Using electroencephalogram to continuously discriminate feelings of personal thermal comfort between uncomfortably hot and comfortable environments

Thermal comfort is an important factor for the design of buildings. Although it has been well recognized that many physiological parameters are linked to the state of thermal comfort or discomfort of humans, how to use physiological signal to judge the state of thermal comfort has not been well studied. In this paper, the feasibility of continuously determining feelings of personal thermal comfort was discussed by using electroencephalogram (EEG) signals in private space. In the study, 22 subjects were exposed to thermally comfortable and uncomfortably hot environments, and their EEG signals were recorded. Spectral power features of the EEG signals were extracted, and an ensemble learning method using linear discriminant analysis or support vector machine as a sub-classifier was used to build the discriminant model. The results show that an average discriminate accuracy of 87.9% can be obtained within a detection window of 60 seconds. This study indicates that it is feasible to distinguish whether a person feels comfortable or too hot in their private space by multi-channel EEG signals without interruption and suggests possibility for further applications in neuroergonomics.     

低觉醒脑电识别与唤醒的可穿戴系统研究

为智能化地识别警戒作业人员出现的低觉醒、注意力下降的生理状态，本文介绍了一种基于FPGA和脑电信号处理的低觉醒状态检测与唤醒系统，系统通过传感器从大脑头皮采集脑电信号，转换为数字信号，经傅里叶变换获取了脑电信号的θ相对能量、α相对能量、重心频率、谱熵等4个特征量，由4个特征量表征低觉醒状态并运用支持向量机对低警戒状态进行识别，当识别出低觉醒状态时采用声音报警模块发出声音，唤醒警戒作业人员。设计系统能够较好地识别出低觉醒状态，识别率达90.8%，可为提高警戒作业工作绩效提供一种可穿戴的智能装备。     

Detrended Fluctuation Analysis of the Human EEG during Listening to Emotional Music

A nonlinear method named detrended fluctuation analysis （DFA） was utilized to investigate the scaling behavior of the human electroencephalogram （EEG） in three emotional music conditions （fear, happiness, sadness） and a rest condition （eyes-closed）. The results showed that the EEG exhibited scaling behavior in two regions with two scaling exponents β1 and β2 which represented the complexity of higher and lower frequency activity besides α band respectively. As the emotional intensity decreased the value of β1 increased and the value of β2 decreased. The change of β1 was weakly correlated with the ＇approach-withdrawal＇ model of emotion and both of fear and sad music made certain differences compared with the eyes-closed rest condition. The study shows that music is a powerful elicitor of emotion and that using nonlinear method can potentially contribute to the investigation of emotion.     

基于能量特征的脑电信号特征提取与分类

为了快速、有效地提取脑电特征,提高分类正确率,采用带通滤波和小波包分析的方法提取Mu、Beta节律对应的脑电信号,在时域范围内,将信号幅度的平方作为能量特征值;在频域范围内,采用AR模型功率谱估计法所得的功率谱密度作为能量特征值.根据运动想象脑电信号特点,构造左右通道信号能量差值的符号特性作为分类判别依据,进行分类测试,方法简单.初步实验结果表明,所利用的两种方法的分类正确率达87.857%.     

基于EEG和DE-CNN-GRU的情绪识别

近年,情绪识别研究已经不再局限于面部和语音识别,基于脑电等生理信号的情绪识别日趋火热.但由于特征信息提取不完整或者分类模型不适应等问题,使得情绪识别分类效果不佳.基于此,本文提出一种微分熵(DE)、卷积神经网络(CNN)和门控循环单元(GRU)结合的混合模型(DE-CNN-GRU)进行基于脑电的情绪识别研究.将预处理后的脑电信号分成5个频带,分别提取它们的DE特征作为初步特征,输入到CNN-GRU模型中进行深度特征提取,并结合Softmax进行分类.在SEED数据集上进行验证,该混合模型得到的平均准确率比单独使用CNN或GRU算法的平均准确率分别高出5.57%与13.82%.     

