Abstract
Stride time is an important indicator for the assessment of gait stability in long-term measurements using inertial measurement sensors. Peak detection is a commonly used method for gait segmentation and stride time estimation. Standard peak detection algorithms often fail due to additional movement components and measurement noise. This paper proposes a novel algorithm for robust peak detection in inertial sensor signals. The multi-stage implementation includes frequency analysis, reference signal synthesis, correlation and statistical analysis and a successive peak detection. The algorithm is validated on different inertial measurement datasets and compared to commonly known peak detection algorithms for periodic signals. In a movement laboratory setup of both healthy elderly and high risk fallers, we achieved satisfying detection results with a $\boldsymbol{F}_{1}$ -measure of 95.5%, which exceeded all additionally implemented algorithms for peak detection in gait signals based on inertial sensor measurements. In addition, we evaluated the stride time estimation performance using the proposed algorithms applied to different sensor positions and found sufficiently high correlation with optical reference data.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.