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

Empirical modelling of genetic algorithms.

R Myers1, E R Hancock

  • 1Department of Computer Science, University of York, York, Y01 5DD, UK. richs@cs.york.ac.uk

Evolutionary Computation
|November 16, 2001
PubMed
Summary

Setting genetic algorithm parameters for consistent labelling is challenging. This study introduces a robust empirical framework using factorial experiments to identify optimal parameters and understand their interactions, improving reliability.

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

The discovery of (1R, 3R)-1-(3-chloro-5-fluorophenyl)-3-(hydroxymethyl)-1,2,3,4-tetrahydroisoquinoline-6-carbonitrile, a potent and selective agonist of human transient receptor potential cation channel subfamily m member 5 (TRPM5) and evaluation of as a potential gastrointestinal prokinetic agent.

Bioorganic & medicinal chemistry·2022
Same author

Hospitalisation and mortality risk of SARS-COV-2 variant omicron sub-lineage BA.2 compared to BA.1 in England.

Nature communications·2022
Same author

Reduction of the Carbapenemase Inactivation Method (CIM) assay time by real-time PCR.

Journal of microbiological methods·2020
Same author

Molecular surveillance of measles and rubella in the WHO European Region: new challenges in the elimination phase.

Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases·2017
Same author

Experimental Demonstration of the Collisionless Plasmoid Instability below the Ion Kinetic Scale during Magnetic Reconnection.

Physical review letters·2016
Same author

Ultrasound-induced inertial cavitation from gas-stabilizing nanoparticles.

Physical review. E, Statistical, nonlinear, and soft matter physics·2015

Area of Science:

  • Computational intelligence
  • Machine learning
  • Data science

Background:

  • Genetic algorithms (GAs) are powerful optimization tools.
  • Determining optimal GA parameters for consistent labelling tasks is complex and crucial for performance.

Purpose of the Study:

  • To propose a robust empirical framework for reliably setting genetic algorithm parameters.
  • To analyze parameter interactions and identify key factors for consistent labelling problems.

Main Methods:

  • Utilized factorial experiments, including Graeco-Latin squares for initial broad analysis.
  • Employed fully crossed factorial designs with logistic regression for detailed parameter analysis.
  • Developed empirical models to predict optimal parameter settings and their importance.

Main Results:

  • Identified optimal genetic algorithm parameter settings for consistent labelling.
  • Quantified the interactions and relative importance of different parameters.
  • Demonstrated model robustness when extrapolating to larger problem sizes (up to triple).

Conclusions:

  • The proposed empirical framework provides a reliable method for optimizing genetic algorithm parameters.
  • Understanding parameter interactions is key to enhancing performance in consistent labelling tasks.
  • The derived models offer robust guidance for parameter tuning, even for scaled-up problems.

Related Experiment Videos