EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Activity Recognition After Stroke: Generative Adversarial Networks for Kinematic Data Augmentation

Aaron J Hadley iD, Christopher L Pulliam iD

Sensors · 25.10.2024 · 24 (21) · 6861

DOI: 10.3390/s24216861 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.10.2024. Verfasst von Aaron J Hadley und 1 weiteren Autor:innen. Beteiligte Einrichtung: Hadley Research, LLC, South Euclid, OH 44121, USA. Hauptthemen laut MEDLINE: Stroke Rehabilitation, Stroke. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Case Western Reserve University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The generalizability of machine learning (ML) models for wearable monitoring in stroke rehabilitation is often constrained by the limited scale and heterogeneity of available data. Data augmentation addresses this challenge by adding computationally derived data to real data to enrich the variability represented in the training set. Traditional augmentation methods, such as rotation, permutation, and time-warping, have shown some benefits in improving classifier performance, but often fail to produce realistic training examples. This study employs Conditional Generative Adversarial Networks (cGANs) to create synthetic kinematic data from a publicly available dataset, closely mimicking the experimentally measured reaching movements of stroke survivors. This approach not only captures the complex temporal dynamics and common movement patterns after stroke, but also significantly enhances the training dataset. By training deep learning models on both synthetic and experimental data, we enhanced task classification accuracy: models incorporating synthetic data attained an overall accuracy of 80.0%, significantly higher than the 66.1% seen in models trained solely with real data. These improvements allow for more precise task classification, offering clinicians the potential to monitor patient progress more accurately and tailor rehabilitation interventions more effectively.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Stroke RehabilitationStrokeHumansBiomechanical PhenomenaNeural Networks, ComputerMachine LearningWearable Electronic DevicesMovementDeep LearningAlgorithms

Stichwörter der Autor:innen

data augmentationdeep learninggenerative adversarial networksmachine learningstrokewearable health monitoring systems

Autor:innen und Institutionen

  • Hadley Research, LLC, South Euclid, OH 44121, USA.
  • Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH 44106, USA.
  • Louis Stokes Cleveland Department of Veterans Affairs Medical Center, Cleveland, OH 44106, USA.

ORCID-Profile: Aaron J Hadley, Christopher L Pulliam

Förderung

  • Case Western Reserve University

Zitieren

APA

Hadley, A. J., & Pulliam, C. L. (2024). Enhancing Activity Recognition After Stroke: Generative Adversarial Networks for Kinematic Data Augmentation. Sensors, 24(21), 6861. https://doi.org/10.3390/s24216861

Vancouver

Hadley AJ, Pulliam CL. Enhancing Activity Recognition After Stroke: Generative Adversarial Networks for Kinematic Data Augmentation. Sensors. 2024;24(21):6861. doi:10.3390/s24216861

BibTeX
@article{Hadley2024,
  author = {Hadley, Aaron J and Pulliam, Christopher L},
  title = {Enhancing Activity Recognition After Stroke: Generative Adversarial Networks for Kinematic Data Augmentation},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {21},
  pages = {6861},
  doi = {10.3390/s24216861}
}
Kostenlos starten →