脑力负荷识别对提高人机交互操作人员的工作绩效具有重要意义。目前已有研究表明,通过提取脑电(electroencephalogram,EEG)信号的能量特征进行脑力负荷识别取得了不错的分类效果。但该方法只关注到信号的幅度信息,而忽略了相位信息;只...脑力负荷识别对提高人机交互操作人员的工作绩效具有重要意义。目前已有研究表明,通过提取脑电(electroencephalogram,EEG)信号的能量特征进行脑力负荷识别取得了不错的分类效果。但该方法只关注到信号的幅度信息,而忽略了相位信息;只分析了各个通道的频域特征,没有考虑不同通道信号之间的同步关系。为充分考虑不同脑区间的功能连接性,提出一种基于加权相位滞后指数(weighted phase lag index,WPLI)热力图的脑力负荷分类方法。对预处理后的脑电信号计算两两通道间的WPLI并绘制热力图,用于评估不同通道信号之间的相位耦合情况,由此反映不同脑区间的功能连接性。由WPLI热力图可以直观地观察到:在高、低负荷状态下,大脑功能连接性的分布存在明显差异。通过实验分别对能量特征图和WPLI热力图采用方向梯度直方图-支持向量机(histogram of oriented gradient-support vector machine,HOG-SVM)和LeNet-5两种方法进行分类。结果表明:WPLI热力图和LeNet-5的组合具有较好的分类结果。展开更多
Parkinson’s disease(PD)is a neurodegenerative disordercharacterized by motor retardation,myotonia,quiescent tremor,and postural gait abnormality,as well as nonmotor symptoms such asanxiety and depression.Biofeedback ...Parkinson’s disease(PD)is a neurodegenerative disordercharacterized by motor retardation,myotonia,quiescent tremor,and postural gait abnormality,as well as nonmotor symptoms such asanxiety and depression.Biofeedback improves motor and nonmotorfunctions of patients by regulating abnormal electroencephalogram(EEG),electrocardiogram(ECG),photoplethysmography(PPG),electromyography(EMG),respiration(RSP),or other physiologicalsignals.Given that multimodal signals are closely related to PDstates,the clinical effect of multimodal biofeedback on patientswith PD is worth exploring.Twenty-one patients with PD in Beijing Rehabilitation Hospital were enrolled and divided into threegroups:multimodal(EEG,ECG,PPG,and RSP feedback signal),EEG(EEG feedback signal),and sham(random feedback signal),and they received biofeedback training five times in two weeks.The combined clinical scale and multimodal signal analysis resultsrevealed that the EEG group significantly improved motor symptomsand increased Berg balance scale scores by regulatingβband activity;the multimodal group significantly improved nonmotorsymptoms and reduced Hamilton rating scale for depression scores by improvingθband activity.Our preliminary results revealed thatmultimodal biofeedback can improve the clinical symptoms of PD,but the regulation effect on motor symptoms is weaker than that ofEEG biofeedback.展开更多
文摘脑力负荷识别对提高人机交互操作人员的工作绩效具有重要意义。目前已有研究表明,通过提取脑电(electroencephalogram,EEG)信号的能量特征进行脑力负荷识别取得了不错的分类效果。但该方法只关注到信号的幅度信息,而忽略了相位信息;只分析了各个通道的频域特征,没有考虑不同通道信号之间的同步关系。为充分考虑不同脑区间的功能连接性,提出一种基于加权相位滞后指数(weighted phase lag index,WPLI)热力图的脑力负荷分类方法。对预处理后的脑电信号计算两两通道间的WPLI并绘制热力图,用于评估不同通道信号之间的相位耦合情况,由此反映不同脑区间的功能连接性。由WPLI热力图可以直观地观察到:在高、低负荷状态下,大脑功能连接性的分布存在明显差异。通过实验分别对能量特征图和WPLI热力图采用方向梯度直方图-支持向量机(histogram of oriented gradient-support vector machine,HOG-SVM)和LeNet-5两种方法进行分类。结果表明:WPLI热力图和LeNet-5的组合具有较好的分类结果。
文摘目的:探讨定量脑电图分析在阿尔茨海默病(Alzheimer’s disease,AD)中的应用价值。方法:我们纳入AD患者和认知功能正常老年人各26人。利用20导联的静息态脑电图检测受试者脑电波形。采用各频段功率值和加权相位延迟指数(weighted phase lag index,wPLI)分析各组人群中脑电波变化的差异性。结果:在AD组中,θ频段的功率显著高于对照组。另外,两组中功能连接的差异主要存在于低频段的δ和θ中。δ频段中AD病人的相位同步性减低,而在θ频段中AD病人的相位同步性明显强于对照组。结论:定量脑电图分析中显示,阿尔茨海默病病人脑内频率慢化和功能失连接的现象。
基金This work was supported by the STI 2030-Major Projects(Grant No.2022ZD0208500)the National Natural Science Foundation of China(Grant Nos.U20A20191,82071912,12104049,82202291)+2 种基金the Key Research and Development Program(Grant No.2022YFC3602603)the Fundamental Research Funds for the Central Universities(Grant No.2021CX11011)the National Key Research and Development Program of China(Grant No.2020YFC2007305).
文摘Parkinson’s disease(PD)is a neurodegenerative disordercharacterized by motor retardation,myotonia,quiescent tremor,and postural gait abnormality,as well as nonmotor symptoms such asanxiety and depression.Biofeedback improves motor and nonmotorfunctions of patients by regulating abnormal electroencephalogram(EEG),electrocardiogram(ECG),photoplethysmography(PPG),electromyography(EMG),respiration(RSP),or other physiologicalsignals.Given that multimodal signals are closely related to PDstates,the clinical effect of multimodal biofeedback on patientswith PD is worth exploring.Twenty-one patients with PD in Beijing Rehabilitation Hospital were enrolled and divided into threegroups:multimodal(EEG,ECG,PPG,and RSP feedback signal),EEG(EEG feedback signal),and sham(random feedback signal),and they received biofeedback training five times in two weeks.The combined clinical scale and multimodal signal analysis resultsrevealed that the EEG group significantly improved motor symptomsand increased Berg balance scale scores by regulatingβband activity;the multimodal group significantly improved nonmotorsymptoms and reduced Hamilton rating scale for depression scores by improvingθband activity.Our preliminary results revealed thatmultimodal biofeedback can improve the clinical symptoms of PD,but the regulation effect on motor symptoms is weaker than that ofEEG biofeedback.
