脑-机接口及其应用研究

主要研究脑-机接口的定义、基本构成、应用领域及其发展前景,以及提出并实现了1套完整可行的脑-机接口系统应用方案——基于稳态视觉诱发电位的脑-机接口控制系统设计与实现.系统搭建在LabVIEW平台上,利用LabVIEW的小波包信号分解和重构模块,实现对稳态视觉诱发电位的有效提取.系统的功能是利用脑电信号进行任务选择和对图...     

基于SSVEP的脑-机接口自动车系统研究

阐述了视觉诱发电位用于脑-机接口的原理,系统采用单片机设计视觉刺激器,同时在LABVIEW平台上,利用希尔伯特黄变换实时提取诱发电位向量,产生脑机接口控制信号,并用于自动车控制系统,从而控制小车的前后左右运动.通过大量实验验证,设计的基于稳态视觉诱发电位的脑-机接口自动车控制系统,发送控制命令正确率高于83％,发送一个...     

异步BCI的大脑工作和空闲状态的辨识方法研究

基于事件相关电位的脑-机接口系统难以检测大脑的空闲状态,限制了被试在任意时间输出指令的自由。利用欧德堡范式同时诱发N200电位、P300电位和瞬态视觉诱发电位。根据瞬态视觉诱发电位的频域特征区分大脑的工作状态和空闲状态;在工作状态下利用N200和P300电位的时域特征识别被试的控制意图,从而构建异步的脑-机接口系统。通过对7名健康被试进行发送指令与观看视频反馈两种状态的实验,实现大脑的工作状态和空闲状态之间的切换。该方法识别大脑状态或者意图的准确率为98.21%,与基于事件相关电位识别空闲状态的方法相比提高了50.89%。     

基于稳态视觉诱发电位的相频特性分类算法研究

目前基于稳态视觉诱发电位（SSVEP）的脑-机接口在人机协作中受到广泛关注,现有面向SSVEP信号的相位与频率信息的深度学习分类方法,仍存在由于信息利用不充分导致的SSVEP信号分类效果较差等问题。而目前已出现多种分类算法用于解决上述问题。本文基于迁移学习思想提出一种用于SSVEP信号分类的深度神经网络模型,将快速傅里叶变换后的复向量作为输入,对各个导联的实、虚部向量进行卷积,学习对应的相频特性。该模型分为两部分：第一部分利用所有被试者之间的统计共性获得相位和频率信息的全局相频特征模块;第二部分利用训练好的全局相频特征模块对局部相频特征模块进行初始化,通过局部相频特征模块的进一步强化学习对训练参数进行微调,以减少每个被试者之间的个体差异。在公开数据集BETA上进行测试,在时窗长度为1.5 s时,平均准确率和平均信息传输率分别为89.98%和71.80 bit/min。实验结果表明,与其他方法相比,本文的分类算法模型取得了较为不错的分类效果,所设计的全局、局部相频特征模块能够改善个体差异因素对分类结果的影响,为深入挖掘、利用SSVEP信号中的相位和频率信息提供了全新思路。     

Grael脑电放大器与深度学习的手势实时识别研究

手势识别是人机交互的关键。为了能够更好地实现脑电信号与肌电信号的融合,精准地识别人体的运动,本文建立了一套基于Grael脑电放大器的手势动作实时检测识别的研究系统。通过Grael脑电放大器和Curry8系统采集5个通道的8种不同手势的表面肌电信号(sEMG),并对采集到的sEMG信号进行滤波去噪、滑动窗口分割以及特征提取等预处理的操作;最后采用几种常用的分类器与卷积神经网络(CNN)对不同手势的sEMG信号进行实时分类识别。结果表明CNN的识别准确率最高,能达到92.98%;对每个手势动作进行30次实时识别检测,结果显示识别延迟大概在1～1.5 s,实时识别的精度可高达90%。该系统为将来研究脑电信号与肌电信号的融合提供了一个可行的方法,在人机交互方面展现了巨大的潜力和应用空间。     

