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

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

106
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
106

You might also read

Related Articles

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

Sort by
Same author

Signature of glassy dynamics in dynamic mode decompositions.

Physical review. E·2026
Same author

Reservoir computing for system identification and model predictive control.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Learning the bistable cortical dynamics of the sleep-onset period.

PLoS computational biology·2026
Same author

Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

T-SHRED: symbolic regression for regularization and model discovery with transformer shallow recurrent decoders.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2026
Same author

ECG-Based Prediction of Shock-Refractory Ventricular Fibrillation During Resuscitation Without Interrupting CPR.

Circulation. Arrhythmia and electrophysiology·2026

Related Experiment Video

Updated: Jun 23, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K

Human motion data expansion from arbitrary sparse sensors with shallow recurrent decoders.

Megan R Ebers1, Mackenzie Pitts2, J Nathan Kutz3

  • 1Department of Applied Mathematics, University of Washington, Seattle, WA 98195.

Biorxiv : the Preprint Server for Biology
|June 19, 2024
PubMed
Summary

Deep learning reconstructs full body motion from minimal sensors. This technology enhances digital biomarker accuracy for health and performance tracking in real-world settings.

Keywords:
gait analysismachine learningmotion inferencesparse sensingwearable sensors

More Related Videos

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.3K
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.6K

Related Experiment Videos

Last Updated: Jun 23, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.3K
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.6K

Area of Science:

  • Biomedical Engineering
  • Machine Learning
  • Human Motion Analysis

Background:

  • Deep learning and sparse sensing are advancing human motion monitoring.
  • Current methods often require extensive sensor setups for comprehensive data.
  • Inferring unmonitored body segment motion is crucial for accurate health and performance assessment.

Purpose of the Study:

  • To develop a deep learning architecture for expanding sparse human motion data to dense configurations.
  • To infer the motion of unmonitored body segments using limited sensor inputs.
  • To improve the accuracy and availability of digital biomarker estimates.

Main Methods:

  • A shallow recurrent decoder network architecture was developed.
  • The model maps sparse sensor data to dense configurations, leveraging sensor time histories.
  • The architecture was applied to diverse datasets including controlled tasks, gait analysis, and free-moving environments.

Main Results:

  • Reconstruction of comprehensive time series measurements from as few as a single sensor.
  • Successful application to subject-specific and group-based movement models.
  • Demonstrated potential for improving digital biomarker estimates.

Conclusions:

  • The developed deep learning architecture effectively expands sparse motion data to dense configurations.
  • This approach enhances the accuracy and accessibility of digital biomarkers for various applications.
  • The technology has significant implications for clinical trials, robotics, and human performance optimization.