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

Effect of Early Administration of Shenfu Injection on Hemodynamics in Septic Patients: A Multicenter, Randomized, Controlled Trial.

Critical care medicine·2026
Same author

AI-powered digital innovations in pharmaceuticals research & development: Current landscape and case examples.

Journal of biopharmaceutical statistics·2026
Same author

Multi-task deep learning assists detection and diagnosis of gliomas and brain metastases.

NPJ digital medicine·2026
Same author

Photosynthesis and yield enhancements in rice by foliar magnesium supply under variable soil nitrogen applications.

Frontiers in plant science·2026
Same author

An epigenetically enhanced whole-cell vaccine in a stimulatory hydrogel for robust antitumor immunity.

Biomaterials·2026
Same author

Genetic polymorphisms of SPP1 and MGP are associated with thumb osteoarthritis: a replication study in the Chinese population.

Molecular biology reports·2026

Related Experiment Video

Updated: Dec 14, 2025

Optimized Fabrication Procedure for High-Quality Graphene-based Moiré Superlattice Devices
11:24

Optimized Fabrication Procedure for High-Quality Graphene-based Moiré Superlattice Devices

Published on: July 11, 2025

13.5K

Machine learning and evolutionary algorithm studies of graphene metamaterials for optimized plasmon-induced

Tian Zhang, Qi Liu, Yihang Dan

    Optics Express
    |July 17, 2020
    PubMed
    Summary

    Machine learning and evolutionary algorithms accelerate the intelligent design of graphene metamaterials for photonics devices. Random forest models offer efficient spectrum prediction and inverse design, enhancing plasmon induced transparency (PIT) effects.

    More Related Videos

    Visible-light Induced Reduction of Graphene Oxide Using Plasmonic Nanoparticle
    07:24

    Visible-light Induced Reduction of Graphene Oxide Using Plasmonic Nanoparticle

    Published on: September 22, 2015

    14.7K
    Scalable Solution-processed Fabrication Strategy for High-performance, Flexible, Transparent Electrodes with Embedded Metal Mesh
    11:09

    Scalable Solution-processed Fabrication Strategy for High-performance, Flexible, Transparent Electrodes with Embedded Metal Mesh

    Published on: June 23, 2017

    10.5K

    Related Experiment Videos

    Last Updated: Dec 14, 2025

    Optimized Fabrication Procedure for High-Quality Graphene-based Moiré Superlattice Devices
    11:24

    Optimized Fabrication Procedure for High-Quality Graphene-based Moiré Superlattice Devices

    Published on: July 11, 2025

    13.5K
    Visible-light Induced Reduction of Graphene Oxide Using Plasmonic Nanoparticle
    07:24

    Visible-light Induced Reduction of Graphene Oxide Using Plasmonic Nanoparticle

    Published on: September 22, 2015

    14.7K
    Scalable Solution-processed Fabrication Strategy for High-performance, Flexible, Transparent Electrodes with Embedded Metal Mesh
    11:09

    Scalable Solution-processed Fabrication Strategy for High-performance, Flexible, Transparent Electrodes with Embedded Metal Mesh

    Published on: June 23, 2017

    10.5K

    Area of Science:

    • Photonics
    • Materials Science
    • Computational Science

    Background:

    • Machine learning and optimization algorithms are increasingly vital for designing photonics devices.
    • Graphene metamaterials (GMs) offer unique properties for advanced optical applications.

    Purpose of the Study:

    • To review and demonstrate data-driven applications of machine learning and evolutionary algorithms for novel graphene metamaterials.
    • To enable efficient spectrum prediction, inverse design, and performance optimization of GMs.

    Main Methods:

    • Utilized traditional machine learning algorithms (k-nearest neighbor, decision tree, random forest, artificial neural networks) to replace numerical simulations for spectrum prediction and inverse design.
    • Employed evolutionary algorithms (genetic algorithm, NSGA-II) for multi-objective optimization to achieve steep transmission characteristics.
    • Theoretically demonstrated the plasmon induced transparency (PIT) effect using the transfer matrix method.

    Main Results:

    • Machine learning algorithms effectively predicted spectra and performed inverse designs for GMs.
    • Random forest algorithms showed advantages in accuracy and training speed.
    • Optimized GMs achieved a maximum transmission peak-to-dip difference of 0.97, demonstrating steep transmission characteristics.

    Conclusions:

    • Machine learning and evolutionary algorithms provide a powerful framework for the intelligent design of photonics devices.
    • This study offers guidance for selecting appropriate machine learning algorithms for inverse design problems in photonics.
    • The findings facilitate the development of novel graphene metamaterials with enhanced plasmon induced transparency effects.