基于Hilbert Huang变换的SSVEP相位提取

稳态视觉诱发电位(steady-state visual evoked potential,SSVEP)被广泛应用于脑-机接口和大脑的认知研究,相位信息是其重要的特征指标之一.针对快速傅里叶变换在SSVEP相位提取中受不确定性原理约束的特点,提出了一种基于Hilbert-Huang变换的SSVEP相位提取方法.该方法通过经验模态分解将脑电信号分解为一系列固有模态函数(intrinsic mode functions,IMF),并通过分析各模态函数瞬时频率的均值判断该IMF分量是否属于噪声.若为噪声则将其从原始信号中滤除,再对滤波后的各IMF分量进行Hilbert变换,并与基准信号做运算即可求得SSVEP相位.实验结果表明,与快速傅里叶法相比该方法可在去除噪声分量的同时提取SSVEP的相位信息,且具有较高的准确率、精度和自适应性.     

用于脑机接口的感觉刺激事件相关电位研究进展

脑机接口研究的目的就是在人脑和计算机或其他电子设备之间建立一种直接联系,使人们可以通过思维来直接控制计算机或外部设备。感觉刺激诱发的事件相关电位是基于脑电的脑机接口系统研究中备受关注的一种信号模式,按其刺激模式的不同又可分为视觉、听觉、体感等单一感觉通道刺激诱发的和跨感觉通道刺激诱发的事件相关电位。事件相关电位研究的发展表明：相对于单一感觉通道,跨感觉通道刺激诱发的事件相关电位具有波幅高、潜伏期短且含有高维度空间分布信息的特点,可弥补单一感觉诱发事件相关电位信息过少、不利识别的缺陷,从而提高信息转化速度和分类准确率,在脑机接口中具有更高的实用价值。     

α波和运动想象的混合范式脑-机接口系统

提出将α波和运动想象2种范式以串行的方式相结合控制的脑-机接口系统,该系统利用α波的阻断现象控制状态选择,选择成功后发出提示音,被试听到提示音后,通过左右手运动想象来完成多个任务。通过这样的混合范式有效的实现了较少种类的脑电信号对外部设备的多任务控制。实验结果表明,5名被试都能顺利完成外部设备的多任务控制,平均正确率为77%,最高正确率可达90%。本系统实现了混合范式下的脑电信号对外部设备的多任务控制,为进一步开发复杂的混合范式的脑-机接口系统奠定基础。     

脑电BCI系统的软硬件开发平台发展现状

脑-机接口系统(brain-computer interface,BCI)是一种将大脑活动信息直接转换为人工输出的系统,允许用户通过思维 活动直接控制外部设备。 脑电图技术(electroencephalogram,EEG)可以实时获取大脑活动产生的神经生理电信息,具有无创、低 廉、高时间分辨率等优点,是 BCI 获取大脑活动信息的主流方式之一。 脑电 BCI 系统具有脑电信号采集、处理和输出结果的功 能,能够诱发特征脑电,并控制外部设备,在康复、医疗诊断和神经科学研究等领域具有巨大的应用价值。 随着脑电 BCI 系统应 用需求不断增加,确保其快速高效地部署和应用的技术越来越重要。 结合近些年脑电 BCI 系统研究和应用,综合论述目前用于 开发脑电采集和编解码的硬件和软件平台的技术,分析归纳其当前现状与未来趋势,以促进开发脑电 BCI 系统软硬件平台的有 效发展。     

电力系统数字混合仿真技术综述及展望

论述了混合仿真技术的发展历史和现状,对国内外现有的混合仿真平台进行了全面的技术总结和比较。在此基础上,从等值模型、相量提取算法、接口位置选择和交互时序4个方面对混合仿真接口技术进行了详细讨论,论述了各方面技术的内涵、方案和面临的主要问题。结合智能电网的发展和"源-网-荷"互动模式,提出将电磁侧系统通过交互接口与信息系统仿真平台相连,构成信息-电磁-机电混合仿真系统,为混合仿真技术的进一步发展提供了可能的方向。     

Enhancement of steady‐state visual evoked potential‐based brain–computer interface systems via a steady‐state motion visual stimulus modality

