中文摘要：

运动想象脑电特征是进行动作模式识别进而实现生物反馈技术的重要依据。在对侧躯体运动想象脑电识别方法的基础上，研究单侧躯体不同运动想象模式下的脑电特征提取问题，提出基于EMD．多尺度熵（MSE）的脑电信号瞬态特征提取及定量描述的方法，设计基于极限学习机（ELM）的动作模式识别模型。通过对10名正常受试者在左侧手臂屈、伸动作模式下的运动想象脑电的分析，提取其特征并进行动作识别，结果证实其识别率可以达到90％以上。实验表明：所提出基于EMD—MSE的运动想象EEG特征提取方法，能够定量刻画不同运动模式下脑电信号的多尺度局部瞬态特征；进一步运用基于ELM学习算法的前馈神经网络，可以实现对不同运动模式下脑电EMD—SME特征的有效分类。

英文摘要：

Brain electrical rhythms features of motor imagery are an important basis to recognize the movement patterns and realize the biofeedback-based rehabilitation therapy. Based on the recognition method of contralateral motion imagery EEG, the feature extraction method for unilateral motion imagery EEG in different patterns was studied in this paper. A new method based on EMD-multiscale entropy （MSE） was proposed to quantitatively describe the EEG transient feature, and a movement pattern recognition model based on extreme learning machine was designed. Furthermore, the present method was tested with the EEG data from 10 healthy subjects performing the flexion and extension motion of unilateral arm, and the validity of the proposed method was verified by the analysis of EEG feature extraction and movement recognition, and the recognition rate was higher than 90%. It is revealed that the EMD-MSE method can quantitatively describe the EEG transient feature under different patterns, and furthermore, the ELM based on feed forward neural network can recognize the movement patterns.