EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Assessing Low Back Movement with Motion Tape Sensor Data Through Deep Learning

Jared Levy iD, Aarti Lalwani iD, Elijah Wyckoff iD, Kenneth J Loh iD, Sara P Gombatto iD, Rose Yu iD, Emilia Farcas iD

Sensors · 2026

DOI: 10.3390/s26041127 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Jared Levy und 6 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science and Engineering, University of California San Diego, La Jolla, CA 92093, USA. Hauptthemen laut MEDLINE: Deep Learning, Low Back Pain. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: US National Science Foundation, U.S. National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Back pain is a pervasive issue affecting a significant portion of the population, often worsened by certain movements of the lower back. Assessing these movements is important for helping clinicians prescribe appropriate physical therapy. However, it can be difficult to monitor patients’ movements remotely outside the clinic. High-fidelity data from motion capture sensors can be used to classify different movements, but these sensors are costly and impractical for use in free-living environments. Motion Tape (MT), a new fabric-based wearable sensor, addresses these issues by being low cost and portable. Despite these advantages, novelty and variability in sensor stability make the MT dataset small scale and inherent to noise. In this work, we propose the Motion-Tape Augmentation Inference Model (MT-AIM), a deep learning classification pipeline trained on MT data. In order to address the challenges of limited sample size and noise present within the MT dataset, MT-AIM leverages conditional generative models to generate synthetic MT data of a desired movement, as well as predicting joint kinematics as additional features. This combination of synthetic data generation and feature augmentation enables MT-AIM to achieve state-of-the-art accuracy in classifying lower back movements, bridging the gap between physiological sensing and movement analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningLow Back PainHumansMovementMotion CaptureWearable Electronic DevicesBiomechanical PhenomenaAlgorithms

Stichwörter der Autor:innen

back paindeep learninggenerative modelsmotion sensingmovement classificationtime-series analysiswearable sensors

Autor:innen und Institutionen

  • Computer Science and Engineering, University of California San Diego, La Jolla, CA 92093, USA.
  • Active, Responsive, Multifunctional, and Ordered-Materials Research (ARMOR) Laboratory, Department of Structural Engineering, University of California San Diego, La Jolla, CA 92093, USA.
  • School of Physical Therapy, San Diego State University, San Diego, CA 92182, USA.
  • Qualcomm Institute, University of California San Diego, La Jolla, CA 92093, USA.

ORCID-Profile: Jared Levy, Aarti Lalwani, Elijah Wyckoff, Kenneth J Loh, Sara P Gombatto, Rose Yu, Emilia Farcas

Förderung

  • US National Science Foundation
  • U.S. National Science Foundation

Zitieren

APA

Levy, J., Lalwani, A., Wyckoff, E., Loh, K. J., Gombatto, S. P., Yu, R., & Farcas, E. (2026). Assessing Low Back Movement with Motion Tape Sensor Data Through Deep Learning. Sensors. https://doi.org/10.3390/s26041127

Vancouver

Levy J, Lalwani A, Wyckoff E, Loh KJ, Gombatto SP, Yu R, et al. Assessing Low Back Movement with Motion Tape Sensor Data Through Deep Learning. Sensors. 2026. doi:10.3390/s26041127

BibTeX
@article{Levy2026,
  author = {Levy, Jared and Lalwani, Aarti and Wyckoff, Elijah and Loh, Kenneth J and Gombatto, Sara P and Yu, Rose and Farcas, Emilia},
  title = {Assessing Low Back Movement with Motion Tape Sensor Data Through Deep Learning},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26041127}
}
Kostenlos starten →