagery. In motor imagery-based BCIs, the common spatial patterns (CSP) algorithm is widely used to extract discriminative patterns from electroencephalography signals. However, the CSP algorithm is sensitive to noise and artifacts, and its performance depends on the operational frequency band. To address these issues, this paper proposes a novel optimized sparse spatio-spectral filtering (OSSSF) algorithm. The proposed OSSSF algorithm combines a filter bank framework with sparse CSP filters to automatically select subject-specific discriminative frequency bands as well as to robustify against noise and artifacts. The proposed algorithm directly selects the optimal regularization parameters using a novel mutual information-based approach, instead of the cross-validation approach that is computationally intractable in a filter bank framework. The performance of the proposed OSSSF algorithm is evaluated on a dataset from 11 stroke patients performing neuro-rehabilitation, as well as on the publicly available BCI competition III dataset IVa. The results show that the proposed OSSSF algorithm outperforms the existing algorithms based on CSP, stationary CSP, sparse CSP and filter bank CSP in terms of the classification accuracy, and substantially reduce the computational time of selecting the regularization parameters compared with the cross-validation approach.     

Face recognition using second-order discriminant tensor subspace analysis

Discriminant information (DI) plays a critical role in face recognition. In this paper, we proposed a second-order discriminant tensor subspace analysis (DTSA) algorithm to extract discriminant features from the intrinsic manifold structure of the tensor data. DTSA combines the advantages of previous methods with DI, the tensor methods preserving the spatial structure information of the original image matrices, and the manifold methods preserving the local structure of the samples distribution. DTSA defines two similarity matrices, namely within-class similarity matrix and between-class similarity matrix. The within-class similarity matrix is determined by the distances of point pairs in the same class, while the between-class similarity matrix is determined by the distances between the means of each pair of classes. Using these two matrices, the proposed method preserves the local structure of the samples to fit the manifold structure of facial images in high dimensional space better than other methods. Moreover, compared to the 2D methods, the tensor based method employs two-sided transformations rather than single-sided one, and yields higher compression ratio. As a tensor method, DTSA uses an iterative procedure to calculate the optimal solution of two transformation matrices. In this paper, we analyzed DTSA's connections to 2D-DLPP and TSA, theoretically. The experiments on the ORL, Yale and YaleB facial databases show the effectiveness of the proposed method.     

A multi-manifold discriminant analysis method for image feature extraction

In this paper, we propose a Multi-Manifold Discriminant Analysis (MMDA) method for an image feature extraction and pattern recognition based on graph embedded learning and under the Fisher discriminant analysis framework. In an MMDA, the within-class graph and between-class graph are, respectively, designed to characterize the within-class compactness and the between-class separability, seeking for the discriminant matrix to simultaneously maximize the between-class scatter and minimize the within-class scatter. In addition, in an MMDA, the within-class graph can represent the sub-manifold information, while the between-class graph can represent the multi-manifold information. The proposed MMDA is extensively examined by using the FERET, AR and ORL face databases, and the PolyU finger-knuckle-print databases. The experimental results demonstrate that an MMDA is effective in feature extraction, leading to promising image recognition performance.     

KPCA method based on within-class auxiliary training samples and its application to pattern classification

Principal component analysis (PCA) and kernel principal component analysis (KPCA) are classical feature extraction methods. However, PCA and KPCA are unsupervised learning methods which always maximize the overall variance and ignore the information of within-class and between-class. In this paper, we propose a simple yet effective strategy to improve the performance of PCA and then this strategy is generalized to KPCA. The proposed methods utilize within-class auxiliary training samples, which are constructed through linear interpolation method. These within-class auxiliary training samples are used to train and get the principal components. In contrast with conventional PCA and KPCA, our proposed methods have more discriminant information. Several experiments are respectively conducted on XM2VTS face database, United States Postal Service (USPS) handwritten digits database and three UCI repository of machine learning databases, experimental results illustrate the effectiveness of the proposed method.     

基于核的Fisher非线性最佳鉴别分析在人脸识别中的应用

抽取最佳鉴别特征是人脸识别中的重要一步。对小样本的高维人脸图像样本,由于各种抽取非线性鉴别特征的方法均存在各自的问题,为此提出了一种求解核的Fisher非线性最佳鉴别特征的新方法,该方法首先在特征空间用类间散度阵和类内散度阵作为Fisher准则,来得到最佳非线性鉴别特征,然后针对此方法存在的病态问题,进一步在类内散度阵的零空间中求解最佳非线性鉴别矢量。基于ORL人脸数据库的实验表明,该新方法抽取的非线性最佳鉴别特征明显优于Fisher线性鉴别分析(FLDA)的线性特征和广义鉴别分析(GDA)的非线性特征。     

Discriminative graph convolution networks for hyperspectral image classification

Recently, the proposal of graph convolutional networks (GCN) has successfully implemented into hyperspectral image data representation and analysis. In spite of the great success, there are still several major challenges in hyperspectral image classification, including within-class diversity, and between-class similarity, which generally degenerate hyperspectral image classification performance. To address the problems, we propose a discriminative graph convolution networks (DGCN) for hyperspectral image classification. This method introduces the concepts of within-class scatter and between-class scatter, which respectively reflect the global geometric structure and discriminative information of the input space. The experimental results on the hyperspectral data sets show that the proposed method has good classification performance.     

一种可调控制参数的LDA人脸识别算法

线性判别分析（LDA）方法进行高维的人脸识别时,经常会遇到小样本问题（SSS）和边缘类重叠问题。本文提出一种新的LDA方法,重新定义类内离散度矩阵,利用参数来权衡其特征值估计的偏差和方差,以解决小样本问题;对类间离散矩阵加权,让边缘类均匀分布,防止边缘类的重叠,以提高识别率。大量的实验已经证明该方法能根据小样本问题的严重度调控参数以达到最高识别率,比传统的方法更优。