• search hit 4 of 4
Back to Result List

Comparison of algorithms and classifiers for stride detection using wearables

  • Sensor-based systems for diagnosis or therapy support of motor dysfunctions need methodologies of automatically stride detection from movement sequences. In this proposal, we developed a stride detection system for daily life use. We compared mostly used algorithms min–max patterns, dynamic time warping, convolutional neural networks (CNN), and automatic framing using two data sets of 32 healthy and 28 Parkinson’s disease (PD) persons. We developed an insole with force and IMU sensors to record the gait data. The PD patients carried out the standardized time up and go test, and the healthy persons a daily life activities test (walking, sitting, standing, ascending and descending stairs). As an automatically stride detection process for daily life use, we propose a first stride detection using automatic framing, and after normalization and resampling data a CNN is used. A F1-score of 0.938 (recall 0.968, precision 0.910) for time up and go test and of 0.944 (recall 0.992, precision 0.901) for daily life activities test were obtainedSensor-based systems for diagnosis or therapy support of motor dysfunctions need methodologies of automatically stride detection from movement sequences. In this proposal, we developed a stride detection system for daily life use. We compared mostly used algorithms min–max patterns, dynamic time warping, convolutional neural networks (CNN), and automatic framing using two data sets of 32 healthy and 28 Parkinson’s disease (PD) persons. We developed an insole with force and IMU sensors to record the gait data. The PD patients carried out the standardized time up and go test, and the healthy persons a daily life activities test (walking, sitting, standing, ascending and descending stairs). As an automatically stride detection process for daily life use, we propose a first stride detection using automatic framing, and after normalization and resampling data a CNN is used. A F1-score of 0.938 (recall 0.968, precision 0.910) for time up and go test and of 0.944 (recall 0.992, precision 0.901) for daily life activities test were obtained for CNN. Compared to the other detection methods, up to 6% F-measure improvement was shown.show moreshow less

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author: Tobias Steinmetzer, Markus Christoph Reckhardt, Fritjof Reinhardt, Dorela Erk, Carlos M. Travieso-González
DOI:https://doi.org/10.1007/s00521-019-04384-6
ISSN:1433-3058
Title of the source (English):Neural Computing and Applications
Document Type:Scientific journal article not peer-reviewed
Language:English
Year of publication:2019
Contributing Corporation:Niederlausitz Clinic, Center of Neurology and Pain Management Senftenberg Germany, University of Las Palmas de Gran Canaria, Signals and Communication Department, IDeTIC Las Palmas de Gran Canaria Spain
Tag:Convolutional neural networks; Gait analysis; Inertial sensors; Parkinson’s disease; Stride detection; Time up and go test; Validation Dynamic time warping
Volume/Year:32(2020)
Issue number:24
First Page:17857
Last Page:17868
Faculty/Chair:Fakultät 1 MINT - Mathematik, Informatik, Physik, Elektro- und Informationstechnik / Institut für Medizintechnologie
Einverstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.