Related Experiment Video
Updated: Aug 16, 2026
08:59
Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
Published on: October 28, 2018
Visualisation of gait data with Kohonen self-organising neural maps
Gabor Barton1, Adrian Lees, Paulo Lisboa
1Research Institute for Sport and Exercise Sciences, Liverpool John Moores University, Liverpool L3 2ET, UK. G.J.Barton@livjm.ac.uk
Gait & Posture
|August 23, 2005
Summary
Artificial neural networks simplify complex gait data, creating visual maps of patient movement patterns. This approach aids in objective analysis and comparison of gait assessments.
Area of Science:
- Biomechanics
- Artificial Intelligence
- Data Visualization
Background:
- Instrumented gait assessment generates complex kinematic and kinetic data.
- Analyzing this multi-dimensional data for gait patterns is challenging.
- Objective analysis protocols are needed to enhance clinical decision-making.
Purpose of the Study:
- To simplify complex joint kinematic and kinetic data from gait assessments.
- To identify and visualize gait stem-patterns using self-organising artificial neural networks.
- To enable objective comparison of patient gait patterns.
Main Methods:
- Utilized self-organising artificial neural networks (ANNs).
- Projected 3D joint angles, moments, and powers onto a topological neural map.
- Visualized multi-dimensional gait data in a 2D space, identifying gait patterns.
Main Results:
- Successfully reduced the complexity of gait kinematic and kinetic data.
- Identified distinct gait stem-patterns through topological mapping.
- Enabled patient positioning and comparison based on visualized gait patterns.
Conclusions:
- Topological neural maps offer a novel method for visualizing complex gait data.
- This visualization facilitates more objective gait analysis and comparison.
- The approach represents a step towards enhanced decision-making in gait assessment.
