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-averaged simulated microgravity ameliorates tau-induced deficit in Drosophila melanogaster.

NPJ microgravity·2026
Same author

A chromatin-associated pool of Aurora A controls kinetochore-microtubule attachments to ensure chromosome biorientation.

Science advances·2026
Same author

Self-Assembly of Hierarchical Macroporous Metal-Organic Framework Films Guided by Hydrophilic-Lipophilic Balance.

Journal of the American Chemical Society·2026
Same author

Effects of illite or bentonite on cytotoxicity, antibacterial and adsorption capacity in porcine intestinal epithelial cells.

Journal of animal science and technology·2026
Same author

Nanofibrous Interface-Engineered Microgel Array Enabling Streamlined Digital PCR.

ACS sensors·2026
Same author

Design and Validation of a Hand Interossei Muscle Dynamometer (HIMDNA) for Finger Abduction and Adduction Strength Measurement.

Annals of biomedical engineering·2026

Related Experiment Video

Updated: Oct 31, 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

4.6K

Self-Attention-Based Deep Learning Network for Regional Influenza Forecasting.

Seungwon Jung, Jaeuk Moon, Sungwoo Park

    IEEE Journal of Biomedical and Health Informatics
    |July 1, 2021
    PubMed
    Summary
    This summary is machine-generated.

    SAIFlu-Net, a novel deep learning model, improves regional influenza forecasting by using self-attention mechanisms to analyze historical data. This approach enhances accuracy in predicting flu outbreaks for better public health preparedness.

    More Related Videos

    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
    04:17

    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

    Published on: May 10, 2024

    1.1K
    High-throughput Detection Method for Influenza Virus
    10:05

    High-throughput Detection Method for Influenza Virus

    Published on: February 4, 2012

    26.4K

    Related Experiment Videos

    Last Updated: Oct 31, 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

    4.6K
    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
    04:17

    DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

    Published on: May 10, 2024

    1.1K
    High-throughput Detection Method for Influenza Virus
    10:05

    High-throughput Detection Method for Influenza Virus

    Published on: February 4, 2012

    26.4K

    Area of Science:

    • Epidemiology
    • Computational Biology
    • Public Health

    Background:

    • Early influenza prediction is crucial for effective public health interventions and resource allocation.
    • Deep/machine learning models offer superior forecasting performance over traditional methods by integrating diverse data sources.
    • Limitations in data availability and reliability often necessitate models relying solely on historical influenza occurrence data, framing forecasting as a multivariate time-series problem.

    Purpose of the Study:

    • To propose SAIFlu-Net, a novel self-attention-based deep learning model for enhanced regional influenza forecasting.
    • To leverage the strengths of Long Short-Term Memory (LSTM) networks and self-attention mechanisms for improved prediction accuracy.
    • To evaluate the efficacy of SAIFlu-Net against existing forecasting models using real-world influenza data.

    Main Methods:

    • Developed SAIFlu-Net, integrating a Long Short-Term Memory (LSTM) network for time-series pattern extraction within each region.
    • Employed a self-attention mechanism within SAIFlu-Net to identify and weight similarities between regional influenza occurrence patterns.
    • Conducted extensive comparative experiments using weekly regional influenza datasets against established forecasting models.

    Main Results:

    • The proposed SAIFlu-Net model demonstrated superior performance compared to existing methods in regional influenza forecasting.
    • SAIFlu-Net achieved lower root mean square error (RMSE), indicating more accurate predictions.
    • The model exhibited a higher Pearson correlation coefficient, signifying a stronger agreement between predicted and actual influenza occurrences.

    Conclusions:

    • SAIFlu-Net represents a significant advancement in regional influenza forecasting, outperforming current models.
    • The integration of self-attention mechanisms effectively captures complex temporal dependencies in influenza data.
    • The findings suggest SAIFlu-Net's potential for improving public health strategies through more reliable early prediction of influenza outbreaks.