A Feature-Encoded Physics-Informed Parameter Identification Neural Network for Musculoskeletal Systems.
A Feature-Encoded Physics-Informed Parameter Identification Neural Network for Musculoskeletal Systems.
复制标题
DOI：
10.1115/1.4055238
复制
发表时间：
2022-12-01
影响因子：
1.7
通讯作者：
Chen, Jiun-Shyan
中科院分区：
文献类型：
--
作者：
Taneja, Karan;He, Xiaolong;He, QiZhi;Zhao, Xinlun;Lin, Yun-An;Loh, Kenneth J.;Chen, Jiun-Shyan
关键词：
从生理测量中识别肌肉-肌腱力生成特性和肌肉活动，例如，运动数据和原始表面肌电图（sEMG）提供了构建用于健康状况评估和运动预测的对象特定的肌肉骨骼（MSK）数字孪生系统的机会。虽然具有从大量数据中提取复杂特征和模式的能力的机器学习方法已经被应用于给定sEMG信号的运动预测，但是所学习的数据驱动映射是黑盒的，并且可能不满足底层物理学并且具有降低的通用性。在这项工作中，我们提出了一个特征编码的物理信息参数识别神经网络（FEPI-PINN）的运动和参数识别的人类MSK系统的同时预测。在这种方法中，高维噪声sEMG信号的特征被投影到一个低维的噪声过滤嵌入空间，以增强转发动态预测。该FEPI-PINN模型可以被训练为将sEMG信号与关节运动相关联，并同时识别关键MSK参数。数值例子表明，该框架可以有效地识别特定于对象的肌肉参数和训练的物理信息的前向动力学代理产生准确的运动预测肘关节屈伸运动，与测量的关节运动数据是很好的协议。
Identification of muscle-tendon force generation properties and muscle activities from physiological measurements, e.g., motion data and raw surface electromyography (sEMG), offers opportunities to construct a subject-specific musculoskeletal (MSK) digital twin system for health condition assessment and motion prediction. While machine learning approaches with capabilities in extracting complex features and patterns from a large amount of data have been applied to motion prediction given sEMG signals, the learned data-driven mapping is black-box and may not satisfy the underlying physics and has reduced generality. In this work, we propose a feature-encoded physics-informed parameter identification neural network (FEPI-PINN) for simultaneous prediction of motion and parameter identification of human MSK systems. In this approach, features of high-dimensional noisy sEMG signals are projected onto a low-dimensional noise-filtered embedding space for the enhancement of forwarding dynamics prediction. This FEPI-PINN model can be trained to relate sEMG signals to joint motion and simultaneously identify key MSK parameters. The numerical examples demonstrate that the proposed framework can effectively identify subject-specific muscle parameters and the trained physics-informed forward-dynamics surrogate yields accurate motion predictions of elbow flexion-extension motion that are in good agreement with the measured joint motion data.
登录
查看更多内容
基于像素基的骨骼肌的无网格建模。
DOI：
10.1080/21681163.2015.1049712
发表时间：
2016
期刊：
Computer methods in biomechanics and biomedical engineering. Imaging & visualization
影响因子：
--
作者：
Chen JS;Basava RR;Zhang Y;Csapo R;Malis V;Sinha U;Hodgson J;Sinha S
通讯作者：
Sinha S
影响因子：
2.5
作者：
Hermens, HJ;Freriks, B;Rau, G
通讯作者：
Rau, G
影响因子：
3.8
作者：
Holzbaur, KRS;Murray, WM;Delp, SL
通讯作者：
Delp, SL
影响因子：
3.1
作者：
Costabal, Francisco Sahli;Yang, Yibo;Kuhl, Ellen
通讯作者：
Kuhl, Ellen
影响因子：
2.4
作者：
He Q;Laurence DW;Lee CH;Chen JS
通讯作者：
Chen JS