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

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

205
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
205
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

234
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
234
Improving Translational Accuracy02:07

Improving Translational Accuracy

13.9K
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...
13.9K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.5K
3.5K

You might also read

Related Articles

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

Sort by
Same author

Submanifold sparse convolutional networks for automated 3D segmentation of kidneys and kidney tumours in computed tomography.

Scientific reports·2026
Same author

An ultrafast plenoptic-camera system for high-resolution 3D particle tracking in unsegmented scintillators.

Nature communications·2026
See all related articles

Related Experiment Videos

Image-Based Model Parameter Optimization Using Model-Assisted Generative Adversarial Networks.

Saul Alonso-Monsalve, Leigh H Whitehead

    IEEE Transactions on Neural Networks and Learning Systems
    |March 14, 2020
    PubMed
    Summary

    This study introduces a model-assisted generative adversarial network (GAN) to create realistic fake images matching real ones by learning model parameters. This method enhances image recognition accuracy by minimizing bias in simulations.

    Related Experiment Videos

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Image Processing

    Background:

    • Accurate image generation is crucial for training and validating image recognition systems.
    • Simulations often require precise model parameters, which can be difficult to determine from experimental data.

    Purpose of the Study:

    • To develop a model-assisted generative adversarial network (GAN) capable of producing synthetic images that closely match real experimental images.
    • To enable the determination of unknown model parameters from real images for improved simulation accuracy.

    Main Methods:

    • A novel model-assisted GAN architecture was proposed, incorporating a convolutional neural network to emulate simulation processes.
    • The generator within the GAN was trained to learn model parameter values that yield synthetic images best matching true images.
    • Two case studies were conducted to validate the agreement between learned and true model parameters.

    Main Results:

    • Excellent agreement was demonstrated between the model parameters generated by the GAN and the true model parameters in both case studies.
    • The model-assisted GAN successfully produced high-fidelity fake images that accurately matched true images.
    • The approach effectively minimized bias in image recognition tasks by retuning default simulations.

    Conclusions:

    • Model-assisted GANs offer a powerful approach for generating realistic synthetic images and accurately estimating underlying model parameters.
    • This technique can significantly improve the reliability and accuracy of image recognition systems, especially when dealing with experimental data.
    • The trained convolutional neural network acts as an efficient conditional generator, enabling rapid production of fake images across various parameter values.