Self-Supervised Learning Improves Accuracy and Data Efficiency for IMU-Based Ground Reaction Force Estimation
IEEE Transactions on Biomedical Engineering · 2024-07 · 71 (7) · 2095-2104
DOI: 10.1109/tbme.2024.3361888 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Engineering, 2024-07. Verfasst von Tian Tan und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Supervised Machine Learning. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIBIB NIH HHS, NIAMS NIH HHS, NICHD NIH HHS.
Abstract (Originalsprache)
OBJECTIVE: Recent deep learning techniques hold promise to enable IMU-driven kinetic assessment; however, they require large extents of ground reaction force (GRF) data to serve as labels for supervised model training. We thus propose using existing self-supervised learning (SSL) techniques to leverage large IMU datasets to pre-train deep learning models, which can improve the accuracy and data efficiency of IMU-based GRF estimation. METHODS: We performed SSL by masking a random portion of the input IMU data and training a transformer model to reconstruct the masked portion. We systematically compared a series of masking ratios across three pre-training datasets that included real IMU data, synthetic IMU data, or a combination of the two. Finally, we built models that used pre-training and labeled data to estimate GRF during three prediction tasks: overground walking, treadmill walking, and drop landing. RESULTS: When using the same amount of labeled data, SSL pre-training significantly improved the accuracy of 3-axis GRF estimation during walking compared to baseline models trained by conventional supervised learning. Fine-tuning SSL model with 1-10% of walking data yielded comparable accuracy to training baseline model with 100% of walking data. The optimal masking ratio for SSL is 6.25-12.5%. CONCLUSION: SSL leveraged large real and synthetic IMU datasets to increase the accuracy and data efficiency of deep-learning-based GRF estimation, reducing the need for labeled data. SIGNIFICANCE: This work, with its open-source code and models, may unlock broader use cases of IMU-driven kinetic assessment by mitigating the scarcity of GRF measurements in practical applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- NIBIB NIH HHS
- NIAMS NIH HHS
- NICHD NIH HHS
- Joe and Clara Tsai Foundation
- Wu Tsai Human Performance Alliance
- National Institutes of Health
- National Natural Science Foundation of China
Zitieren
APA
Tan, T., Shull, P. B., Hicks, J. L., Uhlrich, S. D., & Chaudhari, A. S. (2024). Self-Supervised Learning Improves Accuracy and Data Efficiency for IMU-Based Ground Reaction Force Estimation. IEEE Transactions on Biomedical Engineering, 71(7), 2095-2104. https://doi.org/10.1109/tbme.2024.3361888
Vancouver
Tan T, Shull PB, Hicks JL, Uhlrich SD, Chaudhari AS. Self-Supervised Learning Improves Accuracy and Data Efficiency for IMU-Based Ground Reaction Force Estimation. IEEE Transactions on Biomedical Engineering. 2024;71(7):2095-2104. doi:10.1109/tbme.2024.3361888
BibTeX
@article{Tan2024,
author = {Tan, Tian and Shull, Peter B and Hicks, Jenifer L and Uhlrich, Scott D and Chaudhari, Akshay S},
title = {Self-Supervised Learning Improves Accuracy and Data Efficiency for IMU-Based Ground Reaction Force Estimation},
journal = {IEEE Transactions on Biomedical Engineering},
year = {2024},
volume = {71},
number = {7},
pages = {2095--2104},
doi = {10.1109/tbme.2024.3361888}
}
EUVIMED