EUVIMEDScopri EUVIMED
Open access

Autoencoder-Enhanced Convolutional Neural Networks for Plantar Pressure–Based Gait Pattern Recognition: Model Development and Cross-Validated Evaluation Study

Chuan-Chun Chang iD, Chi-Wen Lung iD, Yih-Kuen Jan iD, Qi-Qian Lu iD, Yi-You Wang iD, Yi-Sheng Chen iD, Ben-Yi Liau iD

JMIR Formative Research · 2026

DOI: 10.2196/88488 ↗

At a glance

Journal article in JMIR Formative Research, 2026. Written by Chuan-Chun Chang and 6 co-authors. Institution: Department of Automatic Control Engineering, Feng Chia University, Taichung, Taiwan. Major MEDLINE topics: Gait, Foot, Pattern Recognition, Automated. Cited 2 times so far (Crossref); 18 references. The full text is freely available in PubMed Central.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

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.

Subjects

MeSH terms (MEDLINE)

GaitFootPattern Recognition, AutomatedHumansConvolutional Neural NetworksAutoencoderFemaleMaleYoung AdultAdolescentPressureNeural Networks, Computer

Author keywords

autoencoderbiomedical engineeringconvolutional neural networksdeep learninggaitmachine learningplantar pressurewearable sensors

Authors and institutions

  • 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 profiles: Chuan-Chun Chang, Chi-Wen Lung, Yih-Kuen Jan, Qi-Qian Lu, Yi-You Wang, Yi-Sheng Chen, Ben-Yi Liau

Cite

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}
}
Start for free →