Motor imagery electroencephalogram (MI-EEG) based brain-computer interface (BCI) is a burgeoning auxiliary means to realize rehabilitation therapy. One of the major concerns in MI-EEG based BCI is to have an accurate classification, and effective and fast feature extraction is the key to build a successful MI-EEG classification model. In this paper, a novel classification system for MI-EEG signals is proposed based on flexible analytic wavelet transform (FAWT). The filtered MI-EEG signals are firstly subjected to the FAWT to obtain sub-bands, and time-frequency features are calculated from the sub-bands. MDS is then adopted to reduce the dimension of the extracted features, and principal component analysis (PCA), kernel principal component analysis (KPCA), locally linear embedding (LLE) and Laplacian Eigenmaps (LE) are utilized as comparison. Finally, linear discriminant analysis (LDA) is utilized to complete the classification of left-hand (LH) and right-hand (RH) MI-EEG signals. The proposed method is experimentally validated on BCI Competition II Data Set III (BCI Dataset III) and BCI Competition III Data Set IIIb (BCI Dataset IIIb). As a result, the combined method of FAWT, MDS attains the maximal mutual information (M_aI) of 0.95 and the maximum accuracy (ACC) of 94.29% using BCI Dataset III, and the mean of the maximal M_aI steepness of 0.3740 using BCI Dataset IIIb. The proposed method yields better performance in comparison to the existing methods. Overall, the effectiveness of the proposed approach suggests that it can be a worthwhile and promising method for a MI-EEG based BCI system.

基于运动图像脑电图（MI-EEG）的脑机接口（BCI）是实现康复治疗的新兴辅助手段。基于MI-EEG的BCI的主要问题之一是要进行准确的分类，有效而快速的特征提取是建立成功的MI-EEG分类模型的关键。本文提出了一种基于柔性解析小波变换（FAWT）的MI-EEG信号分类系统。首先对滤波后的MI-EEG信号进行FAWT以获得子带，然后从子带中计算出时频特征。然后采用MDS来减少提取特征的维数，并使用主成分分析（PCA），内核主成分分析（KPCA），局部线性嵌入（LLE）和拉普拉斯特征图（LE）作为比较。最后，线性判别分析（LDA）用于完成左手（LH）和右手（RH）MI-EEG信号的分类。该方法在BCI竞赛II数据集III（BCI数据集III）和BCI竞赛III数据集IIIb（BCI数据集IIIb）上进行了实验验证。结果，FAWT，MDS的组合方法获得了最大的互信息（M使用BCI数据集III的_a I）为0.95，最大精度（ACC）为94.29％，使用BCI数据集IIIb的最大M _a I陡度的平均值为0.3740。与现有方法相比，该方法具有更好的性能。总体而言，该方法的有效性表明，对于基于MI-EEG的BCI系统而言，它可能是一种值得且有希望的方法。