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

Time-Frequency, Complexity, and Fractal Analyses of Hemoglobin and Deoxyhemoglobin Responses to Quantify Mechanisms of Actions of Cupping Therapy.

Entropy (Basel, Switzerland)·2026
Same author

Robust FDR Control for Neuroimaging-based Classification via Knockoffs.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same author

"We don't know what we don't know": rural council officers' perceptions of the gendered impacts of climate change in Australia.

BMC public health·2026
Same author

Near-Infrared Spectroscopy in the Pathophysiology, Diagnosis, and Exercise-Based Management of Muscle Oxygenation Impairment.

Diagnostics (Basel, Switzerland)·2026
Same author

Adaptive Riemannian optimization for multi-scale diffeomorphic matching.

Nature communications·2026
Same author

A simple model of co-emergence of grid and place fields.

ArXiv·2026

Related Experiment Video

Updated: Dec 13, 2025

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

8.4K

Evaluation of Machine Learning Models for Classifying Upper Extremity Exercises Using Inertial Measurement Unit-Based

Andrew Hua, Pratik Chaudhari, Nicole Johnson

    IEEE Journal of Biomedical and Health Informatics
    |August 6, 2020
    PubMed
    Summary

    Wearable inertial measurement unit (IMU) devices accurately classify upper extremity exercises using machine learning. This technology enhances monitoring of physical therapy home exercise programs.

    More Related Videos

    An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor
    07:25

    An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor

    Published on: February 12, 2018

    7.2K
    Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments
    08:45

    Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments

    Published on: March 28, 2018

    11.1K

    Related Experiment Videos

    Last Updated: Dec 13, 2025

    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

    8.4K
    An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor
    07:25

    An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor

    Published on: February 12, 2018

    7.2K
    Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments
    08:45

    Kinematic Analysis Using 3D Motion Capture of Drinking Task in People With and Without Upper-extremity Impairments

    Published on: March 28, 2018

    11.1K

    Area of Science:

    • Biomedical Engineering
    • Rehabilitation Technology
    • Machine Learning in Healthcare

    Background:

    • Monitoring adherence and effectiveness of prescribed home-based physical therapy exercises presents a significant challenge.
    • Wearable inertial measurement unit (IMU) devices offer a potential solution by capturing kinematic data to analyze exercise biomechanics.

    Purpose of the Study:

    • To evaluate the efficacy of machine learning models in classifying nine distinct upper extremity exercises using IMU-derived kinematic data.
    • To identify optimal model parameters and feature sets for accurate exercise classification.

    Main Methods:

    • Fifty participants performed nine upper extremity exercises (one compound, eight isolation) with IMUs placed on the hand, forearm, upper arm, and torso.
    • Kinematic data, including joint angles, were collected, and various machine learning models were trained and tested.
    • Feature sets included flattened kinematic data and triaxial joint range of motion.

    Main Results:

    • Random forest models utilizing flattened kinematic data achieved the highest accuracy (98.6%).
    • Accuracy remained above 90% even with a reduced training set size (down to 5%).
    • Splitting data by participant decreased accuracy (88.7%), indicating the need for larger training sets in stratified analyses.

    Conclusions:

    • Wearable IMU devices coupled with machine learning can accurately classify upper extremity exercises, providing objective measurements for home-based physical therapy.
    • Random forest classification models demonstrate high accuracy and speed for exercise recognition.
    • Findings support the development of advanced healthcare technologies for improved remote patient monitoring and rehabilitation outcomes.