Qin Zixuan, Stapornchaisit Sorawit, He Zixun, Yoshimura Natsue, Koike Yasuharu
Department of Information and Communications Engineering, Tokyo Institute of Technology, Yokohama, Japan.
Institute of Innovative Research, Tokyo Institute of Technology, Yokohama, Japan.
Front Neurorobot. 2021 Aug 2;15:685961. doi: 10.3389/fnbot.2021.685961. eCollection 2021.
To improve the life quality of forearm amputees, prosthetic hands with high accuracy, and robustness are necessary. The application of surface electromyography (sEMG) signals to control a prosthetic hand is challenging. In this study, we proposed a time-domain CNN model for the regression prediction of joint angles in three degrees of freedom (3-DOFs, include two wrist joint motion and one finger joint motion), and five-fold cross validation was used to evaluate the correlation coefficient (CC). The CC value results of wrist flexion/extension motion obtained from 10 participants was 0.87-0.92, pronation/supination motion was 0.72-0.95, and hand grip/open motion was 0.75-0.94. We backtracked the fully connected layer weights to create a geometry plot for analyzing the motion pattern to investigate the learning of the proposed model. In order to discuss the daily updateability of the model by transfer learning, we performed a second experiment on five of the participants in another day and conducted transfer learning based on smaller amount of dataset. The CC results improved (wrist flexion/extension was 0.90-0.97, pronation/supination was 0.84-0.96, hand grip/open was 0.85-0.92), suggesting the effectiveness of the transfer learning by incorporating the small amounts of sEMG data acquired in different days. We compared our CNN-based model with four conventional regression models, the result illustrates that proposed model significantly outperforms the four conventional models with and without transfer learning. The offline result suggests the reliability of the proposed model in real-time control in different days, it can be applied for real-time prosthetic control in the future.
为提高前臂截肢者的生活质量，需要高精度且稳健的假肢手。将表面肌电（sEMG）信号应用于控制假肢手具有挑战性。在本研究中，我们提出了一种时域卷积神经网络（CNN）模型，用于对三个自由度（3-DOF，包括两个腕关节运动和一个手指关节运动）的关节角度进行回归预测，并使用五折交叉验证来评估相关系数（CC）。从10名参与者获得的腕关节屈伸运动的CC值结果为0.87 - 0.92，旋前/旋后运动为0.72 - 0.95，手握/松开运动为0.75 - 0.94。我们回溯全连接层权重以创建几何图来分析运动模式，以研究所提出模型的学习情况。为了通过迁移学习讨论模型的日常可更新性，我们在另一天对五名参与者进行了第二次实验，并基于较少量的数据集进行迁移学习。CC结果得到改善（腕关节屈伸为0.90 - 0.97，旋前/旋后为0.84 - 0.96，手握/松开为0.85 - 0.92），这表明通过合并在不同日期采集的少量sEMG数据进行迁移学习是有效的。我们将基于CNN的模型与四个传统回归模型进行比较，结果表明所提出的模型在有无迁移学习的情况下均显著优于四个传统模型。离线结果表明所提出的模型在不同日期的实时控制中具有可靠性，未来可应用于实时假肢控制。
