Surface electromyogram( SEMG)signal belongs to non-stationary biological signal,which is so weak and susceptible to interference. Through the acquisition of two channels of SEMG on flexor carpi radialis and brachioradialis with virtual instrument,the mean absolute value( MAV)and root mean square( RMS)can be taken as feature parameters,and the linear discriminant analysis ( LDA)method is appled to pattern recognition of the collected samples. The experiments comparing with other identification methods show that,the proposed recognition method in this paper can successfully identify four kinds of motions such as hand grasping,hand o-pening,radial flexion and ulnar flexion,and the recognition accuracy is much higher.%表面肌电信号( SEMG)属于非平稳的生物电信号,特点是信号微弱、易受干扰.为了有效提取表面肌电信号( SEMG)特征、更好地识别人体上肢运动的模式,针对表面肌电信号的特点提出了一种线性判别分析人体前臂运动特征的识别方法.通过虚拟仪器同时采集桡侧腕屈肌和肱桡肌两路的表面肌电信号,取平均绝对值( MAV)和均方根( RMS)为特征参数,应用线性判别分析( LDA)方法对样本特征矩阵进行模式识别.与其他特征识别方式的对比实验表明,此方法的动作识别率更高,能够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,动作的平均识别率达到了99.5%.
展开▼