基于AR模型和BP网络的表面EMG信号模式分类

Basing on AR model and BP neural network to classify SEMG

提出了一种以AR模型和BP网络相结合的表面肌电信号处理方法 .首先 ,将采集到的肌电信号进行预处理 ,提取AR系数作为其特征值 ;其次 ,设计了一个三层的BP神经网络 ,利用AR系数对手臂的各种肢体动作进行运动模式的分类 .实验表明 ,这种方法不仅减少了计算工作量 ,同时取得了比较理想的识别效果 .

In this paper, a method to process surface electromyography signal was presented. It based on AR model and BP neural network. First, we created AR model with the original signal that was pretreated and took the coefficient as its eigenvector. Second, a three-layer BP neural network was designed to classify the muscle movement of forearm with AR model coefficient. The experiment indicates this measure can reduce workload and get the relatively good results.