摘要
本文提出利用奇异值分解提取最大主分量贡献率和累积贡献率95%所需的主分量个数,作为疲劳脑电图(EEG)的特征指标,研究它们在不同中枢疲劳状态下的变化规律。结果表明,随着中枢疲劳程度的加深,前额叶、额叶和中央区EEG信号的最大主分量贡献率显著增加(P<0.05),累积贡献率95%所需的主分量个数显著减少(P<0.05)。EEG信号奇异系统分解参数作为评价中枢疲劳的一种有效特征,在中枢疲劳研究中具有较大的应用价值。
In the present paper,the contribution of the largest principal component and the number of principal component needed for accumulative contribution 95%are selected as indices of electroencephalogram（EEG）in mental fatigue state in order to investigate the relationship between these parameters and mental fatigue.The experimental results showed that the contribution of the largest principal component of EEG signals increased in the prefrontal,frontal and central areas,while the number of principal component needed for accumulative contribution decreased by95% with the increasing mental fatigue level.The parameters of singular system of EEG signals can be regarded as useful features for the estimation of mental fatigue and have larger application value in the study of mental fatigue.
出处
《生物医学工程学杂志》
EI
CAS
CSCD
北大核心
2014年第5期1132-1134,1138,共4页
Journal of Biomedical Engineering
基金
国家自然科学基金资助项目(61302011
81271659)
中国博士后科学基金面上资助项目(2014M552348)
关键词
中枢疲劳
脑电图
奇异系统分析
最大主分量
mental fatigue
electroencephalogram
singular system analysis
the largest principal component
