EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Gait Event Detection and Gait Parameter Estimation from a Single Waist-Worn IMU Sensor

Roland Stenger iD, Hawzhin Hozhabr Pour iD, Jonas Teich, Andreas Hein iD, Sebastian Fudickar iD

Sensors · 2025

DOI: 10.3390/s25206463 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Roland Stenger und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Medical Informatics, University of Lübeck, 23562 Lübeck, Germany. Hauptthemen laut MEDLINE: Gait, Wearable Electronic Devices, Gait Analysis. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Federal Ministry of Education and Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Changes in gait are associated with an increased risk of falling and may indicate the presence of movement disorders related to neurological diseases or age-related weakness. Continuous monitoring based on inertial measurement unit (IMU) sensor data can effectively estimate gait parameters that reflect changes in gait dynamics. Monitoring using a waist-level IMU sensor is particularly useful for assessing such data, as it can be conveniently worn as a sensor-integrated belt or observed through a smartphone application. Our work investigates the efficacy of estimating gait events and gait parameters based on data collected from a waist-worn IMU sensor. The results are compared to measurements obtained using a GAITRite® system as reference. We evaluate two machine learning (ML)-based methods. Both ML methods are structured as sequence to sequence (Seq2Seq). The efficacy of both approaches in accurately determining gait events and parameters is assessed using a dataset comprising 17,643 recorded steps from 69 subjects, who performed a total of 3588 walks, each covering approximately 4 m. Results indicate that the Convolutional Neural Network (CNN)-based algorithm outperforms the long short-term memory (LSTM) method, achieving a detection accuracy of 98.94% for heel strikes (HS) and 98.65% for toe-offs (TO), with a mean error (ME) of 0.09 ± 4.69 cm in estimating step lengths.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GaitWearable Electronic DevicesGait AnalysisHumansNeural Networks, ComputerAlgorithmsMachine LearningMaleAdultFemaleWalking

Stichwörter der Autor:innen

biomedical computingbiomedical signal processingconvolutional neural networksgait recognitioninertial sensorsmachine learningmotion estimationtime series analysiswearable sensors

Autor:innen und Institutionen

  • Institute for Medical Informatics, University of Lübeck, 23562 Lübeck, Germany.
  • Group Assistance Systems and Medical Device Technology, Department of Health Services Research, Carl von Ossietzky University Oldenburg, 26129 Oldenburg, Germany.
  • Section for Clinical Research IT (SKFIT), Institute of Medical Biometry and Statistics, University of Lübeck, 23562 Lübeck, Germany.
  • Fraunhofer Research Institution for Individualized and Cell-Based Medical Engineering (IMTE), 23562 Lübeck, Germany.

ORCID-Profile: Roland Stenger, Hawzhin Hozhabr Pour, Andreas Hein, Sebastian Fudickar

Förderung

  • German Federal Ministry of Education and Research

Zitieren

APA

Stenger, R., Hozhabr Pour, H., Teich, J., Hein, A., & Fudickar, S. (2025). Gait Event Detection and Gait Parameter Estimation from a Single Waist-Worn IMU Sensor. Sensors. https://doi.org/10.3390/s25206463

Vancouver

Stenger R, Hozhabr Pour H, Teich J, Hein A, Fudickar S. Gait Event Detection and Gait Parameter Estimation from a Single Waist-Worn IMU Sensor. Sensors. 2025. doi:10.3390/s25206463

BibTeX
@article{Stenger2025,
  author = {Stenger, Roland and Hozhabr Pour, Hawzhin and Teich, Jonas and Hein, Andreas and Fudickar, Sebastian},
  title = {Gait Event Detection and Gait Parameter Estimation from a Single Waist-Worn IMU Sensor},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25206463}
}
Kostenlos starten →