基于时变协同的脑瘫患儿肌电包络信号生成模型研究  

Research on a Time-Varying Synergy-Based Model for sEMG Envelope Signal Generation

作　　者：汤璐 郑辉 王祥瑞 潘子豪 Lu Tang;Hui Zheng;Xiangrui Wang;Zihao Pan(School of Health Science and Engineering,University of Shanghai for Science and Technology,Shanghai)

机构地区：[1]上海理工大学健康科学与工程学院,上海

出　　处：《建模与仿真》2025年第3期135-145,共11页Modeling and Simulation

摘　　要：表面肌电信号(surfaceelectromyography,sEMG)是由肌肉活动引发的微弱电信号,由于sEMG信号采集过程受试者募集难度及伦理审批的限制,快速获取大规模样本用于研究面临挑战。本文为解决脑瘫(CerebralPalsy,CP)患者样本不足的问题,提出了一种以时变肌肉协同模型为基础的CP患儿肌电包络信号生成的模型。将采集的健康成人和CP患儿步态过程双下肢各8块肌肉sEMG信号和加速度信号,通过非负矩阵算法提取受试者的协同结构矩阵和激活系数矩阵,并以健康成人的激活系数矩阵为参考,通过引入时间延迟变量获得一系列更新后的激活系数矩阵,随后与CP患儿的协同结构矩阵相乘,进而得到全新的肌电包络信号。为验证生成信号的准确性,本文通过交并比(IntersectionoverUnion,IoU)IoU评估生成信号的肌肉激活时间与真实CP患者之间的相似性,结果显示8块肌肉的平均相似性为64.94%,表明生成包络信号符合CP患者的肌肉激活特征。Surface electromyography(sEMG)signals,which are weak electrical signals generated by muscle activity,face challenges in rapid acquisition of large-scale samples for research due to difficulties in participant recruitment and ethical approval restrictions during the signal acquisition process.To address the issue of insufficient samples from cerebral palsy(CP)patients,this paper proposes a model for generating sEMG envelope signals for children with CP based on a time-varying muscle synergy model.sEMG and acceleration signals from eight muscles in both lower limbs during gait were collected from healthy adults and children with CP.The synergy structure matrix and activa-tion coefficient matrix of the subjects were extracted using a non-negative matrix factorization al-gorithm.Using the activation coefficient matrix of healthy adults as a reference,a series of updated activation coefficient matrices were obtained by introducing time delay variables.These matrices were then multiplied with the synergy structure matrix of children with CP to generate new sEMG envelope signals.To validate the accuracy of the generated signals,the Intersection over Union(IoU)was used to evaluate the similarity between the muscle activation timing of the generated signals and that of real CP patients.The results showed an average similarity of 64.94%across the eight muscles,demonstrating that the generated envelope signals align well with the muscle activation characteristics of CP patients.

关 键 词：表面肌电信号 脑瘫患儿 时变协同模型 包络信号生成 

分 类 号：R318[医药卫生—生物医学工程]