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

Evaluating the epsilon-domination based multi-objective evolutionary algorithm for a quick computation of

Kalyanmoy Deb1, Manikanth Mohan, Shikhar Mishra

  • 1Kanpur Genetic Algorithms Laboratory (KanGAL), Indian Institute of Technology Kanpur, Kanpur, PIN 208016, INDIA. deb@iitk.ac.in

Evolutionary Computation
|November 22, 2005
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

Laser-assisted cranial bone drilling in neurosurgery: Translational potential, current evidence, and future integration with robotic systems - A systematic review.

Surgical neurology international·2026
Same author

Artificial Intelligence, Optimization, and Modeling Techniques in Water Resources Management: Challenges and Future Directions.

Water environment research : a research publication of the Water Environment Federation·2026
Same author

Artificial Intelligence, Optimization, and Modeling Techniques in Water Resource Management: Interconnections and Emerging Synergies.

Water environment research : a research publication of the Water Environment Federation·2026
Same author

Toward Interpretable-AI Policies Using Evolutionary Nonlinear Decision Trees for Discrete-Action Systems.

IEEE transactions on cybernetics·2022
Same author

Quantifying splice-site usage: a simple yet powerful approach to analyze splicing.

NAR genomics and bioinformatics·2021
Same author

Neural Architecture Transfer.

IEEE transactions on pattern analysis and machine intelligence·2021

A new steady-state multi-objective evolutionary algorithm (MOEA) offers a practical balance between computational speed and the quality of Pareto-optimal solutions. This epsilon-dominance based approach achieves good convergence and distribution efficiently.

Area of Science:

  • Computational Intelligence
  • Optimization Algorithms
  • Multi-Objective Optimization

Background:

  • Multi-objective optimization problems (MOPs) require finding multiple Pareto-optimal solutions.
  • Existing multi-objective evolutionary algorithms (MOEAs) often trade off computational speed for solution quality (convergence and distribution).
  • Algorithms like SPEA and NSGA-II demonstrate this trade-off, with SPEA offering better distribution but requiring more computation.

Purpose of the Study:

  • To evaluate a recently proposed steady-state MOEA based on epsilon-dominance.
  • To assess its performance in achieving a well-distributed and well-converged set of Pareto-optimal solutions quickly.
  • To determine if this MOEA offers a pragmatic compromise between speed and solution quality.

Main Methods:

Related Experiment Videos

  • The study evaluates a steady-state MOEA incorporating the epsilon-dominance concept.
  • Efficient parent and archive update strategies are employed.
  • An extensive comparative study was conducted against four other state-of-the-art MOEAs on various objective test problems (2, 3, and 4 objectives).

Main Results:

  • The steady-state MOEA demonstrates a favorable balance between convergence to the Pareto-optimal front, diversity of solutions, and computational time.
  • It performs competitively compared to existing state-of-the-art MOEAs.
  • The epsilon-MOEA allows for control over the achievable accuracy of Pareto-optimal solutions.

Conclusions:

  • The evaluated steady-state MOEA provides a practical and efficient approach to multi-objective optimization.
  • It represents a significant step towards making MOEAs more pragmatic for decision-making.
  • The algorithm effectively balances computational efficiency with the generation of high-quality Pareto-optimal solution sets.