EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CNN-GRU-KAN: A Novel Multi-Branch Framework for Parkinson’s Disease Detection Based on Gait Classification

Xingkai Fu iD, Minlan Jiang iD, Mohammed A A Al-Qaness iD

Bioengineering · 10.08.2026 · 13 (8) · 905

DOI: 10.3390/bioengineering13080905 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 10.08.2026. Verfasst von Xingkai Fu und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua 321004, China. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Parkinson’s disease (PD) diagnosis and severity assessment increasingly rely on gait analysis. To capture complex gait dynamics from limited sensor data, we propose a novel multi-branch framework integrating a one-dimensional convolutional neural network (1D-CNN), a bidirectional gated recurrent unit (Bi-GRU), and Kolmogorov–Arnold networks (KANs) (CNN-GRU-KAN) utilizing 18-channel vertical ground reaction force (VGRF) signals. Each module serves a distinct clinical purpose: the 1D-CNN branch with squeeze-and-excitation (SE) attention extracts localized spatial plantar pressure patterns, while the Bi-GRU branch with temporal attention captures long-range rhythm abnormalities. Crucially, the KAN serves as the classification head. By utilizing learnable B-spline functions instead of traditional fixed activations, KAN adaptively models the highly non-linear boundaries between healthy controls and varying PD severities, effectively mitigating overfitting. Under rigorous subject-independent cross-validation, our model achieves 98.43% accuracy for binary PD detection and 93.46% for five-class UPDRS severity grading. These results highlight the framework’s strong potential for low-cost, unobtrusive clinical tracking and home monitoring.

Schlagwörter

Stichwörter der Autor:innen

Kolmogorov–Arnold networksParkinson’s diseasedeep learninggait classificationhealth informatics

Autor:innen und Institutionen

  • College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua 321004, China.
  • College of Engineering and Information Technology, Emirates International University, Sana'a 16881, Yemen.

ORCID-Profile: Xingkai Fu, Minlan Jiang, Mohammed A A Al-Qaness

Zitieren

APA

Fu, X., Jiang, M., & Al-Qaness, M. A. A. (2026). CNN-GRU-KAN: A Novel Multi-Branch Framework for Parkinson’s Disease Detection Based on Gait Classification. Bioengineering, 13(8), 905. https://doi.org/10.3390/bioengineering13080905

Vancouver

Fu X, Jiang M, Al-Qaness MAA. CNN-GRU-KAN: A Novel Multi-Branch Framework for Parkinson’s Disease Detection Based on Gait Classification. Bioengineering. 2026;13(8):905. doi:10.3390/bioengineering13080905

BibTeX
@article{Fu2026,
  author = {Fu, Xingkai and Jiang, Minlan and Al-Qaness, Mohammed A A},
  title = {CNN-GRU-KAN: A Novel Multi-Branch Framework for Parkinson’s Disease Detection Based on Gait Classification},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {8},
  pages = {905},
  doi = {10.3390/bioengineering13080905}
}
Kostenlos starten →