Related Experiment Video
Updated: Oct 12, 2025
07:24
Home-Based Monitor for Gait and Activity Analysis
Published on: August 8, 2019
6.9K
Gait Disorder Detection and Classification Method Using Inertia Measurement Unit for Augmented Feedback Training in
Hyeonjong Kim1, Ji-Won Kim2,3, Junghyuk Ko1
1Division of Mechanical Engineering, (National) Korea Maritime and Ocean University, Busan 49112, Korea.
Sensors (Basel, Switzerland)
|November 27, 2021
Summary
This study introduces a novel gait detection and classification (GDC) algorithm using augmented feedback training. The GDC method effectively distinguishes between normal gait and gait disorders in Parkinson's disease patients, aiding rehabilitation.
Area of Science:
- Biomedical Engineering
- Neuroscience
- Rehabilitation Technology
Background:
- Parkinson's disease (PD) commonly causes gait disorders, affecting speed and cadence.
- Augmented feedback training shows promise for effective physical rehabilitation in PD patients.
- Accurate gait detection and classification are crucial for personalized rehabilitation strategies.
Purpose of the Study:
- To develop and validate a numerical modeling process and algorithm for gait detection and classification (GDC) utilizing augmented feedback training.
- To assess the performance of the GDC algorithm in distinguishing between normal gait and gait disorders.
- To explore the relationship between gait parameters, thresholds, and classification accuracy for optimizing rehabilitation.
Main Methods:
- Developed a numerical model converting joint angles into Magnitude of Acceleration (MoA) and Z-axis Angular Velocity (ZAV) parameters.
- Implemented a gait detection and classification (GDC) algorithm incorporating augmented feedback training.
- Systematically varied acceleration thresholds (AT) and gyroscopic thresholds (GT) to analyze their impact on gait detection and classification rates (GDCR).
Main Results:
- The GDC algorithm demonstrated higher gait detection and classification rates (GDCR) with increased gait speed and adjusted thresholds (lower AT and GT).
- The algorithm successfully differentiated between normal gait patterns and those affected by gait disorders.
- Controlling GDCR using AT and GT as inputs proved to be a viable methodology for gait analysis.
Conclusions:
- The developed GDC numerical modeling and algorithm are valid for gait analysis in Parkinson's disease.
- This GDC method shows potential for objective gait evaluation and personalized rehabilitation in PD patients.
- The approach offers a promising tool for enhancing physical rehabilitation outcomes for individuals with gait disorders.
