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: Jul 16, 2026

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats
06:52

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

Published on: April 3, 2026

A Multi-Task Learning Framework with Physics Embedded for Signal Reconstruction and State Prediction in Underground

Xin Chen1, Lin Zhang1, Haonian Wu1

  • 1School of Robot Engineering, Yangtze Normal University, Chongqing 408100, China.

Neural Networks : the Official Journal of the International Neural Network Society
|July 14, 2026
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

A Scoping Review of Malnutrition Risk Prediction Models in Cancer Patients.

Journal of clinical nursing·2026
Same author

<i>CFTR</i> gene delivery to human airway epithelia using parainfluenza virus 5 amplifying virus-like particles.

Molecular therapy. Nucleic acids·2026
Same author

T-Bet Modulates Plasmodium-Specific CD4<sup>+</sup> T Cell Differentiation and Anti-Malarial Immunity During Blood-Stage Infection.

Parasite immunology·2026
Same author

A dual-channel electron expressway triggers piezocatalytic ferroptosis-mitochondrial catastrophe cascade for anti-glioblastoma therapy.

Biomaterials·2026
Same author

Enhanced Energy Storage Performance in Mn-Doped BaTiO<sub>3</sub>-Based Epitaxial Thin Films.

ACS applied materials & interfaces·2026
Same author

Host macrophages/monocytes promote malaria transmission by modulating mosquito microbiota via SR-A-mediated phagocytosis.

Nature communications·2026

This study introduces a new method for predicting hydraulic support positions in coal mining, improving safety and efficiency. The Multi-Task Learning Framework with Physics Embedded (MTLPE) accurately reconstructs missing data and forecasts support states.

Area of Science:

  • Mining Engineering
  • Robotics
  • Computer Vision

Background:

  • Current hydraulic support monitoring in longwall coal mining faces challenges with sensor reliability, data annotation, and missing data reconstruction.
  • Existing forecasting models often oversimplify spatial attributes and fail to address spatio-temporal data gaps effectively.

Purpose of the Study:

  • To develop an integrated approach for accurate forecasting of hydraulic support states in longwall coal mining.
  • To address limitations in current monitoring methods, including sensor vulnerability, manual annotation, data reconstruction, and model complexity.

Main Methods:

  • An unsupervised vision-based localization module for hydraulic support positioning.
  • Benchmarking of various spatio-temporal models for performance evaluation.
Keywords:
Coal miningHydraulic supportMulti-Task LearningPhysics-informed neural networksSpatio-temporal forecasting

Related Experiment Videos

Last Updated: Jul 16, 2026

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats
06:52

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

Published on: April 3, 2026

  • A Multi-Task Learning Framework with Physics Embedded (MTLPE) for simultaneous signal reconstruction and position prediction.
  • An iterative learning strategy to enhance model performance.

    • Main Results:

    • The proposed MTLPE model demonstrated superior performance across four operational scenarios.
    • MTLPE achieved a Root Mean Square Error (RMSE) of 0.43 mm, outperforming the best baseline method (0.48 mm RMSE).
    • The integrated approach successfully reconstructed missing spatio-temporal data and improved position prediction accuracy.

    Conclusions:

    • The developed MTLPE framework offers a robust solution for signal reconstruction and position prediction of hydraulic support groups.
    • This work provides innovative insights applicable to multi-rigid-body systems in demanding environments.
    • The findings contribute to enhanced operational safety and efficiency in longwall coal mining.