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

Master-Leader-Slave Cuckoo Search with Parameter Control for ANN Optimization and Its Real-World Application to Water

Najmeh Sadat Jaddi1, Salwani Abdullah1, Marlinda Abdul Malek2

  • 1Data Mining and Optimization Research Group (DMO), Centre for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan, Malaysia, Bangi, Selangor, Malaysia.

Plos One
|January 27, 2017
PubMed
Summary

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

A multi-strategy framework for enhancing Harris hawks optimization for global optimization problems.

Scientific reports·2026
Same author

Retraction Note: Microwave radiation-induced grafting of 2-methacryloyloxyethyl trimethyl ammonium chloride onto lentil extract (LE-g-DMC) as an emerging high-performance plant-based grafted coagulant.

Scientific reports·2026
Same author

Water impact analysis due to coal-electricity generation using the life cycle assessment method: a case study in Malaysia.

Water science and technology : a journal of the International Association on Water Pollution Research·2025
Same author

A related convolutional neural network for cancer diagnosis using microRNA data classification.

Healthcare technology letters·2024
Same author

Water footprint assessment at the ultra-supercritical (USC) coal power plant in Malaysia.

Environmental monitoring and assessment·2024
Same author

Clustering analysis for classifying fake real estate listings.

PeerJ. Computer science·2024

This study introduces an optimized artificial neural network (ANN) model selection using a modified cuckoo search (CS) algorithm. The enhanced CS algorithm improves convergence for complex prediction tasks.

Area of Science:

  • Artificial Intelligence
  • Computational Intelligence
  • Optimization Algorithms

Background:

  • Artificial neural networks (ANNs) are widely used but require careful model selection and weight optimization for accuracy.
  • The cuckoo search (CS) algorithm, inspired by cuckoo brood parasitism, is a metaheuristic optimization technique.
  • Basic CS has limitations in convergence speed and parameter tuning, particularly the nest replacement rate (Pa).

Purpose of the Study:

  • To propose an enhanced cuckoo search (CS) algorithm for optimizing artificial neural network (ANN) model selection.
  • To improve the convergence ability and performance of the standard CS algorithm.
  • To apply the optimized ANN selection strategy to benchmark and real-world prediction problems.

Main Methods:

Related Experiment Videos

  • Modification of the CS algorithm by dynamically adjusting the nest replacement rate (Pa) from maximum to minimum over iterations.
  • Implementation of a master-leader-slave multi-population strategy to enhance exploration and exploitation.
  • Utilizing the best fitness function among slaves, selected by a leader, for subsequent Lévy flights.

    • Main Results:

    • The modified CS algorithm demonstrated improved convergence and effectiveness in ANN model selection.
    • Statistical analysis confirmed the method's ability on benchmark classification and time series prediction tasks.
    • Promising results were achieved when applied to a real-world water quality prediction problem.

    Conclusions:

    • The proposed enhanced CS algorithm offers a robust optimization strategy for ANN model selection.
    • Dynamic adjustment of Pa and the multi-population approach significantly improve search performance.
    • The method shows practical applicability and effectiveness in diverse prediction scenarios.