Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Steps in Outbreak Investigation

Steps in Outbreak Investigation

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:

You might also read

Related Articles

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

Sort by

Same author

Automatic Segmentation and Recognition of the Microstructure of High-Strength Low-Alloy Steel.

Materials (Basel, Switzerland)·2026

Same author

Deep Learning-Based Framework for Efficient Design of Multicomponent High Hardness High Entropy Alloys.

ACS applied materials & interfaces·2025

Same author

Fast and Accurate Recognition of Perovskite Fluorescent Anti-counterfeiting Labels Based on Lightweight Convolutional Neural Networks.

ACS applied materials & interfaces·2024

Same author

A Two-Phase Feature Selection Method for Identifying Influential Spreaders of Disease Epidemics in Complex Networks.

Entropy (Basel, Switzerland)·2023

Same author

Risk perception and subsidy policy-based voluntary vaccination driven by multiple information sources.

PloS one·2022

Same author

Center-environment feature models for materials image segmentation based on machine learning.

Scientific reports·2022

Search research articles

Related Experiment Video

Updated: Jun 27, 2025

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

MPSTAN: Metapopulation-Based Spatio-Temporal Attention Network for Epidemic Forecasting.

Junkai Mao¹, Yuexing Han^1,2,3, Bing Wang¹

¹School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China.

Entropy (Basel, Switzerland)

|April 26, 2024

Summary

This study introduces a novel metapopulation-based spatio-temporal attention network (MPSTAN) for accurate epidemic forecasting. The model improves prediction stability and accuracy by integrating multi-patch epidemiological knowledge, outperforming existing methods.

Keywords:

epidemic forecasting graph attention networks metapopulation epidemic spatio–temporal features

More Related Videos

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

Topographical Estimation of Visual Population Receptive Fields by fMRI

Topographical Estimation of Visual Population Receptive Fields by fMRI

Published on: February 3, 2015

Related Experiment Videos

Last Updated: Jun 27, 2025

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

Topographical Estimation of Visual Population Receptive Fields by fMRI

Topographical Estimation of Visual Population Receptive Fields by fMRI

Published on: February 3, 2015

Area of Science:

Epidemiology
Computational modeling
Network science

Background:

Accurate epidemic forecasting is crucial for public health policy and intervention.
Current spatio-temporal models struggle with diverse epidemic evolutionary trends and lack a generalizable framework.
Integrating epidemiological domain knowledge into neural networks can enhance forecasting but faces challenges with inter-patch interactions.

Purpose of the Study:

To develop a novel hybrid model, the metapopulation-based spatio-temporal attention network (MPSTAN), for improved epidemic forecasting.
To address limitations in current models by incorporating multi-patch epidemiological knowledge and adaptively defining inter-patch interactions.
To enhance the learning of epidemic transmission dynamics by integrating inter-patch knowledge into model construction and the loss function.

Main Methods:

Proposed a metapopulation-based spatio-temporal attention network (MPSTAN).
Incorporated multi-patch epidemiological knowledge into both the model architecture and the loss function.
Utilized adaptive definition of inter-patch interactions within the spatio-temporal framework.

Main Results:

MPSTAN demonstrated superior performance compared to baseline models in extensive experiments on two datasets.
The model achieved more accurate and stable short- and long-term epidemic forecasting across different evolutionary trends.
Integrating domain knowledge in both model construction and loss function proved more efficient for forecasting.

Conclusions:

The proposed MPSTAN effectively improves epidemic forecasting accuracy and stability by leveraging multi-patch epidemiological knowledge.
Domain knowledge integration is vital for enhancing machine learning models in epidemiology.
Strategic selection and integration of domain knowledge can further optimize forecasting performance.