基于共空间模式与决策树支持向量机的运动想象脑电信号分类

针对脑电信号(Electroencephalogram,EEG)采集易受干扰导致EEG分类准确率低的问题,提出一种基于共空间模式(Common Spatial Pattern,CSP)与决策树支持向量机法(Decision Tree Support Vector Machine,DTSVM)相融合的运动想象脑电信号处理方法。首先利用CSP算法对运动想象的EEG特征值进行特征提取,其次运用线性判别分析法(Linear Discriminant Analysis,LDA)、自适应增强分类法(Adaptive Boosting,Adaboost)和决策树支持向量机法分别对特征进行分类,最后通过实验对比发现,利用决策树支持向量机进行分类的分类效果最佳,分类准确率最高可达到92.52%。     

脑电信号多特征融合与卷积神经网络算法研究

针对脑电信号（electroencephalogram,EEG）运动想象中单一特征无法多维表征信号中的信息导致的分类准确率不高的问题,提出一种基于样本熵和共空间模式特征融合的特征提取算法。算法先对原始脑电信号进行小波包分解,从中选择包含μ和β节律的分量进行重构,然后分别提取重构信号的样本熵和CSP(common spatial pattern,CSP)特征,将两者融合组成新的特征向量,使用所设计的一维卷积神经网络对其进行识别获得分类结果。所提方法在2003年BCI Dataset Ⅲ中获得了91.66%的分类准确率,在2008年BCI Dataset A中获得了85.29%的平均分类准确率。与近年来文献中提出的多特征融合算法相比,准确率提高了7.96个百分点。     

基于脑电时频空多域特征融合的情感识别研究

传统基于脑电信号（electroencephalogram,EEG）的情感识别主要采用单一的脑电特征提取方法,为了充分利用EEG中蕴含的丰富信息,提出一种多域特征融合的脑电情感识别新方法。提取了EEG的时域、频域和空域特征,将三域特征进行融合作为情感识别模型的输入。首先计算不同时间窗EEG信号的alpha、beta、gamma三个频段功率谱密度,并结合脑电电极空间信息构成EEG图片,然后利用卷积神经网络（convolutional neural network,CNN）与双向长短期记忆网络（bidirectional long short-term memory network,BLSTM）构建CNN-BLSTM情感识别模型,分别对时、频、空三域特征进行学习。在SEED数据集对该方法进行验证,结果表明该方法能有效提高情感识别精度,平均识别准确率达96.25%。     

基于稀疏组lasso-granger因果关系特征的脑电信号情感识别

针对目前基于单一脑区功能性网络层面的特征提取,文中提出稀疏组lasso-granger因果关系方法.首先从效应性脑网络层面提取不同脑区之间的因果关系作为脑电特征,分别提取受试者α,β,γ脑电波段的granger因果特征值.然后引用稀疏组lasso算法对获取的granger因果特征值进行特征筛选,获得高相关性特征子集作为情感分类特征.最后使用SVM分类器进行情感分类.此外,为了减少计算时间复杂度,使用过滤特征选择(ReliefF)算法,选取有效的脑电信号通道.实验表明,文中方法在Valence-Arousal二维情感模型上获得较高的平均情感分类准确率,分类效果优于对比的脑电特征,提取的情感脑电特征可以有效识别受试者的不同情感状态.     

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。     

基于卷积联合适应网络的脑电信号情感识别

提出一种基于深度卷积联合适应网络（Convolutional neural network-joint adaptation network,CNN-JAN）的脑电信号（Electroencephalogram, EEG）情感识别模型。该模型将迁移学习中联合适应的思想融合到深度卷积网络中,首先采用长方形卷积核提取数据的空间特征,捕捉脑电数据通道间的深层情感相关信息,再将提取的空间特征输入含有联合分布的多核最大均值差异算法（Multi-kernel joint maximum mean discrepancy,MK-JMMD）的适配层进行迁移学习,使用MK-JMMD度量算法解决源域和目标域分布不同的问题。所提方法在SEED数据集上使用微分熵特征和微分尾端性特征分别进行情感分类实验,其中使用微分熵特征被试内跨试验准确率达到84.01%,与对比实验和目前流行的迁移学习方法相比,准确率进一步提高,跨被试实验精度也取得较好的性能,验证了该模型用于EEG信号情感识别任务的有效性。     

