2004 | OriginalPaper | Buchkapitel
Multiobjective Optimization Based on Coevolutionary Algorithm
verfasst von : Jing Liu, Weicai Zhong, Li-cheng Jiao, Fang Liu
Erschienen in: Rough Sets and Current Trends in Computing
Verlag: Springer Berlin Heidelberg
Enthalten in: Professional Book Archive
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
With the intrinsic properties of multiobjective optimization problems in mind, multiobjective coevolutionary algorithm (MOCEA) is proposed. In MOCEA, a Pareto crossover operator, and 3 coevolutionary operators are designed for maintaining the population diversity and increasing the convergence rate. Moreover, a crowding distance is designed to reduce the size of the nondominated set. Experimental results demonstrate that MOCEA can find better solutions at a low computational cost. At the same time, the solutions found by MOCEA scatter uniformly over the entire Pareto front.