基于多参数公共空间频率模式算法的脑电特征提取

针对目前脑机接口中提取明显的脑电信号特征较难以及特征维数较多的缺陷,提出了一种多参数的公共空间频率模式CSSP(Common Spatio-Spectral Pattern)算法对脑电信号进行特征提取。该算法对不同通道的脑电信号采取不同的延时因子,增强了CSSP算法在频域上的滤波效果。在对2003年国际脑机接口BCI(Brain Computer Interface)竞赛的运动想象脑电识别中,利用多参数CSSP特征提取方法结合支持向量机SVM(Support Vector Machine)分类方法,在只提取两维特征的情况下,较公共空间模式CSP(Common Spatial Pattern)与CSSP算法,分类的正确率有了明显提高。同时,多参数的引入使该方法在特征提取上较CSP与CSSP算法具有更强的适用性。     

Feature selection for classification of oscillating time series

We propose a forward sequential feature selection scheme based on k‐means clustering algorithm to derive the feature subset that classifies best the time series data base, according to the criterion of the corrected Rand index. Moreover, we investigate the effect of the standardization scheme on the feature selection and propose a standardization given by the transform to standard Gaussian distribution. Our interest in this work is in classification of oscillating dynamical systems on the basis of measures computed on time series from these systems. The features to be selected are measures of linear and non‐linear analysis of time series, such as auto‐correlation and Lyapunov exponents, as well as oscillation characteristics, such as the mean magnitude of peaks. Simulations on known oscillating deterministic and stochastic systems showed that, for repeated realizations of the same classification task, the proposed feature selection scheme selected very often the same best feature subset, giving high classification accuracy for any standardization. We found that, regardless of the standardization, the highest classification accuracy could be obtained with a small feature subset, containing most frequently an oscillating‐related feature. The same setting was applied to records of epileptic electroencephalogram signals, giving varying results and dependent on the standardization.     

Identification of Driving Intention Based on EEG Signals

The driver''s intention is recognized by electroencephalogram(EEG) signals under different driving conditions to provide theoretical and practical support for the applications of automated driving. An EEG signal acquisition system is established by designing a driving simulation experiment, in which data of the driver''s EEG signals before turning left, turning right, and going straight, are collected in a specified time window. The collected EEG signals are analyzed and processed by wavelet packet transform to extract characteristic parameters. A driving intention recognition model, based on neural network, is established, and particle swarm optimization (PSO) is adopted to optimize the model parameters. The extracted characteristic parameters are inputted into the recognition model to identify driving intention before turning left, turning right, and going straight. Matlab is used to simulate and verify the established model to obtain the results of the model.The maximum recognition rate of driving intention is 92.9%. Results show that the driver''s EEG signal can be used to analyze the law of EEG signals. Furthermore, the PSO-based neural network model can be adapted to recognize driving intention.     

Unsupervised adaptation of electroencephalogram signal processing based on fuzzy C‐means algorithm

This paper studies an unsupervised approach for online adaptation of electroencephalogram (EEG) based brain–computer interface (BCI). The approach is based on the fuzzy C‐means (FCM) algorithm. It can be used to improve the adaptability of BCIs to the change in brain states by online updating the linear discriminant analysis classifier. In order to evaluate the performance of the proposed approach, we applied it to a set of simulation data and compared with other unsupervised adaptation algorithms. The results show that the FCM‐based algorithm can achieve a desirable capability in adapting to changes and discovering class information from unlabeled data. The algorithm has also been tested by the real EEG data recorded in experiments in our laboratory and the data from other sources (set IIb of the BCI Competition IV). The results of real data are consistent with that of simulation data. Copyright © 2011 John Wiley & Sons, Ltd.     

立体视觉深度认知过程研究

利用自行研制的多导视觉诱发电位(VEP)信号采集处理系统和两套视差深度随机点立体(RDS)图对,诱发视皮层神经网络兴奋发放,提取并分析了立体视觉视差深度认知过程的皮层电位信号,对视差相关诱发电位特征进行了标定.采用两种完全不同的信息处理方法重复实验,揭示了高级视皮层功能区出现的N2波由视差相关VEP发放,提示体视视差深度信息处理可能是在高级视皮层功能区上完成的.根据不同功能区隐含信息的处理结果,推测大脑皮层体视信息处理系统中存在信息反馈通路.实验结果还表明,立体视觉深度认知过程是一个动态的复杂信息协同处理过程.