摘要
本文介绍了希尔伯特-黄变换(HHT)的实现过程与优点,研究基于HHT和BP神经网络的运动想象脑电(EEG)识别方法。在对运动想象EEG数据预处理后进行经验模态分解(EMD)分析得到各阶固有模态函数(IMF)分量,去除分解中的多余低频分量再作边际谱分析;选择C3、C4通道边际谱能量差作为特征,经过主成分分析降维后,联合时域的EEG复杂度作为特征向量,利用BP神经网络进行分类。对脑-计算机接口(BCI)竞赛数据进行左右手分类识别,识别率达到87.14%,取得了较理想的结果,证明了HHT对运动想象EEG处理的可行性与有效性。
This paper introduces the characteristics of the Hilbert-Huang transform （HHT）, and studies the classifi- cation of movement imagery EEG based on the HHT method and BP neural network. After preprocessed, the move- ment imagery EEG data were deseomposed with empirical mode decomposition （EMD） into a series of intrinsic mode functions （IMFs）. Then the low frequency IMFs were removed, and the rest of IMFs were conducted by Hilbert transform to get Hilbert marginal spectrum. The marginal spectrum subtracted values between the ehannal C3 and ehannal C4 were selected as the original features which were then decreased the dimension by the principal compo- nents analysis so as to be jointed with EEG complexity to construct the feature vector. The BP neural network was utilized to classify the EEG pattern of left and right hand motor imagery, The brain computer interface （BCI） compe- tition Ⅱ data set Ⅲ was selected to carry out the discrimination, and the classification accuracy rate is up to 87. 14%, which is a comparably good result and proves HHT to be a feasible and effective method on EEG analysis.
出处
《生物医学工程学杂志》
EI
CAS
CSCD
北大核心
2013年第2期249-253,共5页
Journal of Biomedical Engineering
关键词
脑-计算机接口
希尔伯特-黄变换
BP神经网络
运动想象
分类识别
Brain-- computer interface （BCI）
Hilbert-Huang transform （HHT）
BP neural network
Movementimagery
Classification
