Toward the Optimization of the Region-Based P300 Speller

Technology has tremendously contributed to improving communication and facilitating daily activities.Brain-Computer Interface(BCI)study particularly emerged from the need to serve people with disabilities such as Amyotrophic Lateral Sclerosis(ALS).However,with the advancements in cost-effective electronics and computer interface equipment,the BCI study is flourishing,and the exploration of BCI applications for people without disabilities,to enhance normal functioning,is increasing.Particularly,the P300-based spellers are among the most promising applications of the BCI technology.In this context,the region-based paradigm for P300 BCI spellers was introduced in an effort to reduce the crowding effect and adjacency problem that might affect the detection of P300 peak.This study extends this line of research by investigating the effect,in terms of accuracy and usability,of the letters’distribution among the speller’s regions.For this purpose,a clustering algorithm is proposed,and two region-based layouts were generated by redistributing the letters based on their dissimilarity or their similarity.A pilot usability evaluation was also conducted in order to assess the usability of the different layouts in terms of effectiveness,efficiency,and satisfaction.The results indicate that the distribution of the letters has an effect on the classification accuracy as well as the user experience.Particularly,when considering short-term accuracy and cognitive effort,the original region-based layout outperforms other layouts.

Exploiting Sparse Representation in the P300 Speller Paradigm

A Brain-Computer Interface(BCI) aims to produce a new way for people to communicate with computers.Brain signal classification is a challenging issue owing to the high-dimensional data and low Signal-to-Noise Ratio(SNR). In this paper, a novel method is proposed to cope with this problem through sparse representation for the P300 speller paradigm. This work is distinguished using two key contributions. First, we investigate sparse coding and its feasibility for brain signal classification. Training signals are used to learn the dictionaries and test signals are classified according to their sparse representation and reconstruction errors. Second, sample selection and a channel-aware dictionary are proposed to reduce the effect of noise, which can improve performance and enhance the computing efficiency simultaneously. A novel classification method from the sample set perspective is proposed to exploit channel correlations. Specifically, the brain signal of each channel is classified jointly using its spatially neighboring channels and a novel weighted regulation strategy is proposed to overcome outliers in the group. Experimental results have demonstrated that our methods are highly effective. We achieve a state-of-the-art recognition rate of 72.5%, 88.5%, and 98.5% at 5, 10, and 15 epochs, respectively, on BCI Competition Ⅲ Dataset Ⅱ.

视觉P300脑机接口中的SOA扰动现象

异步操控性是脑机接口走向实际应用的关键技术之一。其关键点在于寻找一种可有效区分脑机接口工作状态和空闲状态的指标。建立了针对P300脑机接口的刺激起始异步(SOA)扰动模型,在仿真实验和实测数据中观察到SOA扰动谱线,并根据所提出的模型给出了合理解释。研究了SOA扰动的频域特性,结果表明,当SOA位于220ms附近时,SOA扰动的强度最大,而当SOA低于150ms时,SOA扰动强度将急剧减小。同时SOA扰动所具有的锁相性使得可以通过时域相干平均法进一步提高信噪比。SOA扰动可作为脑机接口处于工作状态的标志,为异步脑机接口的实现提供了一种新的研究思路。

基于人脸范式的P300拼写系统的参数优化

基于P300电位的脑机接口系统,因其识别准确率高、信息传输率快,经常被用于单词拼写等信息交互系统。近年来的研究表明,人脸刺激可以诱发出非常优良的事件相关电位,从而提高P300脑机接口拼写系统的性能。然而,人脸刺激在脑机接口中的呈现方式也会直接影响人脸诱发信号的可识别性。从人脸刺激在脑机接口系统中的几种基本呈现形式展开研究,对刺激间隔(130和200 ms)、界面尺寸(15.6和24英寸)和图片像素(50×69和80×110)3个参数分别展开研究,并邀请10名健康被试参与实验。实验结果表明:离线训练阶段增大这3个参数均可显著提高单个闪烁序列的分类准确率,但在线测试阶段唯有刺激时间间隔的增加可显著提高系统的分类准确率(200 ms:90%±7%,130 ms:75%±13%)。另外,这3个参数的调整对系统诱发的N200、P300、N400等信号强度的影响也不相同。在P300拼写系统的实际应用中,应综合考虑多个物理参数的优化,以提高系统性能。

基于Hololens2的可穿戴式P300脑机接口系统设计与评估

肌萎缩性侧索硬化症(ALS)患者往往难以通过语言和行为来表达意图,无法正常地与外部世界沟通,严重影响生活质量。脑机接口(BCI)的方式能够辅助ALS患者与外部世界进行交流而受到广泛的关注,但是可移动性差的设备在使用中给患者带来不便。为了改善BCI系统的便携性,本文提出了一种基于Hololens2的可穿戴式P300字符拼写系统(MR-BCI)。本系统使用Hololens2混合现实设备呈现范式,OpenBCI设备采集脑电信号,Jetson Nano嵌入式计算机处理数据。同时,为了优化系统的性能,本文提出一种轻量化的卷积神经网络方法应用于嵌入式计算机进行实时分类。结果表明,与基于计算机显示器的拼写系统(CS-BCI)相比,MR-BCI诱发的P300振幅增加,离线和在线模式的准确率分别提高1.7%和1.4%,在线模式的信息传输速率提高了0.7 bit/min。本文提出的MR-BCI在保证系统性能的基础上,实现了可穿戴式BCI系统,对BCI的临床应用具有积极的作用。

改进的蜜蜂进化型遗传算法

提出一种改进的蜜蜂进化型遗传算法。在该算法中,种群的最优个体作为蜂王与被选的每个个体(雄蜂)以一定概率进行交叉操作,从而增强了对种群最优个体所包含信息的开采能力;同时,为了避免过早收敛,算法在种群次优解周围进行局部搜索,引入新的随机个体,增加算法的多样性。实验结果表明,该算法能有效地提高遗传算法性能的求解精度和收敛速度。

A submatrix-based P300 brain-computer interface stimulus presentation paradigm

The P300 event-related potential (ERP), with advantages of high stability and no need for initial training, is one of the most commonly used responses in brain-computer interface (BCI) applications. The row/column paradigm (RCP) that flashes an entire column or row of a visual matrix has been used successfully to help patients to spell words. However, RCP remains subject to errors that slow down communication, such as adjacency-distraction and double-flash errors. In this paper, a new visual stimulus presentation paradigm called the submatrix-based paradigm (SBP) is proposed. SBP divides a 6×6 matrix into several submatrices. Each submatrix flashes in single cell paradigm (SCP) mode and separately performs an ensemble averaging method according to the sequences. The parameter of sequence number is used to improve further the accuracy and information transfer rate (ITR). SBP has advantages of flexibility in division of the matrix and better expansion capability, which were confirmed with different divisions of the 6×6 matrix and expansion to a 6×9 matrix. Stimulation results show that SBP is superior to RCP in performance and user acceptability.

基于匹配滤波器和度量学习的脑电信号分类

脑电信号识别和脑机接口技术是人机交互领域的热点问题。当前脑电信号分类方法模型复杂,难以实际应用。该文提出基于匹配滤波器的脑电信号分类框架:根据脑电信号特点和假设检验建立生成式模型,并基于Gauss噪声假设推导出一个简单的线性判定算子;利用度量学习方法估计主信号分量和最优协方差矩阵,进一步增强分类器的鉴别力。实验结果表明:所推导出的线性判定算子分类精度和计算复杂度都优于其他算法,能够满足实际应用需求。