基于表面肌电信号的手指关节角度估计方法  

Estimation of finger joint angles based on surface electromyographic signal

作　　者：张娜[1,2] 张明进 王晓冬 梁铁[1,3] 李俊[1,3] 熊鹏[1,3] 刘晓光 Zhang Na;Zhang Mingjin;Wang Xiaodong;Liang Tie;Li Jun;Xiong Peng;Liu Xiaoguang(China Key Laboratory of Digital Medical Engineering,Hebei University,Baoding 071002,China;Stone pharmaceutical Group Zhongnuo Pharmaceutical Co.,LTD.,Shijiazhuang 050000,China;College of Electronic Information Engineering,Hebei University,Baoding 071002,China;Affiliated Hospital of Hebei University,Baoding 071002,China)

机构地区：[1]河北大学河北省数字医疗工程重点实验室,保定071002 [2]石药集团中诺药业有限公司,石家庄050000 [3]河北大学电子信息工程学院,保定071002 [4]河北大学附属医院,保定071002

出　　处：《电子测量与仪器学报》2023年第8期60-70,共11页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金(62276087);河北省自然科学基金(2021201002);河北省教育厅科技计划项目(ZD2020146)资助。

摘　　要：为了实现智能假手能够自然地模拟人手的连续运动,提出了基于s EMG的DF-ANN模型来估计手指关节角度的方法。该方法引入了通道注意力机制中的SE-Net模块增强了s EMG的相关特征表达,减少s EMG重要特征的损失,有效提高了回归模型的性能,选取10名健康的受试者进行10种不同手势的实验,选择R-Squared(R^(2))等回归衡量指标来评估该方法关节角度估计的精度,实验结果显示R^(2)为86.5%。与未引入SE-Net的DF-ANN模型,单独的深度森林和人工神经网络相比,R^(2)大约提高了4%。这表明该方法能够有效减小s EMG的关节角度连续解码的误差,能够有助于实现智能假手的柔顺控制。In order to achieve an intelligent prosthetic hand that can naturally simulate the continuous motion of a human hand,this paper proposes a DF-ANN model based on sEMG to estimate the finger joint angle.The method introduces the SE-Net module in the channel attention mechanism to enhance the relevant feature expression of sEMG,reduce the loss of essential features of sEMG,and effectively improve the performance of the regression model.10 healthy subjects were selected for experiments with 10 different hand gestures,and regression measures such as R-Squared(R^(2))were chosen to evaluate the accuracy of the method’s joint angle estimation.The experimental results showed an R^(2) of 86.5%.Compared with the DF-ANN model without introducing SE-Net,the deep forest,and an artificial neural network alone,the R^(2) is improved by about 4%.It indicates that the method effectively reduces the error of successive decoding of joint angles of sEMG and can contribute to the supple control of intelligent prosthetic hands.

关 键 词：表面肌电信号 深度森林 人工神经网络 通道注意力机制 手指关节角度估计 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]