Estimating ground reaction forces and moments during gait from multiple kinematic variables using a feedforward neural network
Technology and Health Care · 2026-03 · 34 (2) · 300-312
DOI: 10.1177/09287329251414523 ↗Kurz gefasst
Fachartikel in der Zeitschrift Technology and Health Care, online erschienen am 03.03.2026. Verfasst von Jeheon Moon und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physical Education, Korea National University of Education, Cheongju, Chungbuk, Republic of Korea. Hauptthemen laut MEDLINE: Gait, Gait Analysis, Neural Networks, Computer. Die Arbeit nennt 47 Literaturangaben. Gefördert von: Korea Institute of Oriental Medicine, National Research Foundation of Korea.
Abstract (Originalsprache)
Background
Ground reaction force (GRF) and ground reaction moment (GRM) are critical in gait analysis. While force plates provide accurate measurements, they are costly and spatially limiting.
Objective
This study aimed to evaluate the reliability and accuracy of GRF and GRM predictions using a feedforward neural network (FNN) integrating infrared camera-based positional data with accelerometer (ACC) data from wearable devices.
Methods
Eighty participants walked at their usual pace along a 10-meter walkway over force plates. Positional and ACC data of body segments were used to train the FNN to predict GRF and GRM. Prediction accuracy was assessed using multiple metrics, including root mean square error (RMSE) and normalized RMSE (NRMSE).
Results
Combining positional and ACC data improved GRF prediction in all directions (vertical, anterior-posterior, medial-lateral). The combined dataset achieved a correlation coefficient of 0.979 for medial-lateral GRF and an NRMSE of 6.07%. GRM predictions also benefited from ACC integration, especially in the sagittal plane, where R 2 reached 0.939, outperforming other models. The vertical direction and transverse axis yielded the lowest RMSE and NRMSE.
Conclusions
These findings surpass many previously reported results, demonstrating the superior performance of the proposed model compared with current state-of-the-art methods. The approach offers a cost-effective, flexible alternative to traditional force plates for clinical and sports assessments.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Physical Education, Korea National University of Education, Cheongju, Chungbuk, Republic of Korea.
- Department of Sport Science, Korea Institute of Sports Science, Seoul, Republic of Korea.
- Department of Human Performance and Health Education, Western Michigan University, Kalamazoo, MI, USA.
- Department of Computer Engineering, Keimyung University, Daegu, Republic of Korea.
- Digital Health Research Division, Korea Institute of Oriental Medicine, Daejeon, Republic of Korea.
- Department of Lifesports Education, Kongju National University, Gongju, Chungnam, Republic of Korea.
ORCID-Profile: Sungmin Kim
Förderung
- Korea Institute of Oriental Medicine
- National Research Foundation of Korea
Zitieren
APA
Moon, J., Kim, T., Lee, S., Ruiz Sanchez, G. A., Seo, J., & Kim, S. (2026). Estimating ground reaction forces and moments during gait from multiple kinematic variables using a feedforward neural network. Technology and Health Care, 34(2), 300-312. https://doi.org/10.1177/09287329251414523
Vancouver
Moon J, Kim T, Lee S, Ruiz Sanchez GA, Seo J, Kim S. Estimating ground reaction forces and moments during gait from multiple kinematic variables using a feedforward neural network. Technology and Health Care. 2026;34(2):300-312. doi:10.1177/09287329251414523
BibTeX
@article{Moon2026,
author = {Moon, Jeheon and Kim, Taewhan and Lee, Sangwoo and Ruiz Sanchez, Gustavo Adrian and Seo, Jeongwoo and Kim, Sungmin},
title = {Estimating ground reaction forces and moments during gait from multiple kinematic variables using a feedforward neural network},
journal = {Technology and Health Care},
year = {2026},
volume = {34},
number = {2},
pages = {300--312},
doi = {10.1177/09287329251414523}
}
EUVIMED