This study addresses the problem of classifying emotional words based on recorded electroencephalogram （EEG） signals by the single-trial EEG classification technique. Emotional two-character Chinese words are used a...This study addresses the problem of classifying emotional words based on recorded electroencephalogram （EEG） signals by the single-trial EEG classification technique. Emotional two-character Chinese words are used as experimental materials. Positive words versus neutral words and negative words versus neutral words are classified, respectively, using the induced EEG signals. The method of temporally regularized common spatial patterns （TRCSP） is chosen to extract features from the EEG trials, and then single-trial EEG classification is achieved by linear discriminant analysis. Classification accuracies are between 55% and 65%. The statistical significance of the classification accuracies is confirmed by permutation tests, which shows the successful identification of emotional words and neutral ones, and also the ability to identify emotional words. In addition, 10 out of 15 subjects obtain significant classification accuracy for negative words versus neutral words while only 4 are significant for positive words versus neutral words, which demonstrate that negative emotions are more easily identified.展开更多
Abstract-Common spatial pattern （CSP） algorithm is a successful tool in feature estimate of brain-computer interface （BCI）. However, CSP is sensitive to outlier and may result in poor outcomes since it is based on...Abstract-Common spatial pattern （CSP） algorithm is a successful tool in feature estimate of brain-computer interface （BCI）. However, CSP is sensitive to outlier and may result in poor outcomes since it is based on pooling the covariance matrices of trials. In this paper, we propose a simple yet effective approach, named common spatial pattern ensemble （CSPE） classifier, to improve CSP performance. Through division of recording channels, multiple CSP filters are constructed. By projection, log-operation, and subtraction on the original signal, an ensemble classifier, majority voting, is achieved and outlier contaminations are alleviated. Experiment results demonstrate that the proposed CSPE classifier is robust to various artifacts and can achieve an average accuracy of 83.02%.展开更多
Objective Classifying motor imagery tasks via functional near-infrared spectroscopy(fNIRS)poses a significant challenge in brain-computer interface(BCI)research due to the high-dimensional nature of the signals.This s...Objective Classifying motor imagery tasks via functional near-infrared spectroscopy(fNIRS)poses a significant challenge in brain-computer interface(BCI)research due to the high-dimensional nature of the signals.This study aimed to address this challenge by employing the common spatial pattern(CSP)algorithm to reduce input dimensions for support vector machine(SVM)and linear discriminant analysis(LDA)classifiers.Methods Data were collected from 15 healthy right-handed volunteers performing tasks involving left-hand motion,left-hand motor imagery,right-hand motion,and right-hand motor imagery.Signals from 20-channel fNIRS were utilized,with input features including statistical descriptors such as mean,variance,slope,skewness,and kurtosis.The CSP algorithm was integrated into both SVM and LDA classifiers to reduce dimensionality.The main statistical methods included classification accuracy assessment and comparison.Results Mean and slope were found to be the most discriminative features.Without CSP,SVM and LDA classifiers achieved average accuracies of 59.81%±0.97%and 69%±11.42%,respectively.However,with CSP integration,accuracies significantly improved to 81.63%±0.99%and 84.19%±3.18%for SVM and LDA,respectively.This value represents an increase of 21.82%and 15.19%in accuracy for SVM and LDA classifiers,respectively.Dimensionality reduction from 100 to 25 dimensions was achieved for SVM,leading to reduced computational complexity and faster calculation times.Additionally,the CSP technique enhanced LDA classifier accuracy by 3.31%for both motion and motor imagery tasks.Conclusion Integration of the CSP algorithm may demonstrate promising potential for improving BCI systems'performance.展开更多
为提高运动想象脑机接口识别准确率,结合共空间模式(common spatial pattern,CSP)和卷积神经网络(convolutional neural network,CNN)方法,提出一种改进滤波器组共空间模式(filter bank common spatial pattern,FBCSP)和CNN的算法,用于...为提高运动想象脑机接口识别准确率,结合共空间模式(common spatial pattern,CSP)和卷积神经网络(convolutional neural network,CNN)方法,提出一种改进滤波器组共空间模式(filter bank common spatial pattern,FBCSP)和CNN的算法,用于多分类运动想象脑电信号识别任务。信号预处理后,使用包含重叠频带的FBCSP计算空间投影矩阵,数据经过投影得到更有区分度的特征序列。然后将特征序列以二维排列方式输入搭建的CNN模型中进行分类。所提出方法在脑机接口竞赛数据集2a和Ⅲa上验证,并和其他文献方法对比。结果表明,本文方法一定程度上提高了运动想象脑电信号的分类准确率,为运动想象研究提供了一个有效办法。展开更多
