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 Videos

Poultry growth modeling using neural networks and simulated data.

H A Ahmad1

  • 1Department of Biology, Jackson State University, Jackson, MS 39217.

The Journal of Applied Poultry Research
|September 17, 2013
PubMed
Summary

This study introduces a novel artificial intelligence approach for poultry growth modeling, simulating data to train neural networks for accurate broiler and guinea fowl growth prediction. The Back-Propagation-3 neural network demonstrated superior performance, achieving near-perfect R-squared values.

Related Concept Videos

Growth Models with Integration: Problem Solving01:27

Growth Models with Integration: Problem Solving

In population modeling, integration provides a systematic way to determine accumulated quantities from known rates of change. One such application arises in ecology, where the total weight of a fish population in a body of water is referred to as its biomass. When the rate of growth of this biomass is known as a function of time, calculus can be used to determine the total biomass at a future date.Growth Rate and Biomass FunctionLet the growth rate of the fish population be represented by a...
Exponential Equations for Modeling Growth01:26

Exponential Equations for Modeling Growth

Exponential models are essential for describing rapid, multiplicative changes in natural systems, such as population growth. When a population doubles at regular intervals, the process can be modeled using a suitable base. For instance, a bacterial culture that doubles every three hours follows the model n(t)=n0⋅2t/3, where n(t) is the population at the time t.A more general model uses the natural base e, especially for continuous growth. This takes the form n(t)=n0⋅ert, where r is the relative...

You might also read

Related Articles

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

Sort by
Same author

An overview of poultry industry in Pakistan.

World's poultry science journal·2015
Same author

Hydrogen termination of CVD diamond films by high-temperature annealing at atmospheric pressure.

The Journal of chemical physics·2013
Same author

Egg production forecasting: Determining efficient modeling approaches.

The Journal of applied poultry research·2012
Same author

Effect of two dietary concentrate levels on tenderness, calpain and calpastatin activities, and carcass merit in Waguli and Brahman steers.

Journal of animal science·2008
Same author

Comparison of forecasting methodologies using egg price as a test case.

Poultry science·2006
Same author

Physiologic responses in healthy Labrador Retrievers during field trial training and competition.

Journal of veterinary internal medicine·2004

Area of Science:

  • Animal Science
  • Computational Biology
  • Artificial Intelligence

Background:

  • Traditional poultry growth models (e.g., Gompertz) face limitations due to genetic, nutritional, and environmental variability.
  • Developing accurate growth curves for diverse bird strains and changing conditions is data-intensive, costly, and time-consuming.
  • Existing models struggle to adapt to dynamic factors influencing poultry development.

Purpose of the Study:

  • To simulate poultry growth data from existing literature for various growth periods.
  • To develop and evaluate artificial intelligence models, specifically neural networks, for enhanced growth prediction.
  • To overcome the limitations of traditional models in capturing complex growth dynamics.

Main Methods:

  • Simulated broiler growth data using normal distributions (5-day intervals, mean, SD) with @Risk software.
Keywords:
growth modelingneural networksimulation

Related Experiment Videos

  • Developed and trained three neural network architectures: BackPropagation-3, BackPropagation-5, and Ward-5 (NeuroShell 2 Ward).
  • Validated models by predicting actual broiler growth over 50 days and applied the methodology to guinea fowl growth.

    • Main Results:

    • The Back-Propagation-3 neural network achieved an R-squared value of 0.998, indicating a near-perfect fit for broiler growth prediction.
    • BackPropagation-5 and Ward-5 networks yielded R-squared values of 0.967 and 0.973, respectively.
    • The approach successfully predicted guinea fowl growth with an R-squared of 0.96 using general regression and Ward-5 networks.

    Conclusions:

    • Artificial intelligence, particularly the Back-Propagation-3 neural network, offers a highly accurate and adaptable method for poultry growth modeling.
    • Simulated data combined with advanced neural networks can effectively overcome the limitations of traditional statistical models.
    • This AI-driven approach provides a cost-effective and efficient alternative for predicting poultry growth across different species and conditions.