EUVIMEDEUVIMED entdecken
Crossref

A deep learning approach for predicting sensory-motor integration in postural stability

Seungheon Chae, Jung Mee Park, Ahnryul Choi, Joung Hwan Mun

Medical & Biological Engineering & Computing · 2026-06 · 64 (6) · 2115-2131

DOI: 10.1007/s11517-026-03567-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, online erschienen am 13.04.2026. Verfasst von Seungheon Chae und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bio-Mechatronic Engineering, College of Biotechnology and Bioengineering, Sungkyunkwan University, Seoul, South Korea. Hauptthemen laut MEDLINE: Deep Learning, Postural Balance. Die Arbeit nennt 51 Literaturangaben. Gefördert von: National Research Foundation of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To maintain postural stability, reliable sensory input and appropriate motor responses are essential. In this study, a novel deep learning approach was proposed to evaluate postural stability by estimating sensory input capabilities (equilibrium score) and corresponding motor responses (movement strategy) from standing center of pressure (COP) signals. The model inputs were COP signals from quiet standing, with short-time Fourier transform (STFT) and wavelet transform (WT) employed as feature extraction methods. The models included GoogleNet and residual attention network (RAN) architectures, with feature distribution smoothing (FDS) applied to mitigate performance degradation caused by class imbalance in the target data. The starting point and bin number for FDS were incorporated as design parameters, with the mean squared error serving as the cost function during the hyperparameter optimization process. The STFT + RAN + FDS model achieved average errors of 0.89 for the equilibrium score and 0.72 for the movement strategy, demonstrating improvements of approximately 48% and 38% compared to the WT + RAN and STFT + RAN models, respectively. The proposed approach effectively predicts postural stability by leveraging COP signal features and advanced model architectures. It holds potential as a cost-effective and accessible solution for addressing postural stability issues, particularly for the growing population of patients with dizziness disorders.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPostural BalanceHumansSignal Processing, Computer-AssistedFourier AnalysisWavelet Analysis

Stichwörter der Autor:innen

Balance DisordersCenter of PressureDeep learningFrequency analysisPostural stability

Autor:innen und Institutionen

  • Department of Bio-Mechatronic Engineering, College of Biotechnology and Bioengineering, Sungkyunkwan University, Seoul, South Korea.
  • Department of Otorhinolaryngology-Head and Neck Surgery, Gangneung Asan Hospital, University of Ulsan College of Medicine, Gangneung-si, Gangwon-do, 25440, South Korea.
  • Department of Biomedical Engineering, College of Medicine, Chungbuk National University, Cheongju, South Korea. achoi@chungbuk.ac.kr.
  • Department of Bio-Mechatronic Engineering, College of Biotechnology and Bioengineering, Sungkyunkwan University, Seoul, South Korea. jmun@skku.edu.

Förderung

  • National Research Foundation of Korea

Zitieren

APA

Chae, S., Park, J. M., Choi, A., & Mun, J. H. (2026). A deep learning approach for predicting sensory-motor integration in postural stability. Medical & Biological Engineering & Computing, 64(6), 2115-2131. https://doi.org/10.1007/s11517-026-03567-3

Vancouver

Chae S, Park JM, Choi A, Mun JH. A deep learning approach for predicting sensory-motor integration in postural stability. Medical & Biological Engineering & Computing. 2026;64(6):2115-2131. doi:10.1007/s11517-026-03567-3

BibTeX
@article{Chae2026,
  author = {Chae, Seungheon and Park, Jung Mee and Choi, Ahnryul and Mun, Joung Hwan},
  title = {A deep learning approach for predicting sensory-motor integration in postural stability},
  journal = {Medical & Biological Engineering & Computing},
  year = {2026},
  volume = {64},
  number = {6},
  pages = {2115--2131},
  doi = {10.1007/s11517-026-03567-3}
}
Kostenlos starten →