中文摘要：

为了提高肌电假手模式识别和速度比例控制准确率,提出一种基于肌电复杂度特征和支持向量机的比例控制假手方法.提取能够表征动作复杂度的Lempel-Ziv复杂度和平均功率作为表面肌电特征,输入支持向量机,对握拳、伸拳、腕伸及腕屈四个动作进行识别,同时通过三次样条插值方法对动作过程的肌电平均功率和动作速度进行拟合,实现假手的速度比例控制.实验表明：该方法取得了94.18%的动作模式平均识别率和8%以内的比例控制误差.

英文摘要：

In order to improve the accuracy of electromyography recognition and speed proportional control,aproportional control prosthetic hand based on EMG complexity and support vector machine（SVM）was proposed.The Lempel-Ziv complexity which could characterize the complexity of the action and the average power were extracted as the feature of surface electromyography.The support vector machine was employed to identify the four movements,which were hand close,hand open,wrist flexion and wrist extension.Meanwhile,the average power of the electromyography and the speed of motion were fitted by cubic spline interpolation method to achieve the speed proportional control of the prosthetic hand.The experimental results show that the proposed method achieves 94.18%of action pattern recognition rate and smaller proportional control error of less than 8%.