Hilbert-Huang变换在脑电信号提取中的应用

高频视觉刺激可以拓宽可用的视觉刺激频率,而且可以减轻使用者的视觉疲劳,使基于视觉诱发电位的脑机接口系统更加实用化。但高频视觉刺激下的稳态视觉诱发电位信号幅值过低不易进行特征提取。本文提出一种新的视觉诱发电位提取方法,结合Hilbert-Huang变换与快速傅立叶变换方法来提取脑电信号。实验结果表明,用这种信号处理方法可以准确提取出高频稳态视觉诱发电位信号特征量,而且可以将脑电信号中的眼电干扰去除,并应用于脑机接口系统中。     

基于瞬态视觉诱发电位的识别算法研究

基于瞬态视觉诱发电位的研究是脑机接口研究中的一种方法,其核心在于瞬态视觉诱发电位的识别算法研究。采用累加平均和小波分解滤波从强噪声背景下提取微弱的视觉诱发电位,采用主成分分析提取诱发电位的特征,用K近邻算法对得到的特征信号进行模式识别。采集三名受试者的脑电数据作为处理对象,识别准确率可以达到95%。实验结果表明:该方法可以比较准确地识别瞬态视觉诱发电位。     

基于稳态视觉诱发脑电信号的频率特征提取方法研究

脑电信号分析与处理是脑-机接口技术的关键环节,视觉诱发电位是脑-机接口技术较为常用的一种方法。采用功率谱估计中的自相关法、Welch法和AR模型法对稳态视觉诱发脑电信号进行频率特征提取,根据Fisher线性分类对3种方法提取的特征量进行分类判别。结果表明,AR模型法提取频率特征量的准确率最高。     

基于虚拟仪器LabVIEW的脑—机接口系统

给出了基于瞬态视觉诱发电位的脑-机接口系统在LabVIEW环境下的实现方案。该方案的关键部分是视觉刺激器的设计和脑电信号的提取两部分。不同的刺激模块代表了多种可能的选择,受试者注视屏幕上其中一个目标,分析诱发电位可判别试者所注视的目标。采用累加平均和滤波的方法提高信噪比,用于提取微弱的脑电信号。该方案能有效地诱发出可识别的具有特征性的视觉诱发电位,并且通过离线的信号处理能够提取出所诱发的视觉诱发电位。     

一种基于人体脑电信号的机械手臂控制系统研究

文章提出了一种基于脑电信号的机械手臂控制系统的设计思路。该系统主要由电极、脑电采集电路、在线检测算法、外设等部分组成。系统采用闪烁刺激使操作者产生基于稳态视觉的诱发电位信号,通过采集电路将信号送入计算机中,由软件对其进一步处理和分析,转换成相应的控制命令控制机械手臂操作。检测算法中解决了脑电信号基线漂移和能量波动问题的困扰。实验显示,系统具有很高的检测实日寸性和准确率。     

基于DSP和ARM的便携式脑电信号处理系统的实现

为使脑一机接口技术(brain-computer interface,BCI)面向实用化、产品化,建立便携式的处理平台成为重要研究问题;系统采用现场可编程门阵列(FPGA)控制VGA显示器,设计了多功能视觉诱发刺激器,实时在线产生多种组合模式的刺激信号,诱发稳态视觉诱发电位;信号采集后放入到数字信号处理器(DSP)中,经过FIR滤波和FFT算法的处理后,得到辨识度较高的视觉诱发电位信号,并由无线将数据发送给STM32处理器,在LCD触屏上实时显示;实验结果表明系统实时采集、处理、显示脑电信号,相对于目前的BCI系统实现了多平台的便携式。     

