Harnessing Machine Learning and Physiological Knowledge for a Novel EMG-Based Neural-Machine Interface
Harnessing Machine Learning and Physiological Knowledge for a Novel EMG-Based Neural-Machine Interface
复制标题
DOI：
10.1109/tbme.2022.3210892
复制
发表时间：
2023-04-01
影响因子：
4.6
通讯作者：
Huang, He
中科院分区：
文献类型：
--
作者：
Berman, Joseph;Hinson, Robert;Huang, He
目的：在这项研究中，我们的目的是开发一种新的基于肌电图（EMG）的神经机器接口（NMI），称为神经网络-肌肉骨骼混合模型（N2 M2），解码连续关节角度。我们的方法结合了机器学习和肌肉骨骼建模的概念。研究方法：我们将我们的新设计与肌肉骨骼模型（MM）和2个基于人工神经网络（ANN）的连续EMG解码器进行了比较：多层感知器（MLP）和具有外源输入的非线性自回归神经网络（NARX网络）。EMG和关节运动学数据收集自10名非残疾和1名经桡截肢者。在3种不同条件下测试的离线性能（即，变化的手臂姿势、移动的电极位置和噪声污染的EMG信号）和虚拟姿势匹配任务的在线表现进行量化。最后，我们实现了N2 M2操作假手和测试功能任务的性能。结果：N2 M2在所有体位和电极位置的预测准确率均高于MLP（p < 0.003）。对于估计的MCP关节角度，N2 M2对噪声EMG信号的敏感性低于MM或NARX网络的误差（p < 0.032）以及NARX网络的相关性（p = 0.007）。此外，N2 M2比NARX网络具有更好的在线任务性能（p = 0.030）。结论：总的来说，我们发现，将机器学习和肌肉骨骼建模的概念结合起来，比单独使用任何一个概念都能产生更强大的关节运动学解码器。意义：这项研究的结果可能会导致一种新的，高度可靠的控制器的动力假手。
Objective: In this study, we aimed to develop a novel electromyography (EMG)-based neural machine interface (NMI), called the Neural Network-Musculoskeletal hybrid Model (N2M2), to decode continuous joint angles. Our approach combines the concepts of machine learning and musculoskeletal modeling. Methods: We compared our novel design with a musculoskeletal model (MM) and 2 continuous EMG decoders based on artificial neural networks (ANNs): multilayer perceptrons (MLPs) and nonlinear autoregressive neural networks with exogenous inputs (NARX networks). EMG and joint kinematics data were collected from 10 non-disabled and 1 transradial amputee subject. The offline performance tested across 3 different conditions (i.e., varied arm postures, shifted electrode locations, and noise-contaminated EMG signals) and online performance for a virtual postural matching task was quantified. Finally, we implemented the N2M2 to operate a prosthetic hand and tested functional task performance. Results: The N2M2 made more accurate predictions than the MLP in all postures and electrode locations (p < 0.003). For estimated MCP joint angles, the N2M2 was less sensitive to noisy EMG signals than the MM or NARX network with respect to error (p < 0.032) as well as the NARX network with respect to correlation (p = 0.007). Additionally, the N2M2 had better online task performance than the NARX network (p = 0.030). Conclusion: Overall, we have found that combining the concepts of machine learning and musculoskeletal modeling has resulted in a more robust joint kinematics decoder than either concept individually. Significance: The outcome of this study may result in a novel, highly reliable controller for powered prosthetic hands.