Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Relative Motion Analysis - Acceleration01:10

Relative Motion Analysis - Acceleration

A slider-crank mechanism converts rotational motion from the crank into linear motion of the slider or vice versa. This mechanism consists of three main parts: the crank, the connecting rod, and the slider. The movement of the slider-crank is an example of general plane motion as the fluctuating angle between the crank and the connecting rod. Consider a segment AB where point A is at the end of the slider and point B is on the diametrically opposite end to point A, on a crack. The variance in...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The 2026 global roadmap for textile-integrated wearable technologies in health.

Physiological measurement·2026
Same author

Interpretable graph-based models on multimodal biomedical data integration: a technical review and benchmarking.

Nature communications·2026
Same author

Wearable, broadband auscultation patch with cantilever pressure transducer for remote healthcare monitoring.

Nature communications·2026
Same author

Establishment of High Channel-Count Packaging in Active Implantable Medical Devices for Neuroprosthesis.

Journal of biomedical materials research. Part B, Applied biomaterials·2026
Same author

Computational modeling for precision targeting of conductivity-clamped gene electrotransfer within the striatum of the human brain.

Journal of neural engineering·2026
Same author

Comprehensive evaluation of ACMG/AMP-based variant classification tools.

Bioinformatics (Oxford, England)·2026

Related Experiment Video

Updated: Jul 10, 2026

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
10:52

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

Accelerometry based classification of walking patterns using time-frequency analysis.

Ning Wang1, Eliathamby Ambikairajah, Nigel H Lovell

  • 1School of Electrical Engineering and Telecommunication, University of New South Wales, UNSW Sydney 2052, Australia. NingWang@ee.unsw.edu.au

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
|November 16, 2007
PubMed
Summary

This study developed 33 time-frequency features to classify five human walking patterns using accelerometer data. The system achieved high accuracy, demonstrating effective gait analysis for diverse terrains.

More Related Videos

Home-Based Monitor for Gait and Activity Analysis
07:24

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Related Experiment Videos

Last Updated: Jul 10, 2026

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
10:52

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

Home-Based Monitor for Gait and Activity Analysis
07:24

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Area of Science:

  • Biomechanics
  • Signal Processing
  • Machine Learning

Background:

  • Human gait analysis is crucial for understanding mobility and detecting abnormalities.
  • Wearable sensors like accelerometers offer a non-invasive method for gait monitoring.
  • Distinguishing between different walking patterns (e.g., level ground, stairs, slopes) is challenging.

Purpose of the Study:

  • To develop and evaluate novel time-frequency domain features for classifying five distinct human walking patterns.
  • To assess the effectiveness of a multi-layer perceptron (MLP) Neural Network (NN) classifier for gait pattern recognition.
  • To investigate classification accuracy using different training and testing methodologies.

Main Methods:

  • Acquired triaxial accelerometer data from 52 subjects performing five walking tasks (level, stairs, slope).
  • Extracted 33 time-frequency domain features using wavelet packet transform on anterior-posterior, medio-lateral, and vertical acceleration signals.
  • Classified walking patterns using a multi-layer perceptron (MLP) Neural Network (NN) classifier.

Main Results:

  • The system achieved high classification accuracies: 88.54% with round robin (RR) and 92.05% with random frame selecting (RFS) train-test methods.
  • Time-frequency features effectively captured variations across different walking conditions.
  • The MLP NN demonstrated robust performance in discriminating between the five gait patterns.

Conclusions:

  • The developed 33-dimensional feature set and MLP NN classifier provide an accurate method for recognizing diverse human walking patterns.
  • The findings support the potential of wearable sensor technology for advanced gait analysis in real-world scenarios.
  • Random frame selecting (RFS) train-test method yielded superior classification performance compared to round robin (RR).