一种基于双特征的联合脑-机接口系统设计

与传统基于单一脑电信号的脑-机接口相比,基于多种特征信号的联合脑-机接口能有效提高脑-机接口性能.在基于稳态视觉诱发电位和P300诱发电位的联合使用的可行性基础上,提出了新的刺激编码方式,构建了一种基于两种特征的联合脑-机接口系统.通过设计3×3字符刺激矩阵,矩阵中纵列按各自设定频率闪烁诱发稳态视觉诱发电位,横行随机出现蓝色框诱发P300.实验表明,当受试者注视并关注目标字符,两种特征脑电信号能够被同时诱发,且对脑电信号中两种特征进行识别能够检测出受试者选取的字符.与传统基于P300的字符脑-机接口相比,刺激诱发时间减少了一半,从根本上提高了脑-机接口的速度.在以后工作中,系统可以扩展到更大矩阵(如6×6),构建更为实用的联合脑-机接口系统.     

基于稳态视觉诱发电位的脑机接口系统的设计与研究

目的设计与研究将稳态视觉诱发电位作为输入信号的脑机接口系统.系统以显示器图形闪烁模块作为稳态视觉诱发电位的刺激源,经过滤波、放大等信号预处理后,对采集到的脑电信号中的稳态视觉诱发电位成分采用一种基于滑动窗的迭代式逐点频谱监测方法进行诱发电位的特征提取和识别,并将其转换为相应的控制命令以实现对伺服机械手臂6种运动方向的实...     

单次单道电刺激脑电模式识别方法研究

研究了一种人体在感受电流刺激条件下的脑电模式识别算法。该方法对于单次电流刺激,根据对单通道脑电信号的分析处理,即可对受试者是否感觉到该刺激做出判断。与传统诱发电位提取所用的平均叠加滤波法相比,避免了人体对重复刺激的疲劳效应。实验结果表明,该方法可用于人体电流感觉阈值的测量,由于不需要受试者做出任何主观反应,与以往技术相比,在保持无创检测的同时,测量过程更为客观,具有良好的临床应用前景。     

Windows环境下脑机接口视觉刺激器的设计

给出了基于视觉诱发电位的脑-机接口模式的方案,该方案的关键部分是视觉刺激器的实现,它提供了用户利用脑电信号识别字符所需的多种刺激模式。在Windows环境下,以闪烁的不同小块代表多种可能的选择,受试者注视其中一个目标,分析诱发电位可判别受试者所注视的目标。实测显示,视窗中的目标图像同时运动时,平滑稳定、无抖动现象,时间精度达到设计要求的1ms,实时向并口输出数据,该方案能有效地诱发出可识别的具有特征性的视觉诱发电位。     

Distinguishing and quantifying the visual aesthetics of a product: An integrated approach of eye-tracking and EEG

Although some methods of measuring visual aesthetics have been established, such as subjective reporting, feature calculating, and physiological assessing, designers still lack an integrated and quantified method in measuring the visual aesthetics of their products. This study aims to integrate eye-tracking metrics and EEG measurements to distinguish and quantify the visual aesthetics of a product. Thirty-two 3D prototypes of LED desk lamp with multiple views were designed to simulate an aesthetic appreciation flow. Eye-tracking and EEG signals were simultaneously recorded when participants were freely browsing each lamp. The evaluation of subjective visual aesthetics was conducted after each browsing. The results demonstrated that fixation time ratio and dwell time ratio significantly differed among the three clusters of visual aesthetic lamps. Meanwhile, average fixation duration only significantly differed between low and high aesthetic lamps and pupil size had no significant variation. Moreover, low aesthetic lamps evoked significantly weakened relative alpha power and enhanced relative gamma power. Thus, the eye-tracking metrics and the EEG measurements can distinguish the visual aesthetics of lamps. Regarding the results of quantification, the integrated multimodal physiological signals achieved an improved and reasonable accuracy. It seems beneficial to integrate multimodal physiological signals involved in different flows of visual aesthetic appreciation in quantifying the visual aesthetics of a product.Relevance to industryAs a premise of attracting consumers’ attention, visual aesthetics has been identified as a crucial role in product design and marketing. Thus, thorough research on the variations of multimodal physiological signals involved in information retrieval and processing in appreciation flow can provide a distinction between product visual aesthetics. The quantification method can be utilized by designers in measuring the visual aesthetics of their products.     

