Multi-parent recombination with simplex crossover in real coded genetic algorithms 论文

1999Tokyo Tech Research Repository (Tokyo Institute of Technology)引用 320
Metaheuristic Optimization Algorithms ResearchAdvanced Multi-Objective Optimization AlgorithmsGreenhouse Technology and Climate Control

摘要

In this paper, we proposed simplex crossover (SPX), a multi-parent recombination operator for real-coded genetic algorithms. SPX generates offspring vector values by uniformly sampling values from simplex formed by m (2 ≤ m ≤ number of parameters + 1) parent vectors. The SPX features an independence from of coordinate systems. Experimental results using test functions, which are commonly used in studies of evolutionary algorithms, showed SPX works well on functions having multimodality and/or epistasis with a medium number of parents: 3-parent on a low dimensional function or 4 parents on high dimensional functions.