EUVIMEDEUVIMED entdecken
Crossref

Estimating Dynamic Plantar Pressure Distribution from Wearable Inertial Sensors Using a Hybrid CNN-BiLSTM Architecture

Yihan Qian, Dong Sun, Zifan Xia, Enze Shao, Yang Song, József Sárosi, István Bíró, Zixiang Gao, Yaodong Gu

Acta of Bioengineering and Biomechanics · 20.08.2025 · 27 (2) · 211-227

DOI: 10.37190/abb/207865 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Acta of Bioengineering and Biomechanics, online erschienen am 03.07.2025. Verfasst von Yihan Qian und 8 weiteren Autor:innen. Beteiligte Einrichtung: 1Faculty of Sports Science, Ningbo University, Ningbo, China. Hauptthemen laut MEDLINE: Wearable Electronic Devices, Foot, Pressure, Neural Networks, Computer. Die Arbeit wurde bisher 9-mal zitiert (Crossref).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Plantar pressure distribution is a crucial indicator in gait analysis, with significant value in clinical diagnoses and sports optimization. Traditional measurement methods, however, are often limited by expensive equipment and laboratory settings. This study aimed to develop an accurate, portable, and cost-effective method using a deep learning model based on data from wearable Inertial Measurement Units to predict comprehensive plantar pressure distributions.

Methods

This study aims to develop a portable deep learning model based on Inertial Measurement Units data to predict plantar pressure distribution. We propose a model that combines Convolutional Neural Network and Bidirectional Long Short-Term Memory, where Convolutional Neural Network extracts local features from Inertial Measurement Units data, Bidirectional Long Short-Term Memory captures the temporal dependencies of the gait cycle, an attention mechanism optimizes the prediction of key time steps, and body weight information is integrated to accommodate individual differences.

Results

Experimental results show that in 10-fold cross-validation, the model achieves a Mean Squared Error of 0.98 and a Structural Similarity Index of 0.89, demonstrating excellent prediction accuracy and distribution similarity.

Conclusions

This study provides a cost-effective method for plantar pressure analysis, which is expected to be integrated into wearable devices for real-time gait monitoring, with applications in rehabilitation and sports optimization.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Wearable Electronic DevicesFootPressureNeural Networks, ComputerHumansMaleGaitAdultFemaleBiomechanical Phenomena

Stichwörter der Autor:innen

CNNIMULSTMattention mechanismplantar pressure

Autor:innen und Institutionen

  • 1Faculty of Sports Science, Ningbo University, Ningbo, China.
  • 2Doctoral School on Safety and Security Sciences, Óbuda University, Budapest, Hungary.
  • 3Department of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong, China.
  • 4Faculty of Engineering, University of Szeged, Szeged, Hungary.
  • 5Human Performance Laboratory, Faculty of Kinesiology, University of Calgary, Calgary, Canada.

Zitieren

APA

Qian, Y., Sun, D., Xia, Z., Shao, E., Song, Y., Sárosi, J., Bíró, I., Gao, Z., & Gu, Y. (2025). Estimating Dynamic Plantar Pressure Distribution from Wearable Inertial Sensors Using a Hybrid CNN-BiLSTM Architecture. Acta of Bioengineering and Biomechanics, 27(2), 211-227. https://doi.org/10.37190/abb/207865

Vancouver

Qian Y, Sun D, Xia Z, Shao E, Song Y, Sárosi J, et al. Estimating Dynamic Plantar Pressure Distribution from Wearable Inertial Sensors Using a Hybrid CNN-BiLSTM Architecture. Acta of Bioengineering and Biomechanics. 2025;27(2):211-227. doi:10.37190/abb/207865

BibTeX
@article{Qian2025,
  author = {Qian, Yihan and Sun, Dong and Xia, Zifan and Shao, Enze and Song, Yang and Sárosi, József and Bíró, István and Gao, Zixiang and Gu, Yaodong},
  title = {Estimating Dynamic Plantar Pressure Distribution from Wearable Inertial Sensors Using a Hybrid CNN-BiLSTM Architecture},
  journal = {Acta of Bioengineering and Biomechanics},
  year = {2025},
  volume = {27},
  number = {2},
  pages = {211--227},
  doi = {10.37190/abb/207865}
}
Kostenlos starten →