EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence

Carlo Dindorf, Jonas Dully, Jürgen Konradi, Claudia Wolf, Stephan Becker, Steven Simon, Janine Huthwelker, Frederike Werthmann, Johanna Kniepert, Philipp Drees, Ulrich Betz, Michael Fröhlich

Frontiers in Bioengineering and Biotechnology · 14.02.2024 · 12

DOI: 10.3389/fbioe.2024.1350135 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Bioengineering and Biotechnology, online erschienen am 14.02.2024. Verfasst von Carlo Dindorf und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Sports Science, University of Kaiserslautern-Landau, Kaiserslautern, Germany. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data.

Methods

Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation.

Results

Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples.

Conclusion

This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain.

Schlagwörter

Stichwörter der Autor:innen

data augmentationdeep learningmachine learningspinestatistical parametric mappingvariational autoencoder

Autor:innen und Institutionen

  • Department of Sports Science, University of Kaiserslautern-Landau, Kaiserslautern, Germany.
  • Institute of Physical Therapy, Prevention and Rehabilitation, University Medical Centre, Johannes Gutenberg University Mainz, Mainz, Germany.
  • Department of Orthopedics and Trauma Surgery, University Medical Centre, Johannes Gutenberg University Mainz, Mainz, Germany.

Zitieren

APA

Dindorf, C., Dully, J., Konradi, J., Wolf, C., Becker, S., Simon, S., Huthwelker, J., Werthmann, F., Kniepert, J., Drees, P., Betz, U., & Fröhlich, M. (2024). Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence. Frontiers in Bioengineering and Biotechnology, 12. https://doi.org/10.3389/fbioe.2024.1350135

Vancouver

Dindorf C, Dully J, Konradi J, Wolf C, Becker S, Simon S, et al. Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence. Frontiers in Bioengineering and Biotechnology. 2024;12. doi:10.3389/fbioe.2024.1350135

BibTeX
@article{Dindorf2024,
  author = {Dindorf, Carlo and Dully, Jonas and Konradi, Jürgen and Wolf, Claudia and Becker, Stephan and Simon, Steven and Huthwelker, Janine and Werthmann, Frederike and Kniepert, Johanna and Drees, Philipp and Betz, Ulrich and Fröhlich, Michael},
  title = {Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence},
  journal = {Frontiers in Bioengineering and Biotechnology},
  year = {2024},
  volume = {12},
  doi = {10.3389/fbioe.2024.1350135}
}
Kostenlos starten →