EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Diff-MomentFormer: Generative Diffusion-Augmented Transformer for End-to-End Joint Moment Estimation

Chengyu Qiao iD, Eryun Liu, Jingwei Ren, Long He

Sensors · 08.05.2026 · 26 (10) · 2944

DOI: 10.3390/s26102944 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 08.05.2026. Verfasst von Chengyu Qiao und 3 weiteren Autor:innen. Beteiligte Einrichtung: The College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China. Hauptthemen laut MEDLINE: Knee Joint, Hip Joint, Joints. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang Provincial Natural Science Foundation, Zhejiang Provincial Postdoctoral Science Foundation, “Pioneer” and “Leading Goose” R&D Program of Zhejiang.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate estimation of human joint moments from multimodal sensor signals is essential for lower-limb exoskeleton control. Recent studies have addressed this problem in an end-to-end manner, but remain limited by insufficient long-range temporal modeling, limited training data, and class imbalance. To address these issues, we propose Diff-MomentFormer, a generative diffusion-augmented Transformer framework for end-to-end joint moment estimation from multimodal wearable sensor signals. The framework integrates a classifier-free conditional diffusion model for activity-conditioned synthetic data generation, together with a Transformer-based regression network for modeling long-range temporal dependencies and cross-modal interactions. Through the combination of controllable data augmentation and global temporal modeling, Diff-MomentFormer can learn more robust multimodal representations for accurate and stable joint moment estimation. Extensive experiments on a public lower-limb biomechanics dataset show that the proposed method consistently improves hip and knee joint moment estimation performance across different activity categories, while ablation studies further confirm the effectiveness of the proposed framework.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Knee JointHip JointJointsHumansBiomechanical PhenomenaAlgorithmsExoskeleton DeviceWearable Electronic Devices

Stichwörter der Autor:innen

Transformerclassifier-free conditional diffusionjoint moment estimationlower-limb exoskeletonmultimodal sensor fusion

Autor:innen und Institutionen

  • The College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China.
  • Hangzhou Zhiyuan Research Institute, Hangzhou 310012, China.

ORCID-Profile: Chengyu Qiao

Förderung

  • Zhejiang Provincial Natural Science Foundation
  • Zhejiang Provincial Postdoctoral Science Foundation
  • “Pioneer” and “Leading Goose” R&D Program of Zhejiang
  • National Natural Science Foundation Program of China
  • National Key Laboratory of Collective Intelligence & Collaboration

Zitieren

APA

Qiao, C., Liu, E., Ren, J., & He, L. (2026). Diff-MomentFormer: Generative Diffusion-Augmented Transformer for End-to-End Joint Moment Estimation. Sensors, 26(10), 2944. https://doi.org/10.3390/s26102944

Vancouver

Qiao C, Liu E, Ren J, He L. Diff-MomentFormer: Generative Diffusion-Augmented Transformer for End-to-End Joint Moment Estimation. Sensors. 2026;26(10):2944. doi:10.3390/s26102944

BibTeX
@article{Qiao2026,
  author = {Qiao, Chengyu and Liu, Eryun and Ren, Jingwei and He, Long},
  title = {Diff-MomentFormer: Generative Diffusion-Augmented Transformer for End-to-End Joint Moment Estimation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {2944},
  doi = {10.3390/s26102944}
}
Kostenlos starten →