基于受限玻尔兹曼机的疲劳脑电特性分析

为了准确提取和分类视觉疲劳所引起的脑电特征，以此提醒过度用眼的工作人员及时休息，提出了多通道受限玻尔兹曼机算法和卷积神经网络(CNN)算法结合的深度学习混合模型，利用该模型对枕叶区10个通道的脑电信号进行自动提取内在特征和分类。在基于SSVEP的视觉疲劳脑电数据集上进行评估，深度学习混合模型的平均准确率达到88.63%,比传统的特征提取和分类方法高10%。实验结果证明了深度学习混合模型取得的分类效果较好，并且克服了传统手动提取特征方法不全面的不足，对疲劳脑电的研究具有现实的意义。     

基于稳态视觉诱发电位的在线脑机接口研究

针对脑机接口中存在的抗噪声能力差、操作复杂的问题,利用便携式脑电采集设备Emotiv EPOC以及NAO机器人,搭建了一个抗噪能力较好的稳态视觉诱发在线脑机接口系统。该系统采用典型相关性分析进行稳态视觉诱发电位的频率识别。在线实验中受试者通过Emotiv控制NAO机器人运动,四类任务的准确率达到87.50%。在线实验没有回避周围的噪声,表明该系统具有较好的抗噪能力。     

脑电情感信号正确提取仿真

脑电信号是一种微伏级信号,从头皮上采集的脑电信号包含眼电信号、心电信号以及各种环境噪音。针对情感识别如何有效处理脑电信号的问题,本文首先对实验采集的脑电信号应用小波分析和独立分量分析进行预处理去除干扰;其次为了有效地提取脑电特征,应用幅值直方图、标准差在时域上定性地找出2种情感的脑电差异;最后应用功率谱对2种情感脑电的γ波节律进行谱分析。仿真实验结果表明,将脑电信号的γ波节律用于情感识别是可行的。     

无线便携式动物脑电遥测记录系统

开发出一套无线便携式动物脑电遥测系统。采集的数据经过放大、滤波后调制发射,接收器接收到无线信号后进行解调并通过串口打印显示出电压信号。实验中将测量电极植入大鼠颅骨内,并将信号采集发射器背负在大鼠身上,分别记录大鼠睡眠、清醒和癫痫脑电波形。实验结果表明该系统,复杂环境下发射器的发射距离达到20 m,可以稳定工作8 h,且具有体积小、功耗低、精度高等特点,适用于大鼠脑电遥测实验。     

Least squares support vector machine employing model-based methods coefficients for analysis of EEG signals

The aim of the study is classification of the electroencephalogram (EEG) signals by combination of the model-based methods and the least squares support vector machines (LS-SVMs). The LS-SVMs were implemented for classification of two types of EEG signals (set A – EEG signals recorded from healthy volunteers with eyes open and set E – EEG signals recorded from epilepsy patients during epileptic seizures). In order to extract the features representing the EEG signals, the spectral analysis of the EEG signals was performed by using the three model-based methods (Burg autoregressive – AR, moving average – MA, least squares modified Yule–Walker autoregressive moving average – ARMA methods). The present research demonstrated that the Burg AR coefficients are the features which well represent the EEG signals and the LS-SVM trained on these features achieved high classification accuracies.     

