期刊
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
卷 29, 期 -, 页码 2484-2495出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNSRE.2021.3126752
关键词
Muscle force estimation; EMG decomposition; neural drive information; motor unit; deep learning
资金
- National Natural Science Foundation of China [61771444]
- Guangzhou Science and Technology Program [201704030039]
This study introduces a novel framework for interpreting motor unit (MU) activities and applying it to muscle force decoding. By characterizing the spatially distributed firing waveforms of MUs and utilizing a twitch force model, a deep network is designed to predict normalized force. Examination of MU category distribution to calibrate actual force levels shows the effectiveness of this framework in muscle force estimation.
Appropriate interpretation of motor unit (MU) activities after surface EMG (sEMG) decomposition is a key factor to decode motor intentions in a noninvasive and physiologically meaningful way. However, there are great challenges due to the difficulty in cross-trial MU tracking and unavoidable loss of partial MU information resulting from incomplete decomposition. In light of these issues, this study presents a novel framework for interpreting MU activities and applies it to decode muscle force. The resulting MUs were clustered and classified into different categories by characterizing their spatially distributed firing waveforms. The process served as a general MU tracking method. On this basis, after transferring the MU firing trains to twitch force trains by a twitch forcemodel, a deep network was designed to predict the normalized force. In addition, MU category distribution was examined to calibrate the actual force level, while functions of some unavailable MUs were compensated. To investigate the effectiveness of this framework, high-density sEMG signalswere recorded using an 8 x 8 electrode array from the abductor pollicis brevis muscles of eight subjects, while thumb abduction force was measured. The proposed method outperformed three common methods (p < 0.001) yielding the lowest root mean square deviation of 6.68% +/- 1.29% and the highest fitness (R-2) of 0.94 +/- 0.04 between the predicted force and the actual force. This study offers a valuable, computational solution for interpreting individual MU activities, and its effectiveness was confirmed in muscle force estimation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据