High-Knee-Flexion Posture Recognition Using Multi-Dimensional Dynamic Time Warping on Inertial Sensor Data
Sensors · 2025
DOI: 10.3390/s25041083 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Annemarie F Laudanski und 4 weiteren Autor:innen. Beteiligte Einrichtung: Biomechanics of Human Mobility Laboratory, Department of Kinesiology and Health Sciences, University of Waterloo, Waterloo, ON N2L 3G1, Canada. Hauptthemen laut MEDLINE: Posture, Knee Joint, Knee. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada, NSERC Canada, NSERC Canada Graduate Scholarship.
Abstract (Originalsprache)
Relating continuously collected inertial data to the activities or postures performed by the sensor wearer requires pattern recognition or machine-learning-based algorithms, accounting for the temporal and scale variability present in human movements. The objective of this study was to develop a sensor-based framework for the detection and measurement of high-flexion postures frequently adopted in occupational settings. IMU-based joint angle estimates for the ankle, knee, and hip were time and scale normalized prior to being input to a multi-dimensional Dynamic Time Warping (mDTW) distance-based Nearest Neighbour algorithm for the identification of twelve postures. Data from 50 participants were divided to develop and evaluate the mDTW model. Overall accuracies of 82.3% and 55.6% were reached when classifying movements from the testing and validation datasets, respectively, which increased to 86% and 74.6% when adjusting for imbalances between classification groups. The highest misclassification rates occurred between flatfoot squatting, heels-up squatting, and stooping, while the model was incapable of identifying sequences of walking based on a single stride template. The developed mDTW model proved robust in identifying high-flexion postures performed by participants both included and precluded from algorithm development, indicating its strong potential for the quantitative measurement of postural adoption in real-world settings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Biomechanics of Human Mobility Laboratory, Department of Kinesiology and Health Sciences, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
- Machine Learning and Data Analytics Laboratory, Department of Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander Universität, Erlangen-Nürnberg (FA), 91054 Erlangen, Bavaria, Germany.
ORCID-Profile: Annemarie F Laudanski, Arne Küderle, Felix Kluge, Bjoern M Eskofier
Förderung
- Natural Sciences and Engineering Research Council of Canada
- NSERC Canada
- NSERC Canada Graduate Scholarship
- Queen Elizabeth II Graduate Scholarship in Science and Technology
- nternational Society of Biomechanics International Travel Grant
Zitieren
APA
Laudanski, A. F., Küderle, A., Kluge, F., Eskofier, B. M., & Acker, S. M. (2025). High-Knee-Flexion Posture Recognition Using Multi-Dimensional Dynamic Time Warping on Inertial Sensor Data. Sensors. https://doi.org/10.3390/s25041083
Vancouver
Laudanski AF, Küderle A, Kluge F, Eskofier BM, Acker SM. High-Knee-Flexion Posture Recognition Using Multi-Dimensional Dynamic Time Warping on Inertial Sensor Data. Sensors. 2025. doi:10.3390/s25041083
BibTeX
@article{Laudanski2025,
author = {Laudanski, Annemarie F and Küderle, Arne and Kluge, Felix and Eskofier, Bjoern M and Acker, Stacey M},
title = {High-Knee-Flexion Posture Recognition Using Multi-Dimensional Dynamic Time Warping on Inertial Sensor Data},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25041083}
}
EUVIMED