Bio-signal-based geometric modeling application for physically disabled users

This paper discusses the challenges in achieving bio-signal-based design environments. While the main motivation of this paper was to provide a user interface for physically disabled people to express their artistic natures, a special emphasis is given on graphical user interface design where bio-signals are the single input source. Among three bio-signal sources investigated—electromyography, electrooculography and electroencephalography (EEG)—stimulus-based human–computer interaction design (EEG feature extraction method) is found to be the most promising for achieving design environments to perform complex tasks. In the proposed stimulus-based brain–computer-interaction application, the user communication with a computer is achieved by coupling intended functionalities with stimuli signals on the computer screen. Constant focus on the intended command stimulates the brain. In return, the brain releases a response signals (steady state visual evoked potential). In theory, brain’s response signals and the stimulus signals are identical. Once successfully identified, the presence of a signal pattern that is identical to the one of the alternative stimulus signals (paired with a command in a user interface) indicates the intention of a user. Since each option is associated with a unique signal pattern, multiple options can simultaneously be offered to users. The main challenge of working with stimulus signals is that the response signals are weak and they are buried inside of highly polluted EEG signals that include brain’s natural activities. In this paper, we introduce a signal processing algorithm based on Lorenz systems of differential equations for identifying the source of stimulus signals. Our experiments strongly suggest that bio-signal-based design environments to perform complex tasks, including geometric modeling can be achieved by utilizing stimulus-based signal processing methodology.     

Bispectral analysis-based approach for steady-state visual evoked potentials detection

Multimedia Tools and Applications - Brain-Computer Interface (BCI) systems are widely based on steady-state visual evoked potentials (SSVEP) detection using electroencephalography (EEG) signals....     

舒尔特方格与LSTM的注意力分级建模

在基于脑电信号的注意力分级研究中,存在两个亟待解决的技术难点。第一不同注意类型的脑电数据采集及标注困难;第二脑电特征提取算法忽视原始脑电信号时序特征。针对以上问题,设计了基于视觉搜索和反应时技术的舒尔特方格范式,实现对不同注意类型脑电数据的采集以及自动标注;设计长短期记忆深度学习网络（LSTM）实现对注意力分级,保存原始脑电信号的时序特征。实验结果表明,注意力分级模型可以很好区分高中低三种注意力水平;对比现有的五种基于EEG信号的注意力分级算法,小波变换（DWT）、近似熵、共空间模式（CSP）、基于相干系数的脑网络和卷积神经网络（CNN）,在相同的EEG数据集上,该注意力分级模型识别准确率最高,高出DWT算法21.49个百分点;高出近似熵算法25.82个百分点;高出CSP算法20.53个百分点;高出基于相干系数的脑网络算法13.32个百分点;高出CNN9.05个百分点。     

A deep wavelet sparse autoencoder method for online and automatic electrooculographical artifact removal

Electrooculographical (EOG) artifacts are problematic to electroencephalographical (EEG) signal analysis and degrade performance of brain–computer interfaces. A novel, robust deep wavelet sparse autoencoder (DWSAE) method is presented and validated for fully automated EOG artifact removal. DWSAE takes advantage of wavelet transform and sparse autoencoder to become a universal EOG artifact corrector. After being trained without supervision, the sparse autoencoder performs EOG correction on time–frequency coefficients collected after brain wave signal wavelet decomposition. Corrected coefficients are then used for wavelet reconstruction of uncontaminated EEG signals. DWSAE is compared with five other methods: second-order blind identification, information maximization, joint approximation diagonalization of eigen-matrices, wavelet neural network (WNN) and wavelet thresholding (WT). Experimental results on a visual attention task dataset, a mental state recognition dataset and a semi-simulated contaminated EEG dataset show that DWSAE is capable of suppressing EOG artifacts effectively, while preserving the nature of background EEG signals. The mean square error of signals before and after correction by DWSAE on a semi-simulated contaminated EEG segment of 30 s is the lowest (65.62) when compared to the results produced by WNN and WT. DWSAE addresses limitations posed by these methods in three ways. First, DWSAE can be performed automatically and online in a single channel of EEG data; this has advantages over independent component analysis-based methods. Second, its results are robust and stable in comparison with those of other wavelet-based methods. Third, as an unsupervised learning scheme, DWSAE does not require the off-line training that is necessary for WNN and other supervised learning machine learning-based methods.