基于数据空间自适应与共空间模式的脑电情感分类

为缓解日间脑电信号波动和差异导致情感分类性能下降的问题,在数据空间自适应(DSA)与共空间模式(CSP)迭代的基础上,提出一种用于脑电情感分类的特征提取算法。针对12个受试者连续5 d的情感脑电信号,采用DSA算法对脑电信号进行空间线性变换,再使用CSP将脑电信号变换到最优子空间,提取日间差异最小且类间差异最大的脑电功率谱密度特征及微分偏侧与差异因果特征。实验结果表明,该算法能提高脑电信号情感分类的准确率和稳定性。     

基于多级SVM分类的语音情感识别算法

为了提高语音情感识别系统的识别准确率,本文在传统支持向量机(SVM)方法的基础之上,提出了一种基于PCA的多级SVM情感分类算法。首先将容易区分的情感分开,针对混淆度大且不能再利用多级分类策略直接进行区分的情感,采用主成分分析法(PCA)进行特征降维,然后逐级地判断出输入语音所属的情感类型。与传统基于SVM分类算法的语音情感识别相比,本文提出的方法可将7种情感的平均识别率提高5.05%,并且特征维度可降低58.3%,从而证明了本文所提出的方法的正确性与有效性。     

WPD-CSP脑电特征提取方法的时间优化

基于小波包分解和共空域模式的方法(WPD-CSP)弥补了CSP方法的频率缺陷,但是非常耗时.针对此问题,提出基于通道选择的WPD-CSP改进方法.使用Fisher判别准则(FDC)选择被试特异的最优通道,对选择的通道进行WPD分解,选择与运动想象任务相关的频率子带进行CSP特征提取,采用Fisher线性判别分析(FLDA)进行分类.使用公开的脑机接口(BCI)竞赛数据集和自采集数据集进行实验,所提方法分别取得了83.11％ 和71.49％ 的最高平均分类准确率.与现有方法相比,该方法具有较好的分类准确率,减少了特征提取的时间.     

基于情感特征向量空间模型的中文商品评论倾向分类算法

为了能够快速有效地将中文商品评论识别为好评或差评,提出一种算法。针对不同类别的商品,预先根据其评论语料构建领域情感词典,评论文本与情感词典集匹配提取情感特征,构建情感特征向量空间模型SF-VSM(Sentiment Feature Vector Space Model),解决传统的特征向量空间模型维数较高及特征选择误差问题。然后基于该模型结合改进的多项式朴素贝叶斯方法对评论进行情感倾向分类。实验结果表明,相比分别基于原始特征和基于χ2特征选取的朴素贝叶斯分类算法,该算法分类精度较高且分类速度快。     

基于脑功能网络和共空间模式分析脑电情绪识别

传统脑网络的情绪分类将聚类系数、平均最短路径等拓扑属性作为分类特征。针对这些属性易受网络连接阈值和特征选择的影响,难以完全表征不同情绪状态下的网络空间拓扑结构差异的问题,提出了一种基于脑网络和共空间模式的脑电情绪识别方法(EEG emotion classification based on common spatial patterns of brain networks topology,EEC-CSP-BNT)。该算法基于互信息在各个子频段内计算电极间的功能连接矩阵,同时利用共空间模式(common spatial pattern,CSP)分析学习空间滤波器,构建分类特征,最后通过分类器(如Fisher线性判别、支持向量机、K最近邻)实现基于脑电的情绪分类。基于DEAP和SEED数据集的实验结果表明,相比于脑网络拓扑属性,EEC-CSP-BNT能有效提取脑网络拓扑结构的分类信息,提高脑电情绪识别性能。     

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.     

Learning optimal spatial filters by discriminant analysis for brain-computer-interface

Common Spatial Pattern (CSP) is one of the most widespread methods for Brain-Computer Interfaces (BCI), which is capable of enhancing the separability of the brain signals such as multi-channel electroencephalogram (EEG). CSP attempts to strengthen the separability by maximizing the variance of the spatially filtered signal of one class while minimizing it for another class. A straightforward way to improve the CSP is to employ the Fisher-Rao linear discriminant analysis (FLDA). But for the two-class scenario in BCI, FLDA merely result in as small as one filter. Experimental results have shown that the number of spatial filter is too small to achieve satisfying classification accuracy. Therefore, more than one filter is expected to get better performance. To deal with this difficulty, in this paper we propose to divide each class into many sub-classes (clusters) and formulate the problem in a re-designed graph embedding framework where the vertexes are cluster centers. We also reformulate the traditional FLDA in our graph embedding framework, which helps developing and understanding the proposed method. Experimental results demonstrate the advantages of the proposed method.     

