Wang Zhuo, Chen Chunjie, Chen Hui, Zhou Yizhe, Wang Xiangyang, Wu Xinyu
IEEE J Biomed Health Inform. 2025 Mar 27;PP. doi: 10.1109/JBHI.2025.3555255.
Accurate estimation of lower limb joint kinematics and kinetics using wearable sensors enables biomechanical analysis beyond laboratory settings and facilitates real-time adaptation of exoskeleton assistance profiles. This study introduces a Dual Transformer Network (DTN) designed to concurrently estimate multiple joint angles and moments from multi-channel surface electromyography (sEMG) signals in the lower limbs. The performance evaluation of the predicted joint angles for the hip, knee, and ankle showed average root mean square error (RMSE) values of 1.1827, 1.4312, and 0.8113, Pearson correlation coefficients () of 0.9992, 0.9993, and 0.9991, and coefficients of determination () of 0.9847, 0.9858, and 0.9838, respectively. For the predicted joint moments, the corresponding values were RMSE of 0.0458, 0.0341, and 0.0522 Nm/kg, of 0.9978, 0.9972, and 0.9990, and of 0.9825, 0.9801, and 0.9902. Angular velocities, derived by differentiating the estimated joint angles, achieved an RMSE below 0.6530 rd/s, exceeding 0.9534, and above 0.9552. Additionally, joint power, computed as the dot product of predicted joint moments and angular velocities, resulted in RMSE below 0.3823W/kg, above 0.9771, and above 0.8925. These results demonstrate the effectiveness of the proposed network in continuously estimating lower limb kinematics and kinetics, contributing to advancements in assist-as-needed exoskeleton control strategies.
使用可穿戴传感器准确估计下肢关节运动学和动力学，能够在实验室环境之外进行生物力学分析，并有助于实时调整外骨骼辅助参数。本研究引入了一种双变压器网络（DTN），旨在从下肢多通道表面肌电图（sEMG）信号中同时估计多个关节角度和力矩。对髋关节、膝关节和踝关节预测关节角度的性能评估显示，平均均方根误差（RMSE）值分别为1.1827、1.4312和0.8113，皮尔逊相关系数（）分别为0.9992、0.9993和0.9991，决定系数（）分别为0.9847、0.9858和0.9838。对于预测的关节力矩，相应的值分别为RMSE为0.0458、0.0341和0.0522 Nm/kg，为0.9978、0.9972和0.9990，为0.9825、0.9801和0.9902。通过对估计的关节角度进行微分得到的角速度，RMSE低于0.6530 rd/s，超过0.9534，超过0.9552。此外，作为预测关节力矩和角速度的点积计算得到的关节功率，RMSE低于0.3823W/kg，超过0.9771，超过0.8925。这些结果证明了所提出网络在连续估计下肢运动学和动力学方面的有效性，有助于按需辅助外骨骼控制策略的发展。
