EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Estimation of 3D Ground Reaction Force and 2D Center of Pressure Using Deep Learning and Load Cells Across Various Gait Conditions

Junggil Kim, Ki-Cheon Kim, Gyerae Tack, Jin-Seung Choi iD

Sensors · 2025

DOI: 10.3390/s25113357 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Junggil Kim und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Konkuk University, Chungju 27478, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Gait. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation, Korea Health Industry Development Institute, National Research Foundation of Korea (NRF).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional force plate-based systems offer high measurement precision but are limited to laboratory settings, restricting their use in real-world environments. To address this, we propose a method for estimating a three-axis ground reaction force (GRF) and two-axis center of pressure (CoP) using a shoe embedded with three uniaxial load cells. The estimation was conducted under five gait conditions: straight walking, turning, uphill, downhill, and running. Data were collected from 40 healthy young adults. Four deep-learning models—Fully Connected Neural Network (FCNN), Convolutional Neural Network (CNN), Sequence-to-Sequence Long Short-Term Memory (Seq2Seq-LSTM), and Transformer—were evaluated. Among them, Seq2Seq-LSTM and CNN achieved the highest performance in predicting both GRF and CoP. However, the medio-lateral (ML) components showed lower accuracy than the vertical and anterior–posterior directions. In slope conditions, particularly for vertical GRF, relatively higher root mean-square error (RMSE) values were observed. Despite some variation across gait types, predicted values showed high agreement with measurements. Compared with previous studies, the proposed method achieved comparable or better performance with a minimal sensor setup. These findings highlight the feasibility of accurate GRF and CoP estimation in diverse gait scenarios and support the potential for real-world applications. Future work will focus on sensor optimization and broader population validation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGaitAdultFemaleHumansMaleYoung AdultBiomechanical PhenomenaPressureRunningShoesWalking

Stichwörter der Autor:innen

center of pressuredeep learningestimationgaitground reaction forceload cell

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Konkuk University, Chungju 27478, Republic of Korea.
  • BK21 Plus Research Institute of Biomedical Engineering, Konkuk University, Chungju 27478, Republic of Korea.

ORCID-Profile: Jin-Seung Choi

Förderung

  • National Research Foundation
  • Korea Health Industry Development Institute
  • National Research Foundation of Korea (NRF)

Zitieren

APA

Kim, J., Kim, K. C., Tack, G., & Choi, J. S. (2025). Estimation of 3D Ground Reaction Force and 2D Center of Pressure Using Deep Learning and Load Cells Across Various Gait Conditions. Sensors. https://doi.org/10.3390/s25113357

Vancouver

Kim J, Kim KC, Tack G, Choi JS. Estimation of 3D Ground Reaction Force and 2D Center of Pressure Using Deep Learning and Load Cells Across Various Gait Conditions. Sensors. 2025. doi:10.3390/s25113357

BibTeX
@article{Kim2025,
  author = {Kim, Junggil and Kim, Ki-Cheon and Tack, Gyerae and Choi, Jin-Seung},
  title = {Estimation of 3D Ground Reaction Force and 2D Center of Pressure Using Deep Learning and Load Cells Across Various Gait Conditions},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25113357}
}
Kostenlos starten →