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

You might also read

Related Articles

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

Sort by
Same author

Design and Evaluation of Stand-to-Sit and Sit-to-Stand Control Protocols for a HIP-Knee-Ankle-Foot Prosthesis with a Motorized Hip Joint.

Bioengineering (Basel, Switzerland)·2026
Same author

Automated Video Quality Assessment for the Edinburgh Visual Gait Score (EVGS).

Methods and protocols·2025
Same author

Validation of the Candrive Older Driver Risk Stratification Tool for Assessing Medical Fitness-to-Drive in Older Australian Drivers.

The journals of gerontology. Series A, Biological sciences and medical sciences·2025
Same author

Automated Assessment of Upper Extremity Function with the Modified Mallet Score Using Single-Plane Smartphone Videos.

Sensors (Basel, Switzerland)·2025
Same author

Real-Time Freezing of Gait Prediction and Detection in Parkinson's Disease.

Sensors (Basel, Switzerland)·2025
Same author

Balance confidence classification in people with a lower limb amputation using six minute walk test smartphone sensor signals.

PLOS digital health·2024

Related Experiment Video

Updated: Mar 1, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.2K

Feature selection for elderly faller classification based on wearable sensors.

Jennifer Howcroft1, Jonathan Kofman1, Edward D Lemaire2,3

  • 1Department of Systems Design Engineering, University of Waterloo, Waterloo, Canada.

Journal of Neuroengineering and Rehabilitation
|June 1, 2017
PubMed
Summary
This summary is machine-generated.

Identifying optimal gait features from wearable sensors significantly improves elderly fall risk classification. Feature selection enhances accuracy and sensitivity, making fall prediction more reliable using fewer data points.

Keywords:
AccelerometerFall riskFaller classificationFeature selectionOlder adultsPlantar pressurePredictionWearable sensors

More Related Videos

Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights
05:26

Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights

Published on: October 25, 2024

1.8K
Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults
04:13

Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults

Published on: February 8, 2019

7.3K

Related Experiment Videos

Last Updated: Mar 1, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.2K
Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights
05:26

Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights

Published on: October 25, 2024

1.8K
Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults
04:13

Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults

Published on: February 8, 2019

7.3K

Area of Science:

  • Biomechanics and Sensor Technology
  • Gerontology and Fall Prevention
  • Machine Learning in Healthcare

Background:

  • Wearable sensors generate extensive gait data for fall risk assessment.
  • Selecting appropriate features is crucial to manage computational costs and improve classification accuracy.
  • This study focuses on optimizing feature sets for faller classification using accelerometer and pressure-sensing insole data.

Purpose of the Study:

  • To identify and evaluate smaller, effective feature sets for classifying elderly fallers.
  • To compare the performance of different feature selection algorithms and machine learning classifiers.
  • To determine the optimal combination of wearable sensor data for faller classification.

Main Methods:

  • 100 older adults (75.5 ± 6.7 years) participated, including 24 fallers.
  • Gait data collected using pressure-sensing insoles and tri-axial accelerometers (head, pelvis, shanks).
  • Feature selection employed Correlation-based Feature Selection (CFS), Fast Correlation Based Filter (FCBF), and Relief-F algorithms. Classification utilized Support Vector Machine (SVM), Naïve Bayesian, and Multi-layer Perceptron (MLP) models.

Main Results:

  • The best single-feature model (SVM) achieved 78% accuracy with one posterior pelvis accelerometer feature.
  • A multi-feature model (SVM) with ten features showed improved sensitivity (44%).
  • Multi-sensor models (Naïve Bayesian) using pelvis and shank accelerometers yielded higher sensitivity (56%) compared to single-sensor models (41%).

Conclusions:

  • Feature selection significantly enhances faller classification accuracy and efficiency compared to using unselected features.
  • While CFS and FCBF identified concise feature sets, Relief-F with specific sensor combinations offered better sensitivity.
  • Feature selection is a critical step for developing effective fall prediction models using wearable sensor data.