Multi-objective Optimisation by Co-operative Co-evolution

Maneeratana, Kuntinee; Boonlong, Kittipong; Chaiyaratana, Nachol

doi:10.1007/978-3-540-30217-9_78

Cited by 25 publications

(17 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Purshouse and Fleming [66] considered a divide-and-conquer strategy that converts a multiobjective problem into several sub-problems, each of which has an "independent" set of objectives. In addition, some co-evolution and island model based approaches used the idea of parallel search to divide an MOP into several subproblems regarding the objective space [75] or the decision space [61]. However, an interesting difference between SDE and the above approaches lies in that the transformation of all the above approaches tries to make a given problem easier, while the transformation of SDE tries to make Pareto-based algorithms suitable for a type of harder problems-manyobjective optimization problems.…”

Section: Discussionmentioning

confidence: 99%

Shift-Based Density Estimation for Pareto-Based Algorithms in Many-Objective Optimization

Yang

Liu

2014

IEEE Trans. Evol. Computat.

587

248

View full text Add to dashboard Cite

Abstract-It is commonly accepted that Pareto-based evolutionary multiobjective optimization (EMO) algorithms encounter difficulties in dealing with many-objective problems. In these algorithms, the ineffectiveness of the Pareto dominance relation for a high-dimensional space leads diversity maintenance mechanisms to play the leading role during the evolutionary process, while the preference of diversity maintenance mechanisms for individuals in sparse regions results in the final solutions distributed widely over the objective space but distant from the desired Pareto front. Intuitively, there are two ways to address this problem: 1) modifying the Pareto dominance relation and 2) modifying the diversity maintenance mechanism in the algorithm. In this paper, we focus on the latter and propose a shift-based density estimation (SDE) strategy. The aim of our study is to develop a general modification of density estimation in order to make Pareto-based algorithms suitable for many-objective optimization. In contrast to traditional density estimation which only involves the distribution of individuals in the population, SDE covers both the distribution and convergence information of individuals. The application of SDE in three popular Paretobased algorithms demonstrates its usefulness in handling manyobjective problems. Moreover, an extensive comparison with five state-of-the-art EMO algorithms reveals its competitiveness in balancing convergence and diversity of solutions. These findings not only show that SDE is a good alternative to tackle manyobjective problems, but also present a general extension of Paretobased algorithms in many-objective optimization.

show abstract

Section: Discussionmentioning

confidence: 99%

Shift-Based Density Estimation for Pareto-Based Algorithms in Many-Objective Optimization

Yang

Liu

2014

IEEE Trans. Evol. Computat.

587

248

View full text Add to dashboard Cite

show abstract

“…This phenomenon has been observed in the early work by Sangkawelert and Chaiyaratana (2003) where the obtained values of M 3 from various test problems cannot be properly used to evaluate the performance of the MODCGA. Based on the previous work, the use of M 3 index as a performance indicator is not recommended and further modification of the M 3 index is required (Maneeratana et al, 2004). Although the measurement criteria discussed here are defined for calculations using objective vectors, the alternative criteria, which are defined for decision vectors, have also been discussed in Zitzler et al (2000).…”

Section: Test Problem Dtlz6mentioning

confidence: 99%

Effects of diversity control in single-objective and multi-objective genetic algorithms

2006

Self Cite

View full text Add to dashboard Cite

This paper covers an investigation on the effects of diversity control in the search performances of single-objective and multi-objective genetic algorithms. The diversity control is achieved by means of eliminating duplicated individuals in the population and dictating the survival of non-elite individuals via either a deterministic or a stochastic selection scheme. In the case of single-objective genetic algorithm, onemax and royal road R 1 functions are used during benchmarking. In contrast, various multi-objective benchmark problems with specific characteristics are utilised in the case of multi-objective genetic algorithm. The results indicate that the use of diversity control with a correct parameter setting helps to prevent premature convergence in single-objective optimisation. Furthermore, the use of diversity control also promotes the emergence of multi-objective solutions that are close to the true Pareto optimal solutions while maintaining a uniform solution distribution along the Pareto front.

show abstract

“…By partitioning the problem in this manner, the search space that each population has to cover would significantly reduce [23]. In [8], two evolutions coevolved in parallel one of which was an evolution of fuzzy rule bases that produced suitable control parameter values for a second allowing the genetic operator to show an adequate performance.…”

Section: Parallel Evolutionmentioning

confidence: 99%

Synthesis of Time-to-Amplitude Converter by Mean CoeVolution with Adaptive Parameters

Sapargaliyev¹,

Kalganova

2011

JSEA

View full text Add to dashboard Cite

show abstract

Multi-objective Optimisation by Co-operative Co-evolution

Cited by 25 publications

References 14 publications

Shift-Based Density Estimation for Pareto-Based Algorithms in Many-Objective Optimization

Shift-Based Density Estimation for Pareto-Based Algorithms in Many-Objective Optimization

Effects of diversity control in single-objective and multi-objective genetic algorithms

Synthesis of Time-to-Amplitude Converter by Mean CoeVolution with Adaptive Parameters

Contact Info

Product

Resources

About