Ji Na, Ma Liang, Dong Hui, Zhang Xuejun
College of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, 210023 Nanjing, China.
Nation-Local Joint Project Engineering Lab of RF Integration & Micropackage, Nanjing University of Posts and Telecommunications, 210023 Nanjing, China.
Brain Sci. 2019 Aug 14;9(8):201. doi: 10.3390/brainsci9080201.
The classification recognition rate of motor imagery is a key factor to improve the performance of brain-computer interface (BCI). Thus, we propose a feature extraction method based on discrete wavelet transform (DWT), empirical mode decomposition (EMD), and approximate entropy. Firstly, the electroencephalogram (EEG) signal is decomposed into a series of narrow band signals with DWT, then the sub-band signal is decomposed with EMD to get a set of stationary time series, which are called intrinsic mode functions (IMFs). Secondly, the appropriate IMFs for signal reconstruction are selected. Thus, the approximate entropy of the reconstructed signal can be obtained as the corresponding feature vector. Finally, support vector machine (SVM) is used to perform the classification. The proposed method solves the problem of wide frequency band coverage during EMD and further improves the classification accuracy of EEG signal motion imaging.
运动想象的分类识别率是提高脑机接口（BCI）性能的关键因素。因此，我们提出了一种基于离散小波变换（DWT）、经验模态分解（EMD）和近似熵的特征提取方法。首先，利用DWT将脑电图（EEG）信号分解为一系列窄带信号，然后用EMD对该子带信号进行分解，得到一组平稳时间序列，称为本征模函数（IMF）。其次，选择合适的IMF进行信号重构。由此，可得到重构信号的近似熵作为相应的特征向量。最后，使用支持向量机（SVM）进行分类。该方法解决了EMD过程中频率覆盖范围宽的问题，进一步提高了EEG信号运动想象的分类准确率。
