China 
Africa 
Explore chapters and articles related to this topic
Intelligent Optimization Techniques for Manufacturing Optimization Problems
Published in R. Saravanan, Manufacturing Optimization through Intelligent Techniques, 2017
After deciding on coding, the second decision to make in using a genetic algorithm is how to perform the selection — that is, how to chose the individuals in the population that will create offspring for the next generation and how many offspring each will create. The purpose of selection is, of course, to emphasize fitter individuals in the population, in hopes that their offspring will, in turn, have even higher fitness. Selection must be balanced with variation from crossover and mutation (the “exploitation/exploration balance”): too strong selection means that suboptimal, highly fit individuals will take over the population, reducing the diversity needed for further change and progress; too weak selection will result in too slow evolution. As was the case for encodings, numerous selection schemes have been proposed in the GA literature.
Genetic Algorithms for Optimization
Published in Adrian A. Hopgood, Intelligent Systems for Engineers and Scientists, 2021
During the later stages of evolution, a successful algorithm would have finished exploring the search space and would be exploiting the region of the global optimum. The differences between the population fitnesses can be relatively small at this stage, leading to weak selection and stalled evolution. The application of fitness scaling at these late stages of evolution is intended to strengthen the selection pressure in order to converge near the exact optimum. Fitness scaling counters stalled evolution by spreading out the selection rates for the population in the later stages.
Integrated scheduling algorithm based on an operation relationship matrix table for tree-structured products
Published in International Journal of Production Research, 2018
Qi Lei, Weifei Guo, Yuchuan Song
The selection of operators embodies the idea of survival of the fittest, that is, high-performance individuals are maximised for preservation, which improves the overall convergence and computational efficiency. Strong selection pressure may lead to premature convergence and a local optimum, whereas weak selection pressure may slow down the optimisation process. Thus, stochastic universal sampling, which selects individuals randomly and equidistantly, is chosen. This sampling method not only calculates the probability of selecting a roulette wheel selection, but also maintains the population diversity for a relatively long time.