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 Experiment Videos

Classification of basic daily movements using a triaxial accelerometer.

M J Mathie1, B G Celler, N H Lovell

  • 1Centre for Health Informatics, University of New South Wales, Sydney, Australia.

Medical & Biological Engineering & Computing
|October 27, 2004
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Surgical approach to model facial nerve paralysis in an ovine model for in vivo testing of a novel intervention.

Journal of plastic, reconstructive & aesthetic surgery : JPRAS·2025
Same author

All optical neural interfaces.

Applied optics·2024
Same author

Development and performance of a biomimetic artificial perilymph for in vitro testing of medical devices.

Journal of neural engineering·2018
Same author

From A to Z: Wearable technology explained.

Maturitas·2018
Same author

Unintended Consequences of Wearable Sensor Use in Healthcare. Contribution of the IMIA Wearable Sensors in Healthcare WG.

Yearbook of medical informatics·2016
Same author

Health-Enabling and Ambient Assistive Technologies: Past, Present, Future.

Yearbook of medical informatics·2016

This study presents a flexible, automated framework for classifying human movements using accelerometry. The system accurately distinguishes basic activities like walking and falls, achieving high precision in real-world scenarios.

Area of Science:

  • Biomedical Engineering
  • Human Movement Analysis
  • Wearable Technology

Background:

  • Accurate human movement classification is crucial for health monitoring and rehabilitation.
  • Existing systems often lack flexibility and adaptability for diverse movement patterns.
  • Accelerometry offers a non-invasive method for capturing movement data.

Purpose of the Study:

  • To introduce a generic, modular framework for automated human movement classification using accelerometry.
  • To develop and validate a classifier based on this framework for identifying basic human movements.
  • To assess the accuracy, sensitivity, and specificity of the developed classification system.

Main Methods:

  • Development of a hierarchical binary decision tree framework for movement classification.

Related Experiment Videos

  • Implementation of a classifier using signals from a single, waist-mounted triaxial accelerometer.
  • Validation through controlled laboratory studies with 26 healthy subjects performing basic movements.
  • Classification of movements into activity/rest and subclasses like falls, walking, transitions, sitting, standing, and lying.

    • Main Results:

    • The developed classifier achieved high performance across all classification levels.
    • Sensitivity for every classification exceeded 87%, with specificity surpassing 94%.
    • Overall system accuracy demonstrated a sensitivity of 97.7% and specificity of 98.7% on a dataset of 1309 movements.

    Conclusions:

    • The proposed generic framework provides a modular and flexible approach to automated human movement classification.
    • The developed classifier demonstrates high accuracy and reliability for identifying basic human movements from accelerometry data.
    • This system has potential applications in health monitoring, activity recognition, and fall detection.