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

Hybrid genetic algorithms for feature selection.

Il-Seok Oh1, Jin-Seon Lee, Byung-Ro Moon

  • 1Division of Electronics and Computer Engineering, Chonbuk National University, Jeonju, Chonbuk 561-756, Korea. isoh@chonbuk.ac.kr

IEEE Transactions on Pattern Analysis and Machine Intelligence
|November 4, 2004
PubMed
Summary
This summary is machine-generated.

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

Cross-channel feature transfer 3D U-Net for automatic segmentation of the perilymph and endolymph fluid spaces in hydrops MRI.

Computers in biology and medicine·2025
Same author

Gripping Success Metric for Robotic Fruit Harvesting.

Sensors (Basel, Switzerland)·2025
Same author

Automated volumetric analysis of the inner ear fluid space from hydrops magnetic resonance imaging using 3D neural networks.

Scientific reports·2024
Same author

Effectiveness of Human-Artificial Intelligence Collaboration in Cephalometric Landmark Detection.

Journal of personalized medicine·2022
Same author

Correction to: Diagnosis of schizophrenia with functional connectome data: a graph-based convolutional neural network approach.

BMC neuroscience·2022
Same author

Diagnosis of schizophrenia with functional connectome data: a graph-based convolutional neural network approach.

BMC neuroscience·2022

This study introduces a hybrid genetic algorithm (GA) for improved feature selection. The novel approach enhances performance and provides subset-size control, outperforming traditional methods.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Feature selection is crucial for optimizing machine learning model performance and efficiency.
  • Traditional genetic algorithms (GAs) can be enhanced for more effective feature selection.
  • Controlling the size of selected feature subsets is a key challenge.

Purpose of the Study:

  • To propose a novel hybrid genetic algorithm (GA) for effective feature selection.
  • To integrate local search operations into GAs for refined search capabilities.
  • To analyze and compare the performance and timing requirements of the proposed hybrid GA against conventional methods.

Main Methods:

  • Development of a hybrid genetic algorithm (GA) incorporating local search operations.

Related Experiment Videos

  • Parameterization of local search operations to control their fine-tuning power.
  • Rigorous timing analysis to compare computational requirements of algorithms.
  • Experimental evaluation using standard datasets to assess performance.

    • Main Results:

    • The hybrid GA demonstrated superior convergence properties compared to classical GAs.
    • The hybridization technique significantly improved final performance and enabled subset-size control.
    • Experimental results confirmed the hybrid GA's superiority over simple GAs and sequential search algorithms.
    • Timing analysis provided insights into the efficiency of the proposed method.

    Conclusions:

    • The proposed hybrid genetic algorithm offers a powerful and efficient approach to feature selection.
    • Integration of local search enhances GA performance and provides valuable subset-size control.
    • The hybrid GA represents a significant advancement over existing feature selection techniques.