EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Tactile Sensor-Based Body Center of Pressure Estimation System Using Supervised Deep Learning Models

Jaehyeon Baik iD, Yunho Choi, Kyung-Joong Kim, Young Jin Park iD, Hosu Lee

Sensors · 2026

DOI: 10.3390/s26010286 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Jaehyeon Baik und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Control and Robot Engineering, Gyeongsang National University, Jinju 52828, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Touch. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The center of pressure (CoP) is a key biomechanical indicator for assessing balance and fall risk; however, force plates, the gold standard for CoP measurement, are costly and impractical for widespread use. Low-cost alternatives such as inertial units or pressure sensors are limited by drift, sparse sensor coverage, and directional performance imbalances, with previous supervised learning approaches reporting ML-AP NRMSE differences of 3.2–4.7% using 1D time-series models on sparse sensor arrays. Therefore, we propose a tactile sensor-based CoP estimation system using deep learning models that can extract 2D spatial features from each pressure distribution image with CNN/ResNet encoders followed by a Bi-LSTM for temporal patterns. Using data from 23 healthy adults performing four balance protocols, we compared ResNet-Bi-LSTM and CNN-Bi-LSTM with baseline CNN-LSTM and Bi-LSTM models used in previous studies. Model performance was validated using leave-one-out cross-validation (LOOCV) and evaluated with RMSE, NRMSE, and R2. The ResNet-Bi-LSTM with angular features achieved the best performance, with RMSE values of 18.63 ± 4.57 mm in the mediolateral (ML) direction and 17.65 ± 3.48 mm in the anteroposterior (AP) direction, while reducing the ML/AP NRMSE difference to 1.3% compared to 3.2–4.7% in previous studies. Under dynamic protocols, ResNet-Bi-LSTM maintained the lowest RMSE across models. These findings suggest that tactile sensor-based systems may provide a cost-effective alternative to force plates and hold potential for applications in gait analysis and real-time balance monitoring. Future work will validate clinical applicability in patient populations and explore real-time implementation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningTouchHumansPressureConvolutional Neural NetworksPostural BalanceAdultSupervised Machine LearningBiomechanical Phenomena

Stichwörter der Autor:innen

CNN-Bi-LSTMResNet-Bi-LSTMbalancecenter of pressureestimationsupervised learningtactile sensor

Autor:innen und Institutionen

  • Department of Control and Robot Engineering, Gyeongsang National University, Jinju 52828, Republic of Korea.
  • Department of Electrical and Computer Engineering, University of Washington, Seattle, WA 98195, USA.
  • Department of AI Convergence, College of Information and Computing, Gwangju Institute of Science and Technology, Gwangju 61005, Republic of Korea.
  • School of Mechanical Engineering, Gyeongsang National University, Jinju 52828, Republic of Korea.
  • Gyeongnam Aerospace & Defence Institute of Science and Technology, Gyeongsang National University, Jinju 52828, Republic of Korea.

ORCID-Profile: Jaehyeon Baik, Young Jin Park

Zitieren

APA

Baik, J., Choi, Y., Kim, K. J., Park, Y. J., & Lee, H. (2026). Tactile Sensor-Based Body Center of Pressure Estimation System Using Supervised Deep Learning Models. Sensors. https://doi.org/10.3390/s26010286

Vancouver

Baik J, Choi Y, Kim KJ, Park YJ, Lee H. Tactile Sensor-Based Body Center of Pressure Estimation System Using Supervised Deep Learning Models. Sensors. 2026. doi:10.3390/s26010286

BibTeX
@article{Baik2026,
  author = {Baik, Jaehyeon and Choi, Yunho and Kim, Kyung-Joong and Park, Young Jin and Lee, Hosu},
  title = {Tactile Sensor-Based Body Center of Pressure Estimation System Using Supervised Deep Learning Models},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26010286}
}
Kostenlos starten →