为解决运动想象脑电(electroencephalogram, EEG)信号多分类传输速率慢、准确率低的问题,本研究利用“一对多”滤波组共空间模式(one vs rest filter bank common spatial pattern, OVR-FBCSP)和稀疏嵌入(sparse embeddings, SE)提出了...为解决运动想象脑电(electroencephalogram, EEG)信号多分类传输速率慢、准确率低的问题,本研究利用“一对多”滤波组共空间模式(one vs rest filter bank common spatial pattern, OVR-FBCSP)和稀疏嵌入(sparse embeddings, SE)提出了一种基于SE的多分类EEG信号分类方法。为降低多类任务特征提取的复杂度,提高分类效率,本方法首先采用OVR-FBCSP进行EEG信号特征提取;然后对其相应的标签矩阵进行低维嵌入,构建稀疏嵌入模型,分别计算训练和测试数据的嵌入矩阵;最后在嵌入空间中对训练和测试数据执行k最近邻(k-nearest neighbor, kNN)分类。本研究在BCI Competition IV-2a公开数据集进行了实验测试,并与其他分类方法进行了对比。实验结果表明,本研究方法拥有较高的分类准确率和较短的分析时间。展开更多
基金The National Natural Science Foundation of China(No.61375118)the Program for New Century Excellent Talents in University of China(No.NCET-12-0115)
文摘This study addresses the problem of classifying emotional words based on recorded electroencephalogram （EEG） signals by the single-trial EEG classification technique. Emotional two-character Chinese words are used as experimental materials. Positive words versus neutral words and negative words versus neutral words are classified, respectively, using the induced EEG signals. The method of temporally regularized common spatial patterns （TRCSP） is chosen to extract features from the EEG trials, and then single-trial EEG classification is achieved by linear discriminant analysis. Classification accuracies are between 55% and 65%. The statistical significance of the classification accuracies is confirmed by permutation tests, which shows the successful identification of emotional words and neutral ones, and also the ability to identify emotional words. In addition, 10 out of 15 subjects obtain significant classification accuracy for negative words versus neutral words while only 4 are significant for positive words versus neutral words, which demonstrate that negative emotions are more easily identified.
基金supported by the National Natural Science Foundation of China under Grant No. 30525030, 60701015, and 60736029.
文摘Abstract-Common spatial pattern （CSP） algorithm is a successful tool in feature estimate of brain-computer interface （BCI）. However, CSP is sensitive to outlier and may result in poor outcomes since it is based on pooling the covariance matrices of trials. In this paper, we propose a simple yet effective approach, named common spatial pattern ensemble （CSPE） classifier, to improve CSP performance. Through division of recording channels, multiple CSP filters are constructed. By projection, log-operation, and subtraction on the original signal, an ensemble classifier, majority voting, is achieved and outlier contaminations are alleviated. Experiment results demonstrate that the proposed CSPE classifier is robust to various artifacts and can achieve an average accuracy of 83.02%.
文摘Objective Classifying motor imagery tasks via functional near-infrared spectroscopy(fNIRS)poses a significant challenge in brain-computer interface(BCI)research due to the high-dimensional nature of the signals.This study aimed to address this challenge by employing the common spatial pattern(CSP)algorithm to reduce input dimensions for support vector machine(SVM)and linear discriminant analysis(LDA)classifiers.Methods Data were collected from 15 healthy right-handed volunteers performing tasks involving left-hand motion,left-hand motor imagery,right-hand motion,and right-hand motor imagery.Signals from 20-channel fNIRS were utilized,with input features including statistical descriptors such as mean,variance,slope,skewness,and kurtosis.The CSP algorithm was integrated into both SVM and LDA classifiers to reduce dimensionality.The main statistical methods included classification accuracy assessment and comparison.Results Mean and slope were found to be the most discriminative features.Without CSP,SVM and LDA classifiers achieved average accuracies of 59.81%±0.97%and 69%±11.42%,respectively.However,with CSP integration,accuracies significantly improved to 81.63%±0.99%and 84.19%±3.18%for SVM and LDA,respectively.This value represents an increase of 21.82%and 15.19%in accuracy for SVM and LDA classifiers,respectively.Dimensionality reduction from 100 to 25 dimensions was achieved for SVM,leading to reduced computational complexity and faster calculation times.Additionally,the CSP technique enhanced LDA classifier accuracy by 3.31%for both motion and motor imagery tasks.Conclusion Integration of the CSP algorithm may demonstrate promising potential for improving BCI systems'performance.
文摘为提高运动想象脑机接口识别准确率,结合共空间模式(common spatial pattern,CSP)和卷积神经网络(convolutional neural network,CNN)方法,提出一种改进滤波器组共空间模式(filter bank common spatial pattern,FBCSP)和CNN的算法,用于多分类运动想象脑电信号识别任务。信号预处理后,使用包含重叠频带的FBCSP计算空间投影矩阵,数据经过投影得到更有区分度的特征序列。然后将特征序列以二维排列方式输入搭建的CNN模型中进行分类。所提出方法在脑机接口竞赛数据集2a和Ⅲa上验证,并和其他文献方法对比。结果表明,本文方法一定程度上提高了运动想象脑电信号的分类准确率,为运动想象研究提供了一个有效办法。
