EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mobile Spatiotemporal Gait Segmentation Using an Ear-Worn Motion Sensor and Deep Learning

Julian Decker, Lukas Boborzi, Roman Schniepp, Klaus Jahn iD, Max Wuehr iD

Sensors · 2024

DOI: 10.3390/s24196442 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Julian Decker und 4 weiteren Autor:innen. Beteiligte Einrichtung: German Center for Vertigo and Balance Disorders (DSGZ), LMU University Hospital, 81377 Munich, Germany. Hauptthemen laut MEDLINE: Deep Learning, Gait, Algorithms, Wearable Electronic Devices. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Federal Ministry for Education and Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mobile health technologies enable continuous, quantitative assessment of mobility and gait in real-world environments, facilitating early diagnoses of gait disorders, disease progression monitoring, and prediction of adverse events like falls. Traditionally, mobile gait assessment predominantly relied on body-fixed sensors positioned at the feet or lower trunk. Here, we investigate the potential of an algorithm utilizing an ear-worn motion sensor for spatiotemporal segmentation of gait patterns. We collected 3D acceleration profiles from the ear-worn sensor during varied walking speeds in 53 healthy adults. Temporal convolutional networks were trained to detect stepping sequences and predict spatial relations between steps. The resulting algorithm, mEar, accurately detects initial and final ground contacts (F1 score of 99% and 91%, respectively). It enables the determination of temporal and spatial gait cycle characteristics (among others, stride time and stride length) with good to excellent validity at a precision sufficient to monitor clinically relevant changes in walking speed, stride-to-stride variability, and side asymmetry. This study highlights the ear as a viable site for monitoring gait and proposes its potential integration with in-ear vital-sign monitoring. Such integration offers a practical approach to comprehensive health monitoring and telemedical applications, by integrating multiple sensors in a single anatomical location.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningGaitAlgorithmsWearable Electronic DevicesHumansMaleAdultFemaleEarWalkingYoung AdultWalking Speed

Stichwörter der Autor:innen

deep learningearearablesgait analysisin-ear sensinginertial sensorvital-sign monitoringwearables

Autor:innen und Institutionen

  • German Center for Vertigo and Balance Disorders (DSGZ), LMU University Hospital, 81377 Munich, Germany.
  • Schön Klinik Bad Aibling, 83043 Bad Aibling, Germany.
  • Institut für Notfallmedizin und Medinzinmanagement (INM), LMU University Hospital, 80336 Munich, Germany.
  • Department of Neurology, LMU University Hospital, 81377 Munich, Germany.

ORCID-Profile: Klaus Jahn, Max Wuehr

Förderung

  • German Federal Ministry for Education and Science

Zitieren

APA

Decker, J., Boborzi, L., Schniepp, R., Jahn, K., & Wuehr, M. (2024). Mobile Spatiotemporal Gait Segmentation Using an Ear-Worn Motion Sensor and Deep Learning. Sensors. https://doi.org/10.3390/s24196442

Vancouver

Decker J, Boborzi L, Schniepp R, Jahn K, Wuehr M. Mobile Spatiotemporal Gait Segmentation Using an Ear-Worn Motion Sensor and Deep Learning. Sensors. 2024. doi:10.3390/s24196442

BibTeX
@article{Decker2024,
  author = {Decker, Julian and Boborzi, Lukas and Schniepp, Roman and Jahn, Klaus and Wuehr, Max},
  title = {Mobile Spatiotemporal Gait Segmentation Using an Ear-Worn Motion Sensor and Deep Learning},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24196442}
}
Kostenlos starten →