Knowledge-Based Deep Learning for Time-Efficient Inverse Dynamics
Accurate understanding of muscle activation and muscle forces plays an essential role in neuro-rehabilitation and musculoskeletal disorder treatments. Computational musculoskeletal modeling has been widely used as a powerful non-invasive tool to estimate them through inverse dynamics using static op...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10844911/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583965736697856 |
|---|---|
| author | Shuhao Ma Yu Cao Ian D. Robertson Chaoyang Shi Jindong Liu Zhi-Qiang Zhang |
| author_facet | Shuhao Ma Yu Cao Ian D. Robertson Chaoyang Shi Jindong Liu Zhi-Qiang Zhang |
| author_sort | Shuhao Ma |
| collection | DOAJ |
| description | Accurate understanding of muscle activation and muscle forces plays an essential role in neuro-rehabilitation and musculoskeletal disorder treatments. Computational musculoskeletal modeling has been widely used as a powerful non-invasive tool to estimate them through inverse dynamics using static optimization, but the inherent computational complexity results in time-consuming analysis. In this paper, we propose a knowledge-based deep learning framework for time-efficient inverse dynamic analysis, which can predict muscle activation and muscle forces from joint kinematic data directly while not requiring any label information during model training. The Bidirectional Gated Recurrent Unit (BiGRU) neural network is selected as the backbone of our model due to its proficient handling of time-series data. Prior physical knowledge from forward dynamics and pre-selected inverse dynamics based physiological criteria are integrated into the loss function to guide the training of neural networks. Experimental validations on two datasets, including one benchmark upper limb movement dataset and one self-collected lower limb movement dataset from six healthy subjects, are performed. The experimental results have shown that the selected BiGRU architecture outperforms other neural network models when trained using our specifically designed loss function, which illustrates the effectiveness and robustness of the proposed framework. |
| format | Article |
| id | doaj-art-2758944b037c476bbd07660b8dd9457c |
| institution | Kabale University |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-2758944b037c476bbd07660b8dd9457c2025-01-28T00:00:15ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-013352253110.1109/TNSRE.2025.353099210844911Knowledge-Based Deep Learning for Time-Efficient Inverse DynamicsShuhao Ma0https://orcid.org/0009-0008-4808-1221Yu Cao1https://orcid.org/0000-0002-3486-5518Ian D. Robertson2https://orcid.org/0000-0003-1522-2071Chaoyang Shi3https://orcid.org/0000-0002-9065-9057Jindong Liu4Zhi-Qiang Zhang5https://orcid.org/0000-0003-0204-3867School of Electronic and Electrical Engineering, University of Leeds, Leeds, U.K.School of Electronic and Electrical Engineering, University of Leeds, Leeds, U.K.School of Electronic and Electrical Engineering, University of Leeds, Leeds, U.K.Key Laboratory of Mechanism Theory and Equipment Design of Ministry of Education, School of Mechanical Engineering, Tianjin University, Tianjin, ChinaEstun Medical Ltd., Nanjing, ChinaSchool of Electronic and Electrical Engineering, University of Leeds, Leeds, U.K.Accurate understanding of muscle activation and muscle forces plays an essential role in neuro-rehabilitation and musculoskeletal disorder treatments. Computational musculoskeletal modeling has been widely used as a powerful non-invasive tool to estimate them through inverse dynamics using static optimization, but the inherent computational complexity results in time-consuming analysis. In this paper, we propose a knowledge-based deep learning framework for time-efficient inverse dynamic analysis, which can predict muscle activation and muscle forces from joint kinematic data directly while not requiring any label information during model training. The Bidirectional Gated Recurrent Unit (BiGRU) neural network is selected as the backbone of our model due to its proficient handling of time-series data. Prior physical knowledge from forward dynamics and pre-selected inverse dynamics based physiological criteria are integrated into the loss function to guide the training of neural networks. Experimental validations on two datasets, including one benchmark upper limb movement dataset and one self-collected lower limb movement dataset from six healthy subjects, are performed. The experimental results have shown that the selected BiGRU architecture outperforms other neural network models when trained using our specifically designed loss function, which illustrates the effectiveness and robustness of the proposed framework.https://ieeexplore.ieee.org/document/10844911/Musculoskeletal modelinverse dynamicsknowledge-based deep learning |
| spellingShingle | Shuhao Ma Yu Cao Ian D. Robertson Chaoyang Shi Jindong Liu Zhi-Qiang Zhang Knowledge-Based Deep Learning for Time-Efficient Inverse Dynamics IEEE Transactions on Neural Systems and Rehabilitation Engineering Musculoskeletal model inverse dynamics knowledge-based deep learning |
| title | Knowledge-Based Deep Learning for Time-Efficient Inverse Dynamics |
| title_full | Knowledge-Based Deep Learning for Time-Efficient Inverse Dynamics |
| title_fullStr | Knowledge-Based Deep Learning for Time-Efficient Inverse Dynamics |
| title_full_unstemmed | Knowledge-Based Deep Learning for Time-Efficient Inverse Dynamics |
| title_short | Knowledge-Based Deep Learning for Time-Efficient Inverse Dynamics |
| title_sort | knowledge based deep learning for time efficient inverse dynamics |
| topic | Musculoskeletal model inverse dynamics knowledge-based deep learning |
| url | https://ieeexplore.ieee.org/document/10844911/ |
| work_keys_str_mv | AT shuhaoma knowledgebaseddeeplearningfortimeefficientinversedynamics AT yucao knowledgebaseddeeplearningfortimeefficientinversedynamics AT iandrobertson knowledgebaseddeeplearningfortimeefficientinversedynamics AT chaoyangshi knowledgebaseddeeplearningfortimeefficientinversedynamics AT jindongliu knowledgebaseddeeplearningfortimeefficientinversedynamics AT zhiqiangzhang knowledgebaseddeeplearningfortimeefficientinversedynamics |