Multi-objective genetic algorithms: A way to improve the convergence rate |
| |
| Affiliation: | 1. EA 4174, Université Lyon 1, Lyon, France;2. HemaCore LLC, Moscow, Russia;3. Center for Theoretical Problems of Physico-Chemical Pharmacology, Moscow, Russia,;4. Federal Research and Clinical Center of Pediatric Hematology, Oncology and Immunology, Moscow, Russia;5. National Research Center for Hematology, Moscow, Russia;6. Physics Department, Moscow State University, Moscow, Russia;7. Unite d’Hemostase Clinique, Hopital Edouard Herriot, Lyon, France;1. School of Mathematics, Sun Yat-sen University, Guangzhou 510275, China;2. Guangdong Province Key Laboratory of Computational Science, China;3. College of Mathematics and Statistics, Shenzhen University, Shenzhen 518060, China;4. Shenzhen Key Laboratory of Advanced Machine Learning and Applications, Shenzhen University, Shenzhen 518060, China |
| |
| Abstract: | ![]()
Multi-objective optimization is generally a time consuming step of the design process. In this paper, a Pareto based multi-objective genetic algorithm is proposed, which enables a faster convergence without degrading the estimated set of solutions. Indeed, the population diversity is correctly conserved during the optimization process; moreover, the solutions belonging to the frontier are equally distributed along the frontier. This improvement is due to an extension function based on a natural phenomenon, which is similar to a cyclical epidemic which happens every N generations (eN-MOGA). The use of this function enables a faster convergence of the algorithm by reducing the necessary number of generations. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