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。     

Optimized spatial filters as a new method for mass spectrometry-based cancer diagnosis

In the past two decades, mass spectrometry-based identification of serum proteomic patterns has emerged as a new diagnostic tool for the early detection of various types of cancers. However, due to its high dimensionality, the analysis of mass spectrometry data poses considerable challenges. Existing methods proposed for the analysis of mass spectrometry data usually consist of a number of steps. In this study, a comparatively simple but efficient method, namely, an optimal spatial filter (OSF) method, is proposed for the classification of mass spectrometry data. The newly proposed method is based on the theory of common spatial patterns (CSPs), which are widely used to classify motor imagery EEG signals in brain-computer interface (BCI) applications. The CSP method aims to find spatial filters to project the data into a new space in which optimal discrimination between classes is achieved. Although it has been shown that the CSP method performs quite well in classifying motor imagery EEG signals, it has a major drawback. In the CSP method, the between-class variance is maximized, but the minimization of within-class variance is ignored. As a result, the projected data may have large within-class variances. To overcome this problem, in this study, optimal filters are found by using the differential evolution (DE) algorithm. For the fitness function of the differential evolution algorithm, a divergence analysis is used. In the divergence analysis, both the between-class and within-class distributions of the projected data are considered. The experimental results obtained using publicly available mass spectrometry datasets showed that, when compared to existing methods, the proposed OSF method is quite simple and achieves the minimum classification error for each dataset. Furthermore, the proposed OSF method highlights the importance of certain parts of the spectra, which is highly valuable for the identification of biomarkers that lie outside the pathological pathway of the disease.     

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。     

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.     

面向脑电情感识别的改进多分类RVM模型研究

从相关向量机（RVM）和支持向量机（SVM）的相似性以及RVM的稀疏特性出发，将RVM应用于脑电信号（EEG）的情感识别中。针对一对一（OAO）和一对多（OAA）两种多分类方法各自的特点和不足，提出了一种全新的两层多分类模型（OAA-OAO），改进现有OAO算法中无效投票影响最终决策的现象。设计情感EEG信号识别对比实验，验证基于RVM的改进多分类算法在脑电信号情感识别中的应用。对于实验室采集的情感脑电信号，提取其非线性特征（功率谱熵、样本熵和Hurst指数）并采用主成分分析法进行降维。将OAA-OAO-RVM算法分别和OAO-SVM、OAO-RVM两种识别网络进行对比，分析RVM的识别性能以及OAA-OAO多分类算法的分类性能。结果表明，采用降维后的最优特征集合作为识别网络的输入向量得到的识别性能更高，且RVM表现出的性能优于SVM。同时，改进后的OAA-OAO算法较传统OAO模型的平均识别率提高了7.89%，证明OAA-OAO算法可有效去除一部分无效投票从而使分类精度得到显著提高，验证了此模型是一种有效的多分类模型。     

An EEG emotion recognition method based on transfer learning and echo state network for HilCPS

As a new cyber physical application, emotion recognition has been shown to make human-in-the-loop cyber-physical system (HilCPS) more efficient and sustainable. Therefore, emotion recognition is of great significance for HilCPS. Electroencephalogram (EEG) signals contain abundant and useful information, and can objectively reflect human emotional states. According to EEG signals, using machine learning to recognize emotion is the main method at present. This method depends on the quantity and quality of samples as well as the capability of classification model. However, the quantity of EEG samples is often insufficient and the quality of EEG samples is often irregular. Meanwhile, EEG samples possess strong nonlinearity. Therefore, an EEG emotion recognition method based on transfer learning (TL) and echo state network (ESN) for HilCPS is proposed in this paper. First, a selection algorithm of EEG samples based on average Frechet distance is proposed to improve the sample quality. Second, a feature transfer algorithm of EEG samples based on transfer component analysis is proposed to expand the sample quantity. Third, in order to solve the problem of the nonlinearity of EEG samples, a classification model of EEG samples based on ESN is constructed to accurately classify emotional states. Finally, experimental results show that compared with traditional methods, the proposed method can expand the quantity of the high-quality EEG samples and effectively improve the accuracy of emotion recognition.