Koo Bon Ho, Siu Ho Chit, Petersen Lonnie G
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
MIT Lincoln Laboratory, Lexington, MA 02421, USA.
Sensors (Basel). 2025 Sep 3;25(17):5474. doi: 10.3390/s25175474.
The use of surface electromyography (sEMG) for conventional motion classification and prediction has had limitations due to sensor hardware differences. With the popularization of deep learning-based approaches to the application of motion prediction, this study explores the effects that different hardware sensor platforms have on the performance of a deep learning neural network trained to predict the one-degree-of-freedom (DoF) angular trajectory of a human. Two different sEMG sensor platforms were used to collect raw data from subjects conducting exercises, which was used to train a neural network designed to predict the future angular trajectory of the arm. The results show that the raw data originating from different sensor hardware with different configurations (including the communication method, data acquisition unit (DAQ) usage, electrode configuration, buffering method, preprocessing method, and experimental variables like the sampling frequency) produced bi-LSTM networks that performed similarly. This points to the hardware-agnostic nature of such deep learning networks.
由于传感器硬件差异，表面肌电图（sEMG）用于传统运动分类和预测存在局限性。随着基于深度学习的运动预测方法的普及，本研究探讨了不同硬件传感器平台对训练用于预测人体单自由度（DoF）角轨迹的深度学习神经网络性能的影响。使用两种不同的sEMG传感器平台从进行锻炼的受试者收集原始数据，这些数据用于训练一个旨在预测手臂未来角轨迹的神经网络。结果表明，来自具有不同配置（包括通信方法、数据采集单元（DAQ）使用情况、电极配置、缓冲方法、预处理方法以及采样频率等实验变量）的不同传感器硬件的原始数据，产生的双向长短期记忆（bi-LSTM）网络表现相似。这表明此类深度学习网络具有硬件无关性。
