基于WPT和LDA的表面肌电信号特征识别方法

SEMG Feature Recognition Based on WPT and LDA

针对时域特征参数在表面肌电信号(SEMG)模式识别过程中的局限性,提出一种小波包变换(WPT)和线性判别分析(LDA)相结合的新方法;通过虚拟仪器采集桡侧腕屈肌和肱桡肌两路表面肌电信号,应用小波包变换对表面肌电信号进行多尺度分解,提取小波包系数并计算其均方根作为特征参数,应用线性判别分析对表面肌电信号数据进行分类识别;实验结果表明,采用此方法成功地从表面肌电信号中识别握拳、展拳、手腕内翻和手腕外翻4种动作,与时域参数相比,此方法更能有效提取表面肌电信号信息,且有较高的动作识别率,识别率高达98.2%。

According to the limitation of the time domain features in pattern recognition of surface electromyography （SEMG） signal, we put forward a kind of method combining wavelet packet transform （WPT） and linear discriminant analysis （LDA）. Two channel SEMG sig nal on flexor carpi radialis and brachioradialis are acquired with virtual instrument. Then we use wavelet packet transform （WPT） to carry out SEMG multi--scale decomposition, extract wavelet coefficients and work out their Root Mean Square （RMS） as SEMG characteristic pa- rameters. At last we apply linear discriminant analysis （LDA） to classify the data of SEMG signal. Experiments show that, using this method can successfully identify four kinds of motions such as hand grasping, hand opening, radial flexion and ulnar flexion. Compared with the time domain parameters, this method can effectively extract the information of SEMG signal, and has a higher recognition rate up to 98.2 %.