Steady‐state visual evoked potential (SSVEP)‐based brain–computer interface (BCI) systems are among the most accurate assistive devices for patients with severe disabilities. However, existing visual stimulation patterns lead to eye fatigue, which affects the system performance. Therefore, in this study, we propose two improvements to SSVEP‐based BCI systems. First, we propose a novel visual stimulator that incorporates a visual motion stimulus for the steady‐state visual stimulus to reduce eye fatigue while maintaining the advantages associated with SSVEPs. We also propose two corresponding feature extraction algorithms, i.e. SSVEP detection and visual attention detection, to capture the phenomena of steady‐state motion visual stimulus responses. The accuracy of the test was ∼83.6%. Second, we propose a novel hybrid BCI‐SSVEP system and a motion visual stimulus hybrid BCI system to enhance the SSVEP‐based BCI system during a state of eye fatigue. Participants used the SSVEP system until reaching a fatigued state and then began using a hybrid motion visual stimulus. The accuracy of the proposed system was ∼85.6%. The proposed improvements can be incorporated into practical BCI systems for wheelchair control. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Multi‐command SSAEP‐based BCI system with training sessions for SSVEP during an eye fatigue state

This paper proposes a steady‐state auditory stimulus modality and a detection algorithm to replace steady‐state visual evoked potential (SSVEP )‐based brain–computer interface (BCI ) systems during visual fatigue periods. The optimal speaker position for the steady‐state auditory evoked potential (SSAEP )‐based BCI system and possible electrode positions are investigated. Using the proposed system, an accuracy of 85% for two commands was achieved based on the T3–T5 and T4–T6 electrode positions using only one speaker. SSAEP is a promising BCI modality for mitigating the problem of eye fatigue that often occurs during the use of SSVEP ‐based BCI systems. However, SSAEP ‐based BCI systems suffer from low accuracy. To increase accuracy, we propose a new enhanced SSAEP training method. The training process was enhanced by instructing users to control their attention levels while simultaneously detecting an auditory stimulus frequency. Furthermore, we propose a corresponding single‐frequency, multi‐command BCI paradigm for the proposed training method. With the proposed paradigm, four commands can be detected using only one auditory stimulus frequency. The proposed training system yielded an accuracy of ∼81% compared to 66% for sessions performed without the proposed training method. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

基于Resinv-Unet的图像特征点检测方法

针对传统特征点检测算法需人为制定检测机制和基于深度学习的特征点检测网络泛化能力不强的问题,引入灰度不变量和残差结构,设计并实现具备像素级特征点检测能力的残差不变量神经网络(residual-invariant neural network, Resinv-Unet)。采用自标注的方式,在真实场景图像数据集的基础上构建用于训练神经网络的数据集。实验结果表明,Resinv-Unet相较于现有的特征点检测算法和特征点检测网络,在真实场景图像上具有更强的泛化能力和鲁棒性,在平均精确度、精确度和召回率上均取得更好的性能指标,其中,平均精确度达到0.715 5、精确度达到0.776 2、召回率达到0.713 7。     

听觉刺激对稳态视觉诱发电位影响研究

基于稳态视觉诱发电位(steady state visual evoked potential,SSVEP)和听觉脑机接口技术目前已成为研究重点.未来的挑战是研究基于视觉和听觉联合统一系统框架的脑机接口技术.多感觉在不同脑区间存在的跨膜整合以及视听双刺激的交互作用,给该技术研究带来较大困难,故研究听觉刺激对枕区SSVEP影响很有意义.在闪光刺激频率为12 Hz,占空比分别为5％、20％、30％、40％、50％、60％、70％、80％、95％条件下,分别加入500、1 000、1 500 Hz的正弦纯音、响度为50 dB的听觉刺激,研究听觉对SSVEP的变化规律.结果表明,对同一受试者,视听双刺激条件下SSVEP随占空比变化依然呈现“窗口”效应,听觉刺激对SSVEP影响起增强或抑制作用.此外听觉刺激对SSVEP影响出现的占空比“窗口”的位置、数量以及对SSVEP增强或抑制作用的程度也因人而已.结果为更好研究视听相互作用机理及其在脑机接口技术应用提供有意义的实验依据.     

