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: Apr 4, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Enhancing COVID-19 forecasts with a lightweight multi-head depthwise separable convolution network.

Haoyuan Lan1,2, Shunjiang Ni3,4

  • 1School of Safety Science, Tsinghua University, Beijing, 100084, China.

Scientific Reports
|April 2, 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

TCGL: Temporal Contrastive Graph for Self-Supervised Video Representation Learning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022
Same author

A network-based model to explore the role of testing in the epidemiological control of the COVID-19 pandemic.

BMC infectious diseases·2021
Same author

Scenario-Entity Analysis based on an entity-relationship model: Revisiting crime reconstruction.

Forensic science international·2019
Same author

Impact of travel patterns on epidemic dynamics in heterogeneous spatial metapopulation networks.

Physical review. E, Statistical, nonlinear, and soft matter physics·2009

CDSCnet, a novel lightweight model, accurately forecasts COVID-19 with limited data. This Chunking Depthwise Separable Convolution network outperforms existing models, offering a reliable tool for epidemic spread analysis.

Area of Science:

  • Epidemiology
  • Machine Learning
  • Data Science

Background:

  • Forecasting COVID-19 is challenging due to limited data.
  • Existing models often struggle with small datasets and capturing long-term dependencies.

Purpose of the Study:

  • To introduce CDSCnet (Chunking Depthwise Separable Convolution network), a lightweight model for COVID-19 forecasting.
  • To evaluate CDSCnet's performance against established models using real-world COVID-19 data.

Main Methods:

  • Developed CDSCnet, a lightweight CNN model with fixed convolution heads for long-term dependency capture.
  • Conducted comparative analysis using COVID-19 datasets from 7 countries (e.g., India, Brazil, USA).
  • Evaluated performance on both smooth and high-noise datasets.
Keywords:
COVID-19Deep learningForecasting

Related Experiment Videos

Last Updated: Apr 4, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Main Results:

  • CDSCnet demonstrated superior prediction accuracy compared to CNN-LSTM variants.
  • Achieved a maximum Mean Absolute Error (MAE) reduction exceeding 50% on the Spain task.
  • Consistently optimal performance across diverse datasets.

Conclusions:

  • CDSCnet effectively captures epidemic spread dynamics, even with limited data.
  • The model serves as a reliable decision-support tool for public health.
  • CDSCnet offers a promising approach for infectious disease forecasting.