At present,multi-channel electroencephalogram(EEG)signal acquisition equipment is used to collect motor imagery EEG data,and there is a problem with selecting multiple acquisition channels.Choosing too many channels w...At present,multi-channel electroencephalogram(EEG)signal acquisition equipment is used to collect motor imagery EEG data,and there is a problem with selecting multiple acquisition channels.Choosing too many channels will result in a large amount of calculation.Components irrelevant to the task will interfere with the required features,which is not conducive to the real-time processing of EEG data.Using too few channels will result in the loss of useful information and low robustness.A method of selecting data channels for motion imagination is proposed based on the time-frequency cross mutual information(TFCMI).This method determines the required data channels in a targeted manner,uses the common spatial pattern mode for feature extraction,and uses support vector ma-chine(SVM)for feature classification.An experiment is designed to collect motor imagery EEG da-ta with four experimenters and adds brain-computer interface(BCI)Competition IV public motor imagery experimental data to verify the method.The data demonstrates that compared with the meth-od of selecting too many or too few data channels,the time-frequency cross mutual information meth-od using motor imagery can improve the recognition accuracy and reduce the amount of calculation.展开更多
共空间模式侧重提取信号的空间信息,是脑电信号中滤波和特征提取的常用算法之一。然而脑电信号的时间窗、频带和通道的选择都会影响其分类结果。为了提高CSP特征的表征能力,采用了基于相关系数的脑电通道选择方法,结合时频共空间模式提...共空间模式侧重提取信号的空间信息,是脑电信号中滤波和特征提取的常用算法之一。然而脑电信号的时间窗、频带和通道的选择都会影响其分类结果。为了提高CSP特征的表征能力,采用了基于相关系数的脑电通道选择方法,结合时频共空间模式提取特征,提出了通道选择共时频空间模式(CS-CTFSP)新框架。首先利用通道间相关性,在主通道的基础上筛选合适的通道集合;并利用时频共空间模式从每个时间窗口的多个子频带中提取CSP特征;接着引入一种子频带筛选方法去除无区分能力的频带单元后,结合LASSO提取稀疏特征;最后采用LDA分类器对脑电信号进行分类。在对BCI Competition III Dataset IVa和BCI Competition IV Dataset I二分类运动想象任务的分类实验中,平均分类精度达到91.10%和87.92%,并与其他运动想象方法进行了比较,验证了本文方法的有效性。展开更多
The article examines the existing infrastructure of open common spaces within two New Belgrade mass housing blocks(Blocks 23 and 70a)through a typo-morphological analysis.These spaces between the buildings,although th...The article examines the existing infrastructure of open common spaces within two New Belgrade mass housing blocks(Blocks 23 and 70a)through a typo-morphological analysis.These spaces between the buildings,although the most neglected,underused,and deteriorated components of mass housing neighbourhoods,are at the same time crucial to the quality,vitality and integrated governance of these neighbourhoods.They represent the primary tangible commons in cities and neighbourhoods.The question of urban commons is increasingly present in scientific literature,urban and architectural discourse.Nevertheless,approaches exploring the spatiality of the urban commons are scarce,leading to insufficient understanding of the spatial aspect and potentials of the already existing commons.Therefore,this study includes(1)identification,typological decoding and classification of the common spaces,focusing on the case of New Belgrade blocks,followed by(2)analysis of the spatial patterns and integration of the identified spaces within the blocks.The study confirms the complexity and diverse typology of the common spaces.It finds that the in-between,common spaces contribute to higher integration of different segments of the blocks.The open common spaces have an essential role in humanisation of the blocks,and thus the quality of life in the blocks as integrated neighbourhoods.The findings indicate that the spatial setting of the open common spaces in New Belgrade blocks allows for(re)emergence of collective practices,leading to inclusive and integrated rehabilitation of the neighbourhoods.展开更多
基金Supported by the National Natural Science Foundation of China(No.51775325)National Key R&D Program of China(No.2018YFB1309200)the Young Eastern Scholars Program of Shanghai(No.QD2016033).
