Related Experiment Video
Updated: Mar 23, 2026
Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
Published on: March 4, 2018
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.
Insights
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.
Abstract:
Measuring stride variability and dynamics in children is useful for the quantitative study of gait maturation and neuromotor development in childhood and adolescence. In this paper, we computed the sample entropy (SampEn) and average stride interval (ASI) parameters to quantify the stride series of 50 gender-matched children participants in three age groups. We also normalized the SampEn and ASI values by leg length and body mass for each participant, respectively. Results show that the original and normalized SampEn values consistently decrease over the significance level of the Mann-Whitney U test (p < 0.01) in children of 3-14 years old, which indicates the stride irregularity has been significantly ameliorated with the body growth. The original and normalized ASI values are also significantly changing when comparing between any two groups of young (aged 3-5 years), middle (aged 6-8 years), and elder (aged 10-14 years) children. Such results suggest that healthy children may better modulate their gait cadence rhythm with the development of their musculoskeletal and neurological systems. In addition, the AdaBoost.M2 and Bagging algorithms were used to effectively distinguish the children's gait patterns. These ensemble learning algorithms both provided excellent gait classification results in terms of overall accuracy (≥90%), recall (≥0.8), and precision (≥0.8077).
