Individual Variability in Deep Learning-Based Joint Angle Estimation from a Single IMU: A Cross-Population Study
Sensors · 2025
DOI: 10.3390/s26010178 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Koyo Toyoshima und 4 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Science and Engineering, Ehime University, Bunkyo-cho 3, Matsuyama 790-8577, Ehime, Japan. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
Walking ability is crucial for maintaining independence and healthy aging. Although joint angle measurement is important for detailed gait assessment, it is rarely performed in clinical practice due to the complexity of motion capture systems. This study investigates individual variability and cross-population generalizability of deep learning-based joint angle estimation from a single inertial measurement unit (IMU) attached to the pelvis. Gait data from three distinct populations were collected: 17 young adults, 20 healthy older adults (aged 65+), and 14 pre-operative patients scheduled for hip replacement surgery due to hip osteoarthritis (also aged 65+). A 1D ResNet-based convolutional neural network was trained to estimate bilateral hip, knee, and ankle joint angles from IMU signals. We systematically compared within-population training (trained and tested on the same population) with cross-population training (trained on combined data from all populations) using nested 5-fold cross-validation. Cross-population training showed population-specific effectiveness: older adults demonstrated consistent improvement, while young adults showed minimal change due to already high baseline performance, and pre-operative patients exhibited highly variable responses. These findings suggest that the effectiveness of cross-population learning depends on within-population gait heterogeneity, with important implications for developing clinically applicable gait analysis systems across diverse patient populations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate School of Science and Engineering, Ehime University, Bunkyo-cho 3, Matsuyama 790-8577, Ehime, Japan.
- Graduate School of Medicine, Ehime University, Shitsukawa, Toon 791-0295, Ehime, Japan.
- Rehabilitation Center, Ehime University Hospital, Shitsukawa, Toon 791-0295, Ehime, Japan.
ORCID-Profile: Koyo Toyoshima, Jae Hoon Lee
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Toyoshima, K., Lee, J. H., Kogami, S., Miyaki, T., & Manabe, T. (2025). Individual Variability in Deep Learning-Based Joint Angle Estimation from a Single IMU: A Cross-Population Study. Sensors. https://doi.org/10.3390/s26010178
Vancouver
Toyoshima K, Lee JH, Kogami S, Miyaki T, Manabe T. Individual Variability in Deep Learning-Based Joint Angle Estimation from a Single IMU: A Cross-Population Study. Sensors. 2025. doi:10.3390/s26010178
BibTeX
@article{Toyoshima2025,
author = {Toyoshima, Koyo and Lee, Jae Hoon and Kogami, Shigeru and Miyaki, Teppei and Manabe, Toru},
title = {Individual Variability in Deep Learning-Based Joint Angle Estimation from a Single IMU: A Cross-Population Study},
journal = {Sensors},
year = {2025},
doi = {10.3390/s26010178}
}
EUVIMED