文摘At present,multi-channel electroencephalogram(EEG)signal acquisition equipment is used to collect motor imagery EEG data,and there is a problem with selecting multiple acquisition channels.Choosing too many channels will result in a large amount of calculation.Components irrelevant to the task will interfere with the required features,which is not conducive to the real-time processing of EEG data.Using too few channels will result in the loss of useful information and low robustness.A method of selecting data channels for motion imagination is proposed based on the time-frequency cross mutual information(TFCMI).This method determines the required data channels in a targeted manner,uses the common spatial pattern mode for feature extraction,and uses support vector ma-chine(SVM)for feature classification.An experiment is designed to collect motor imagery EEG da-ta with four experimenters and adds brain-computer interface(BCI)Competition IV public motor imagery experimental data to verify the method.The data demonstrates that compared with the meth-od of selecting too many or too few data channels,the time-frequency cross mutual information meth-od using motor imagery can improve the recognition accuracy and reduce the amount of calculation.
文摘在多模态脑机接口(Brain-computer interface,BCI)研究中,通道选择是直接影响系统性能的关键因素。针对脑电图(Electroencephalogram,EEG)和功能性近红外光谱(Functional near-infrared spectroscopy,fNIRS)各自通道之间存在冗余信息和噪声干扰,本文提出了一种基于PF(Pearson-Fisher,PF)系数的通道选择方法。首先将表征信号间相关性的Pearson系数与表征特征间可分性的Fisher值相结合,构建代表任务区分性的PF系数,并设置合理阈值对通道进行选择。然后提取EEG中的共空间模式(Common space pattern,CSP)特征和fNIRS中的统计特征。最后通过收缩线性判别分析(Shrinking linear discriminant analysis,SLDA)分类器进行分类。在对心理算数(Mental arithmetic,MA)任务数据的分类实验中,本文所提出方法分类精度可以达到90.8%,表明了该方法的有效性和鲁棒性。
文摘共空间模式侧重提取信号的空间信息,是脑电信号中滤波和特征提取的常用算法之一。然而脑电信号的时间窗、频带和通道的选择都会影响其分类结果。为了提高CSP特征的表征能力,采用了基于相关系数的脑电通道选择方法,结合时频共空间模式提取特征,提出了通道选择共时频空间模式(CS-CTFSP)新框架。首先利用通道间相关性,在主通道的基础上筛选合适的通道集合;并利用时频共空间模式从每个时间窗口的多个子频带中提取CSP特征;接着引入一种子频带筛选方法去除无区分能力的频带单元后,结合LASSO提取稀疏特征;最后采用LDA分类器对脑电信号进行分类。在对BCI Competition III Dataset IVa和BCI Competition IV Dataset I二分类运动想象任务的分类实验中,平均分类精度达到91.10%和87.92%,并与其他运动想象方法进行了比较,验证了本文方法的有效性。
基金This article is part of an ongoing PhD research of the first author.The field work and the student workshops were supported by Erasmus+mobilitygrants。
文摘The article examines the existing infrastructure of open common spaces within two New Belgrade mass housing blocks(Blocks 23 and 70a)through a typo-morphological analysis.These spaces between the buildings,although the most neglected,underused,and deteriorated components of mass housing neighbourhoods,are at the same time crucial to the quality,vitality and integrated governance of these neighbourhoods.They represent the primary tangible commons in cities and neighbourhoods.The question of urban commons is increasingly present in scientific literature,urban and architectural discourse.Nevertheless,approaches exploring the spatiality of the urban commons are scarce,leading to insufficient understanding of the spatial aspect and potentials of the already existing commons.Therefore,this study includes(1)identification,typological decoding and classification of the common spaces,focusing on the case of New Belgrade blocks,followed by(2)analysis of the spatial patterns and integration of the identified spaces within the blocks.The study confirms the complexity and diverse typology of the common spaces.It finds that the in-between,common spaces contribute to higher integration of different segments of the blocks.The open common spaces have an essential role in humanisation of the blocks,and thus the quality of life in the blocks as integrated neighbourhoods.The findings indicate that the spatial setting of the open common spaces in New Belgrade blocks allows for(re)emergence of collective practices,leading to inclusive and integrated rehabilitation of the neighbourhoods.
