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

Improving Translational Accuracy02:07

Improving Translational Accuracy

12.0K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
12.0K
Survival Tree01:19

Survival Tree

173
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
173
Upsampling01:22

Upsampling

346
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
346

You might also read

Related Articles

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

Sort by
Same author

Bronchial lesions in a high serum IgA mouse model: pulmonary venular IgA deposition and spatially distinct lymphoid cell aggregation.

Journal of pathology and translational medicine·2026
Same author

Mechanistic Atomic Hydrogen Chemistry for Ruthenium Deposition: From Ligand Elimination to Area-Selective Patterning.

Journal of the American Chemical Society·2026
Same author

Overcoming the Critical Thickness Limit: Interfacial Control of Crystallization Pathways in Atomic-Scale Dielectric Thin Films.

ACS nano·2026
Same author

Molecular dynamics simulation of nitrogen diffusion in iron and iron nitrides using <i>ab initio</i> data trained machine learning potentials.

Physical chemistry chemical physics : PCCP·2026
Same author

Tuning surface reactivity pathways through molecular inhibitor redosing for precision nanopatterning.

Materials horizons·2026
Same author

A self-regulating wearable OLED patch for accelerated wound healing <i>via</i> photobiomodulation-triggered drug delivery.

Materials horizons·2026

Related Experiment Video

Updated: Oct 2, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K

HRGAN: A Generative Adversarial Network Producing Higher-Resolution Images than Training Sets.

Minyoung Park1, Minhyeok Lee1, Sungwook Yu1

  • 1School of Electrical and Electronics Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 06974, Korea.

Sensors (Basel, Switzerland)
|February 26, 2022
PubMed
Summary

This study introduces a novel Generative Adversarial Network (GAN) called HRGAN. HRGAN can generate synthetic images at a higher resolution than the training data, overcoming a key limitation of conventional GANs.

Keywords:
Inception scoregenerative adversarial networkimage generationimage resolution

Related Experiment Videos

Last Updated: Oct 2, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Generative Adversarial Networks (GANs) excel at synthetic image generation.
  • Conventional GANs are limited to generating images at the resolution of the training dataset.

Purpose of the Study:

  • To propose a novel GAN framework, Higher Resolution GAN (HRGAN), capable of generating images with higher resolution than the training data.
  • To address the resolution limitation in conventional GAN frameworks.

Main Methods:

  • Introduced a novel GAN framework, HRGAN, incorporating additional up-sampling convolutional layers.
  • Utilized a pre-trained network, termed an evaluator, to introduce an additional training target for the generator.
  • Calibrated generated images for realistic features using the evaluator.

Main Results:

  • HRGAN successfully generated images at 64x64 and 128x128 resolutions from 32x32 resolution training sets (CIFAR-10, CIFAR-100).
  • HRGAN significantly outperformed existing models in Inception score.
  • Achieved a 28.6% improvement in Inception score for 128x128 image generation on CIFAR-10.

Conclusions:

  • The proposed HRGAN framework enables the generation of synthetic images at resolutions exceeding the training data.
  • HRGAN demonstrates superior performance in image quality and resolution enhancement compared to existing GAN models.