TY - JOUR
T1 - Boosting Personalized Musculoskeletal Modeling With Physics-Informed Knowledge Transfer
AU - Zhang, Jie
AU - Zhao, Yihui
AU - Bao, Tianzhe
AU - Li, Zhenhong
AU - Qian, Kun
AU - Frangi, Alejandro F.
AU - Xie, Sheng Quan
AU - Zhang, Zhi Qiang
N1 - Funding Information:
This work was supported in part by the U.K. Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/S019219/1 and Grant EP/V057782/1 and in part by the European Union (EU) Marie Curie Individual Fellowship under Grant 101023097.
Publisher Copyright:
© 1963-2012 IEEE.
PY - 2022/12/8
Y1 - 2022/12/8
N2 - Data-driven methods have become increasingly more prominent for musculoskeletal modelling due to their conceptually intuitive simple and fast implementation. However, the performance of a pre-trained data-driven model using the data from specific subject(s) may be seriously degraded when validated using the data from a new subject, hindering the utility of the personalised musculoskeletal model in clinical applications. This paper develops an active physics-informed deep transfer learning framework to enhance the dynamic tracking capability of the musculoskeletal model on the unseen data. The salient advantages of the proposed framework are twofold: 1) For the generic model, physics-based domain knowledge is embedded into the loss function of the data-driven model as soft constraints to penalise/regularise the data-driven model. 2) For the personalised model, the parameters relating to the feature extraction will be directly inherited from the generic model, and only the parameters relating to the subject-specific inference will be fine-tuned by jointly minimising the conventional data prediction loss and the modified physics-based loss. In this paper, we use the synchronous muscle forces and joint kinematics prediction from surface electromyogram (sEMG) as the exemplar to illustrate the proposed framework. Moreover, convolutional neural network (CNN) is employed as the deep neural network to implement the proposed framework, and the physics law between muscle forces and joint kinematics is utilised as the soft constraints. Results of comprehensive experiments on a self-collected dataset from eight healthy subjects indicate the effectiveness and great generalization of the proposed framework.
AB - Data-driven methods have become increasingly more prominent for musculoskeletal modelling due to their conceptually intuitive simple and fast implementation. However, the performance of a pre-trained data-driven model using the data from specific subject(s) may be seriously degraded when validated using the data from a new subject, hindering the utility of the personalised musculoskeletal model in clinical applications. This paper develops an active physics-informed deep transfer learning framework to enhance the dynamic tracking capability of the musculoskeletal model on the unseen data. The salient advantages of the proposed framework are twofold: 1) For the generic model, physics-based domain knowledge is embedded into the loss function of the data-driven model as soft constraints to penalise/regularise the data-driven model. 2) For the personalised model, the parameters relating to the feature extraction will be directly inherited from the generic model, and only the parameters relating to the subject-specific inference will be fine-tuned by jointly minimising the conventional data prediction loss and the modified physics-based loss. In this paper, we use the synchronous muscle forces and joint kinematics prediction from surface electromyogram (sEMG) as the exemplar to illustrate the proposed framework. Moreover, convolutional neural network (CNN) is employed as the deep neural network to implement the proposed framework, and the physics law between muscle forces and joint kinematics is utilised as the soft constraints. Results of comprehensive experiments on a self-collected dataset from eight healthy subjects indicate the effectiveness and great generalization of the proposed framework.
KW - Personalized musculoskeletal model
KW - physics-informed deep transfer learning
KW - surface electromyogram (sEMG)
KW - wrist muscle forces and joint kinematics estimation
UR - http://www.scopus.com/inward/record.url?scp=85144810265&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/68bf92d6-fd7b-3f6a-9795-e3af6e7382db/
U2 - 10.1109/TIM.2022.3227604
DO - 10.1109/TIM.2022.3227604
M3 - Article
VL - 72
SP - 1
EP - 11
JO - IEEE Transactions on Instrumentation and Measurement
JF - IEEE Transactions on Instrumentation and Measurement
SN - 0018-9456
M1 - 2500811
ER -