Dry and noncontact EEG sensors for mobile brain-computer interfaces

Dry and noncontact electroencephalographic (EEG) electrodes, which do not require gel or even direct scalp coupling, have been considered as an enabler of practical, real-world, brain-computer interface (BCI) platforms. This study compares wet electrodes to dry and through hair, noncontact electrodes within a steady state visual evoked potential (SSVEP) BCI paradigm. The construction of a dry contact electrode, featuring fingered contact posts and active buffering circuitry is presented. Additionally, the development of a new, noncontact, capacitive electrode that utilizes a custom integrated, high-impedance analog front-end is introduced. Offline tests on 10 subjects characterize the signal quality from the different electrodes and demonstrate that acquisition of small amplitude, SSVEP signals is possible, even through hair using the new integrated noncontact sensor. Online BCI experiments demonstrate that the information transfer rate (ITR) with the dry electrodes is comparable to that of wet electrodes, completely without the need for gel or other conductive media. In addition, data from the noncontact electrode, operating on the top of hair, show a maximum ITR in excess of 19 bits/min at 100% accuracy (versus 29.2 bits/min for wet electrodes and 34.4 bits/min for dry electrodes), a level that has never been demonstrated before. The results of these experiments show that both dry and noncontact electrodes, with further development, may become a viable tool for both future mobile BCI and general EEG applications.     

Independence of amplitude-frequency and phase calibrations in an SSVEP-based BCI using stepping delay flickering sequences

This study proposes a steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) independent of amplitude-frequency and phase calibrations. Six stepping delay flickering sequences (SDFSs) at 32-Hz flickering frequency were used to implement a six-command BCI system. EEG signals recorded from Oz position were first filtered within 29-35 Hz, segmented based on trigger events of SDFSs to obtain SDFS epochs, and then stored separately in epoch registers. An epoch-average process suppressed the inter-SDFS interference. For each detection point, the latest six SDFS epochs in each epoch register were averaged and the normalized power of averaged responses was calculated. The visual target that induced the maximum normalized power was identified as the visual target. Eight subjects were recruited in this study. All subjects were requested to produce the "563241" command sequence four times. The averaged accuracy, command transfer interval, and information transfer rate (mean ± std.) values for all eight subjects were 97.38 ± 5.97%, 3.56 ± 0.68 s, and 42.46 ± 11.17 bits/min, respectively. The proposed system requires no calibration in either the amplitude-frequency characteristic or the reference phase of SSVEP which may provide an efficient and reliable channel for the neuromuscular disabled to communicate with external environments.     

Brain-Computer Interfaces Based on Visual Evoked Potentials

Recently, electroencephalogram (EEG)-based brain? computer interfaces (BCIs) have become a hot spot in the study of neural engineering, rehabilitation, and brain science. In this article, we review BCI systems based on visual evoked potentials (VEPs). Although the performance of this type of BCI has already been evaluated by many research groups through a variety of laboratory demonstrations, researchers are still facing many difficulties in changing the demonstrations to practically applicable systems. On the basis of the literature, we describe the challenges in developing practical BCI systems. Also, our recent work in the designs and implementations of the BCI systems based on steady-state VEPs (SSVEPs) is described in detail. The results show that by adequately considering the problems encountered in system design, signal processing, and parameter optimization, SSVEPs can provide the most useful information about brain activities using the least number of electrodes. At the same time, system cost could be greatly decreased and usability could be readily improved, thus benefiting the implementation of a practical BCI.     

Visual spatial attention tracking using high-density SSVEP data for independent brain-computer communication.

The steady-state visual evoked potential (SSVEP) has been employed successfully in brain-computer interface (BCI) research, but its use in a design entirely independent of eye movement has until recently not been reported. This paper presents strong evidence suggesting that the SSVEP can be used as an electrophysiological correlate of visual spatial attention that may be harnessed on its own or in conjunction with other correlates to achieve control in an independent BCI. In this study, 64-channel electroencephalography data were recorded from subjects who covertly attended to one of two bilateral flicker stimuli with superimposed letter sequences. Offline classification of left/right spatial attention was attempted by extracting SSVEPs at optimal channels selected for each subject on the basis of the scalp distribution of SSVEP magnitudes. This yielded an average accuracy of approximately 71% across ten subjects (highest 86%) comparable across two separate cases in which flicker frequencies were set within and outside the alpha range respectively. Further, combining SSVEP features with attention-dependent parieto-occipital alpha band modulations resulted in an average accuracy of 79% (highest 87%).