4.5 Article

A multi-Kalman filter-based approach for decoding arm kinematics from EMG recordings

期刊

BIOMEDICAL ENGINEERING ONLINE
卷 21, 期 1, 页码 -

出版社

BMC
DOI: 10.1186/s12938-022-01030-6

关键词

Kalman filter; Decoding; EMG; Prosthetic arms

资金

  1. Deutscher Akademischer Austauschdienst (DAAD) German Egyptian Research short term scholarship (GERSS) [57237401]

向作者/读者索取更多资源

This study proposes an EMG-based multi-Kalman filter approach to decode arm kinematics, specifically the elbow angle, wrist joint horizontal and vertical positions. The results demonstrate the efficacy of the proposed approach, achieving good performance when training and testing with the same-subject data, and indicating the possibility of obtaining a subject-independent decoder.
Background Remarkable work has been recently introduced to enhance the usage of Electromyography (EMG) signals in operating prosthetic arms. Despite the rapid advancements in this field, providing a reliable, naturalistic myoelectric prosthesis remains a significant challenge. Other challenges include the limited number of allowed movements, lack of simultaneous, continuous control and the high computational power that could be needed for accurate decoding. In this study, we propose an EMG-based multi-Kalman filter approach to decode arm kinematics; specifically, the elbow angle (theta), wrist joint horizontal (X) and vertical (Y) positions in a continuous and simultaneous manner. Results Ten subjects were examined from which we recorded arm kinematics and EMG signals of the biceps, triceps, lateral and anterior deltoid muscles corresponding to a randomized set of movements. The performance of the proposed decoder is assessed using the correlation coefficient (CC) and the normalized root-mean-square error (NRMSE) computed between the actual and the decoded kinematic. Results demonstrate that when training and testing the decoder using same-subject data, an average CC of 0.68 +/- 0.1, 0.67 +/- 0.12 and 0.64 +/- 0.11, and average NRMSE of 0.21 +/- 0.06, 0.18 +/- 0.03 and 0.24 +/- 0.07 were achieved for theta, X, and Y, respectively. When training the decoder using the data of one subject and decoding the data of other subjects, an average CC of 0.61 +/- 0.19, 0.61 +/- 0.16 and 0.48 +/- 0.17, and an average NRMSE of 0.23 +/- 0.07, 0.2 +/- 0.05 and 0.38 +/- 0.15 were achieved for theta, X, and Y, respectively. Conclusions These results suggest the efficacy of the proposed approach and indicates the possibility of obtaining a subject-independent decoder.

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。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据