Self-supervised learning enhances accuracy and data efficiency in lower-limb joint moment estimation from gait kinematics
This study demonstrates that self-supervised learning significantly improves the accuracy and data efficiency of joint moment estimation, providing a more efficient solution for biomechanical evaluation. The proposed model can reduce the burden of collecting data and expand clinical applications.
Authors
- Maria Fasli (ORCID: https://orcid.org/0000-0001-8831-102X)
- Behnam Gholami (ORCID: https://orcid.org/0000-0003-0338-1921)
- Jiayu He (ORCID: https://orcid.org/0000-0002-1329-7312)
- Xiaojun Zhai (ORCID: https://orcid.org/0000-0002-1030-8311)
- Qichang Mei (ORCID: https://orcid.org/0000-0003-1113-877X)
- Bernard X. W. Liew (ORCID: https://orcid.org/0000-0002-7057-7548)
- Klaus D. McDonald-Maier (ORCID: https://orcid.org/0000-0002-6412-8519)
- David Hollinger (ORCID: https://orcid.org/0000-0003-0689-9531)
- Yifan Li (ORCID: https://orcid.org/0009-0003-4790-1711)
Institutions
- Ningbo University (CN)
- University of Essex (GB)
- King's College London (GB)
Publication Details
- Journal
- Frontiers in Bioengineering and Biotechnology
- Published
- 2025-09-24
- DOI
- https://doi.org/10.3389/fbioe.2025.1633513
- Primary Topic
- Gait Recognition and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Medical Research Council
- Engineering and Physical Sciences Research Council