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

Response Surface Methodology01:16

Response Surface Methodology

206
Response Surface Methodology (RSM) is a collection of statistical and mathematical techniques used to develop, improve, and optimize processes. It is particularly valuable when many input variables or factors potentially influence a response variable.
The process of RSM involves several key steps:
206
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

7.8K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.8K
Residual Plots01:07

Residual Plots

5.0K
A residual plot is a statistical representation of data used to analyze correlation and regression results. It helps verify the requirements for drawing specific conclusions about correlation and regression. To obtain the residual plot, first, the residual for each data value is calculated, which is simply the vertical distance between the observed and the predicted value obtained from the regression equation.
When the residual values are plotted against the variable x, it is called a residual...
5.0K

You might also read

Related Articles

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

Sort by
Same author

The zinc finger gene SQSTM1/p62 is involved in the response to ammonia nitrogen stress in the razor clam (Sinonovacula constricta).

Developmental and comparative immunology·2026
Same author

Twist-Induced Giant Modulation of Optical and Optoelectronic Anisotropy in van der Waals NbOX<sub>2</sub> Homo-/Heterostructures.

Nano letters·2026
Same author

Study on an All-Optic Temperature Sensor Based on a Low-Coherent Optical Interferometry.

Sensors (Basel, Switzerland)·2025
Same author

Giant Modulation of Second and Third Harmonic Generations in in-Plane Ferroelectric NbOI<sub>2</sub> via MoS<sub>2</sub> Atomic Layers.

Small (Weinheim an der Bergstrasse, Germany)·2025
Same author

Observation of Intrinsic and LED Light-Enhanced Memristor Performance in In-Plane Ferroelectric NbOI<sub>2</sub>.

ACS nano·2025
Same author

Nonvolatile Control of Optical and Electronic Responses in Two-Dimensional MoS<sub>2</sub> via Ferroelectric ScAlN Thin Films.

ACS applied materials & interfaces·2025

Related Experiment Video

Updated: Aug 9, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

599

Metasurface design with a complex residual neural network.

Kaizhu Liu, Changsen Sun

    Applied Optics
    |February 23, 2023
    PubMed
    Summary

    Researchers developed a complex residual neural network (CRNN) to solve complex electromagnetic field problems for metasurfaces. This deep learning method accurately predicts scattering parameters, enabling faster design of metalenses and accelerating electromagnetic field calculations.

    Area of Science:

    • Electromagnetics
    • Computational Physics
    • Materials Science

    Background:

    • Deep learning methods have advanced electromagnetic field computation.
    • Existing methods primarily address real-number problems, leaving complex-number electromagnetic calculations unsolved.
    • Metasurface design and analysis require efficient solutions for complex electromagnetic fields.

    Purpose of the Study:

    • To propose and validate a novel computation method for metasurfaces using deep learning.
    • To address the challenge of solving complex-number electromagnetic field problems.
    • To accelerate the design and analysis of metasurface devices.

    Main Methods:

    • Development of a complex residual neural network (CRNN) tailored for electromagnetic field computations.

    More Related Videos

    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.3K
    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

    2.9K

    Related Experiment Videos

    Last Updated: Aug 9, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    599
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.3K
    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

    2.9K
  • Prediction of scattering (S)21 parameters for cylindrical structures across a wavelength range (1.2–1.7 µm).
  • Utilizing CRNN to rapidly predict S21 parameters based on input structural parameters.

    • Main Results:

    • The CRNN accurately predicted S21 parameters for cylindrical structures.
    • The method demonstrated its capability by enabling the design of a metalens.
    • The CRNN approach proved effective for complex-number electromagnetic calculations.

    Conclusions:

    • The proposed CRNN method offers an effective solution for complex-number electromagnetic field problems in metasurfaces.
    • This approach significantly accelerates the prediction of scattering parameters and facilitates metasurface design.
    • The CRNN method shows potential for broader applications in electromagnetic field calculations requiring speed enhancement.