Related Experiment Video
Updated: Mar 23, 2026
06:54
Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
Published on: March 4, 2018
14.9K
Analysis and Classification of Stride Patterns Associated with Children Development Using Gait Signal Dynamics
Meihong Wu1, Lifang Liao1, Xin Luo1
1School of Information Science and Technology, Xiamen University, 422 Si Ming South Road, Xiamen, Fujian 361005, China.
Biomed Research International
|April 2, 2016
Summary
Childhood gait maturation shows reduced stride irregularity and improved cadence rhythm with age. Machine learning models accurately classify these developing gait patterns.
Area of Science:
- Pediatric Gait Analysis
- Neuromotor Development
- Biomechanical Engineering
Background:
- Quantitative assessment of gait maturation and neuromotor development in children is crucial.
- Stride variability and dynamics provide insights into developmental changes.
- Understanding these changes aids in identifying developmental milestones and potential issues.
Purpose of the Study:
- To quantify stride variability and dynamics in children aged 3-14 years.
- To investigate the relationship between gait parameters and physical growth.
- To evaluate the effectiveness of machine learning algorithms in classifying children's gait patterns.
Main Methods:
- Sample entropy (SampEn) and average stride interval (ASI) were computed for 50 children across three age groups.
- SampEn and ASI were normalized by leg length and body mass, respectively.
- AdaBoost.M1 and Bagging algorithms were employed for gait pattern classification.
Main Results:
- Both original and normalized SampEn values significantly decreased with age (p < 0.01), indicating reduced stride irregularity.
- Original and normalized ASI values showed significant changes between age groups, suggesting improved gait cadence modulation.
- Ensemble learning algorithms achieved high accuracy (≥90%), recall (≥0.8), and precision (≥0.8077) in classifying gait patterns.
Conclusions:
- Gait irregularity diminishes and cadence modulation improves with physical and neuromotor development in children.
- Machine learning, specifically AdaBoost.M2 and Bagging, effectively distinguishes developmental gait patterns.
- These findings contribute to a quantitative understanding of gait maturation in childhood and adolescence.
