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 Videos

Time Series Multiple Channel Convolutional Neural Network with Attention-Based Long Short-Term Memory for Predicting

Jehn-Ruey Jiang1, Juei-En Lee1, Yi-Ming Zeng1

  • 1Department of Computer Science and Information Engineering, National Central University, Taoyuan City 32001, Taiwan.

Sensors (Basel, Switzerland)
|January 1, 2020
PubMed
Summary
This summary is machine-generated.

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

EGFR activation disrupts immunotherapy response via SHP2-mediated suppression of tumor-intrinsic response to IFN-γ.

The Journal of clinical investigation·2026
Same author

Machine learning integration with multi-omics data constructs a robust prognostic model and identifies PTGES3 as a therapeutic target for precision oncology in lung adenocarcinoma.

Frontiers in immunology·2025
Same author

Exosomal miR-320b regulates cardiomyocyte FOXM1 expression and may serve as an early-stage compensatory mechanism in obstructive sleep apnea.

PloS one·2025
Same author

Migration of a urethral foreign body into the scrotum in an adolescent: a case report.

BMC urology·2025
Same author

Mesenchymal Stem Cell Protection and Chondrogenic Differentiation in Tracheal Fistula Therapy via Bioactive Platinum Nanozymes.

ACS applied materials & interfaces·2025
Same author

Platinum nanozyme embedded in hyaluronate with multifunctional attributes synergistically promoting tracheal fistula healing.

International journal of biological macromolecules·2024

This study introduces two deep learning models for predicting bearing remaining useful life (RUL). These models, TSMC-CNN and TSMC-CNN-ALSTM, offer accurate end-to-end RUL prediction from raw data.

Area of Science:

  • Engineering
  • Computer Science
  • Machine Learning

Background:

  • Accurate prediction of remaining useful life (RUL) is crucial for predictive maintenance in machinery.
  • Traditional methods often require extensive feature engineering and may not capture complex temporal dependencies.

Purpose of the Study:

  • To propose novel deep learning architectures for end-to-end RUL prediction of bearings.
  • To enhance RUL prediction accuracy by leveraging multi-channel time series analysis and attention mechanisms.

Main Methods:

  • Developed Time Series Multiple Channel Convolutional Neural Network (TSMC-CNN) for feature extraction from multi-channel time series.
  • Integrated an attention-based Long Short-Term Memory (ALSTM) network with TSMC-CNN (TSMC-CNN-ALSTM) to focus on relevant temporal features.
Keywords:
bearingconvolutional neural networkdeep learninglong short-term memoryremaining useful lifetime series

Related Experiment Videos

  • Utilized PRONOSTIA bearing operation datasets for model training and validation.

    • Main Results:

    • Both TSMC-CNN and TSMC-CNN-ALSTM demonstrated superior performance in RUL prediction compared to existing methods.
    • The proposed models achieved lower Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE).

    Conclusions:

    • The proposed end-to-end deep learning methods effectively predict bearing RUL.
    • TSMC-CNN-ALSTM, incorporating an attention mechanism, offers enhanced accuracy for RUL prediction tasks.