基于小波包熵的运动意识任务分类研究

STUDY ON CLASSIFICATION OF IMAGINARY HAND MOVEMENTS BASED ON WAVELET PACKET ENTROPY

提出了以小波包熵作为脑电特征向量的左右手运动意识任务分类方法,对被测试者想象左右手运动时的脑电小波包熵动态变化情况及分析窗口长度的选择进行了研究。结果表明,小波包熵能很好地反映左右手运动想象的脑电特征变化,用线性判别式算法对脑电特征进行识别,分类正确率达到92.14%。由于小波包熵的计算比较简单,稳定性好,识别率高,为大脑运动意识任务的分类提供了新思路。

Based on wavelet packet entropy derived from EEG, a method of classification of imagining hand movements was proposed. The EEG signals have been recorded during the imagination of left or right hand movement. The wavelet packet entropy of EEG and its dynamic changing properties with respect to time and windows length have been analyzed. The event-related EEG patterns during imagining left and right hand movement were identified by using linear discriminant algorithm. The results show that the method is effective and the correct rate of classification is up to 92.14%. Since the computation of wavelet packet entropy is simple, the result is stable, and the identification rate is high, the new method might provide a new way for the classification of mental tasks.