Autoencoder-Enhanced Convolutional Neural Networks for Plantar Pressure–Based Gait Pattern Recognition: Model Development and Cross-Validated Evaluation Study
JMIR Formative Research · 2026
DOI: 10.2196/88488 ↗Kurz gefasst
Fachartikel in der Zeitschrift JMIR Formative Research, 2026. Verfasst von Chuan-Chun Chang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Automatic Control Engineering, Feng Chia University, Taichung, Taiwan. Hauptthemen laut MEDLINE: Gait, Foot, Pattern Recognition, Automated. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Plantar pressure imaging is a stable modality that reflects gait-related biomechanical characteristics and has been used increasingly for gait assessment and recognition. However, plantar pressure images are high dimensional and nonlinear, making manual feature engineering and conventional machine learning insufficient to capture discriminative patterns.
Objective
This study aimed to develop a gait pattern recognition model based on plantar pressure using an autoencoder (AE)-enhanced convolutional neural network (CNN) and to evaluate its performance against baseline deep learning and classical machine learning approaches.
Methods
A total of 13 healthy volunteers (aged 18-24 years) were recruited. Plantar pressure data were collected during treadmill walking using an in-shoe pressure measurement system and converted into frame-wise plantar pressure images. We compared a lightweight CNN (Light CNN), an AE-CNN cascade model, and an encoder-augmented CNN with an additional bottleneck layer. Model development used participant-wise data partitioning, and performance was evaluated using accuracy, precision, recall, and F1-score.
Results
The proposed encoder-augmented CNN achieved the best overall performance (F1-score=96.20%), outperforming the Light CNN (F1-score=94.44%) and AE-CNN cascade (F1-score=92.45%). Confusion matrices and learning curves further indicated stable training behavior and consistent classification performance across gait patterns.
Conclusions
Integrating representation learning (AE-based compression) with CNN-based classification improved the recognition of gait patterns from plantar pressure images. This pilot study included only healthy participants. Future work should validate generalizability in larger and clinically diverse cohorts and further investigate participant-level evaluation and model interpretability, as well as deployment feasibility.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Automatic Control Engineering, Feng Chia University, Taichung, Taiwan.
- Department of Creative Product Design, Asia University, Taichung, Taiwan.
- Rehabilitation Engineering Lab, Department of Health and Kinesiology, University of Illinois Urbana-Champaign, Urbana, IL, United States.
- Department of Communications Engineering, Feng Chia University, Taichung, Taiwan.
ORCID-Profile: Chuan-Chun Chang, Chi-Wen Lung, Yih-Kuen Jan, Qi-Qian Lu, Yi-You Wang, Yi-Sheng Chen, Ben-Yi Liau
Zitieren
APA
Chang, C. C., Lung, C. W., Jan, Y. K., Lu, Q. Q., Wang, Y. Y., Chen, Y. S., & Liau, B. Y. (2026). Autoencoder-Enhanced Convolutional Neural Networks for Plantar Pressure–Based Gait Pattern Recognition: Model Development and Cross-Validated Evaluation Study. JMIR Formative Research. https://doi.org/10.2196/88488
Vancouver
Chang CC, Lung CW, Jan YK, Lu QQ, Wang YY, Chen YS, et al. Autoencoder-Enhanced Convolutional Neural Networks for Plantar Pressure–Based Gait Pattern Recognition: Model Development and Cross-Validated Evaluation Study. JMIR Formative Research. 2026. doi:10.2196/88488
BibTeX
@article{Chang2026,
author = {Chang, Chuan-Chun and Lung, Chi-Wen and Jan, Yih-Kuen and Lu, Qi-Qian and Wang, Yi-You and Chen, Yi-Sheng and Liau, Ben-Yi},
title = {Autoencoder-Enhanced Convolutional Neural Networks for Plantar Pressure–Based Gait Pattern Recognition: Model Development and Cross-Validated Evaluation Study},
journal = {JMIR Formative Research},
year = {2026},
doi = {10.2196/88488}
}
EUVIMED