Hand gesture recognition based on motor unit spike trains decoded from high-density electromyography
Hand gesture recognition based on motor unit spike trains decoded from high-density electromyography
复制标题
基于高密度肌电图解码的运动单位尖峰序列的手势识别
DOI：
10.1016/j.bspc.2019.101637
复制
发表时间：
2020-01-01
影响因子：
5.1
通讯作者：
Zhu, Xiangyang
中科院分区：
文献类型：
--
作者：
Chen, Chen;Yu, Yang;Zhu, Xiangyang
目的：近十年发展起来的表面肌电信号分解方法，用于提取从脊髓传递到肌肉的神经信息。本文研究了从高密度肌电信号识别手势时运动单位活动的准确性，并提出了一种神经信号与手势之间的映射方法。采用盲源分离算法将EMG信号离线分解成运动单位棘波序列(MUST)。提出了一种基于运动单元分类的手势识别方法。首先将11项动议对应的分组。然后将神经驱动对每个动作的激活程度估计为各组必需动作的放电次数之和。通过比较每个动作的激活程度来确定输出手势类别。结果：平均每个动作识别出29个+/-8个动作，估计分解准确率为90%。基于该方法对11个手势的平均分类准确率为95%，优于传统的基于全局肌电特征的手势分类方法。结论和意义：这些结果表明了识别预期运动任务中运动单位活动的可能性，并展示了手势的高分类精度，具有人机界面的前景。(C)2019爱思唯尔有限公司。保留所有权利。
Objective: Methods for surface electromyographic (EMG) signal decomposition have been developed in the past decade, to extract neural information transferred from the spinal cord to muscles. Here, we characterize the accuracy in the identification of motor unit activities during hand postures from high-density EMG signals and we propose a mapping approach between these neural signals and hand gestures.Methods: High-density EMG signals were recorded during 11 hand gesture tasks from 11 able-bodied subjects. EMG signals were offline decomposed into motor unit spike trains (MUSTs) with a blind source separation algorithm. A gesture recognition approach based on motor unit classification was proposed. MUSTs were first pooled into groups corresponding to the 11 motions. Then the activation level of the neural drive to each motion was estimated as the summed discharge timings of MUSTs in each group. The output gesture class was determined by comparing the estimated activation level of each motion.Results: On average, 29 +/- 8 MUSTs were identified for each motion with an estimated decomposition accuracy >90%. The average classification accuracy for 11 hand gestures based on the proposed approach was >95% and outperformed the classic approach of using global EMG features.Conclusion and significance: These results indicate the possibility of identifying motor unit activities during intended motor tasks and demonstrate high classification accuracy of the hand gestures, with perspectives for human-machine interfacing. (C) 2019 Elsevier Ltd. All rights reserved.