北京生物医学工程

基于EMD和Hilbert变换的自发脑电信号特征提取

EEG Feature Extraction Based on Empirical Mode Decomposition and Hilbert Transform in Brain Computer Interface

作者：吴婷颜国正钱炳锋

单位：上海电机大学机械学院（上海200240）

分类号：

出版年·卷·期（页码）：2011·30·4（381-386）

摘要：

在脑机接口研究中，针对脑电信号的特征提取，提出一种基于EMD的Hilbert变换的方法。在变换过程中根据信号的局部特征自动选择基函数，求得信号在每个时间段的希尔波特谱；以时频窗口内的统计特性作为特征，利用Fisher距离选择最佳特征集输入分类器。最后利用BCI 2003竞赛数据，通过对特征矢量的可分性和识别精度两个指标的评估，表明了所提出方法的有效性。

In the study of brain computer interfaces，a method based on empirical mode decomposition(EMD) and Hilbert transformation was proposed. The method was used for the feature extraction of electroencephalogram. In this method，the basis function was selected automatically according to the local features of signal during the transforming process，the Hilbert spectrum was obtained in each period，and the statistical characteristics in time-frequency window were considered as features. Then the optimal feature sets were formed by the Fisher distance rule and put into the classification. The performance of the eigenvector was evaluated by separability and recognition accuracy with the data set of BCI 2003 competition，and classification results proved the effectiveness of the proposed method.

参考文献：

［1］Guger C，Neuper C，Walterspacher D，et al.Rapid prototyping of an EEG-based brain-computer interface (BCI)［J］. IEEE Trans Neural Syst Rehab Eng，2001,9(1):49-58.
［2］Lal TN，Schrder M，Hinterberger T, et al.Support vector channel selection in BCI［J］. IEEE Trans Neural Syst Rehab Eng，2004,5(6):1003-1010.
［3］Pfurtscheller G，Neuper C，Schlogl A，et al.Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters［J］. IEEE Trans Rehab Eng，1998,6(3):316-325.
［4］Millán J.Adaptive brain interfaces［J］. Commun ACM，2003，46：74-80.
［5］Millán J，Mourin~o J.Asynchronous BCI and local neural classifiers：An overview of the adaptive brain interface project［J］. IEEE Trans Neural Syst Rehab Eng，2003，11：159-161.
［6］Schroeder M，Bogdan M，Rosenstiel W，et al.Automated EEG feature selection for brain computer interfaces［C］.Proc 1st int IEEE EMBS Conf Neural Eng,2003:626-629.
［7］Garrett D，Peterson DA，Anderson CW，et al.Comparison of linear，nonlinear，and feature election methods for EEG signal classification［J］. IEEE Trans Neural Syst Rehab Eng，2003，11(2)：141-144.
［8］Srinivas M，Patnaik LM.Adaptive Probabilities of Crossover and Mutation in Genetic Algorithms［J］. IEEE Trans on Sys Man and Cybe，1994，24(4)：656-667.
［9］Wang HY.Nonstationary random signal analysis and processing［M］. Beijing：Defence Industry Press，1999.
［10］Mao KZ，Tan KC，SerW.Probabilistic neural-network structure determination for pattern classification［J］. IEEE Tran Neural Networks，2000,11(4):1010-1017.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录