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 Video

Updated: Aug 15, 2025

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

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

6.8K

Comparing algorithms for assessing upper limb use with inertial measurement units.

Tanya Subash1,2, Ann David1,3, StephenSukumaran ReetaJanetSurekha4

  • 1Department of Bioengineering, Christian Medical College, Vellore, India.

Frontiers in Physiology
|January 5, 2023
PubMed
Summary

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

Predicting motor recovery using surface electromyography in people with severe motor impairment after stroke: A prospective cohort study protocol.

MethodsX·2026
Same author

A VR-based experimental system for studying mirror visual feedback effects on cross-education.

Scientific reports·2026
Same author

The relationship between welfare technology experience and engagement in everyday activities.

Disability and rehabilitation. Assistive technology·2026
Same author

The facilitators and barriers to home-based robotic rehabilitation in India: a pilot feasibility study.

Frontiers in stroke·2026
Same author

Developing a comprehensive ICF core set to document health and functioning in children with Cancer in India: A preliminary study.

Indian journal of cancer·2025
Same author

Generalizable gesture classification of HDsEMG using volume representations of muscles averaged across multiple individuals.

Scientific reports·2025
This summary is machine-generated.

Machine learning best detects upper limb use from wrist sensors, outperforming traditional methods. A hybrid score offers a good alternative when labeled data is unavailable for training machine learning models.

Area of Science:

  • Biomechanics
  • Wearable Technology
  • Rehabilitation Engineering

Background:

  • Quantifying upper limb use is crucial for rehabilitation and activity monitoring.
  • Existing methods using wrist-worn inertial measurement units include thresholded activity counting, gross movement scores, and machine learning.
  • A direct comparison and detailed analysis of these measures, particularly machine learning's data requirements, are lacking.

Purpose of the Study:

  • To directly compare thresholded activity counting, gross movement score, a novel hybrid measure, and machine learning algorithms for upper limb use detection.
  • To investigate the information utilized by machine learning models and the impact of data characteristics on their performance.
  • To provide insights for optimizing upper limb use assessment with wearable sensors.
Keywords:
hemiparesismachine learningsensorimotor assessmentupper-limb rehabilitationupper-limb usewearable sensors

More Related Videos

An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field
06:52

An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field

Published on: May 26, 2020

8.0K
A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers
07:24

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

Published on: April 21, 2017

12.6K

Related Experiment Videos

Last Updated: Aug 15, 2025

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

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

6.8K
An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field
06:52

An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field

Published on: May 26, 2020

8.0K
A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers
07:24

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

Published on: April 21, 2017

12.6K

Main Methods:

  • Direct comparison of multiple upper limb use quantification methods using a single dataset.
  • Implementation and evaluation of thresholded activity counting, gross movement score, a hybrid measure, and random forest machine learning.
  • Additional analyses to explore feature importance and data-dependency of machine learning models.

Main Results:

  • The intra-subject random forest machine learning measure demonstrated superior accuracy in detecting upper limb use.
  • Among traditional algorithms, the hybrid activity counting and gross movement score measure performed best.
  • Machine learning models utilized forearm orientation and movement magnitude, with performance influenced by movement types and data proportions.

Conclusions:

  • Machine learning offers superior performance for upper limb use detection compared to traditional methods.
  • The hybrid measure serves as a viable alternative in scenarios lacking annotated data for machine learning training.
  • This study advances the understanding and optimization of wearable sensor-based upper limb use assessment.