Release Time:2019-03-12  Hits:

Indexed by: Conference Paper

Date of Publication: 2017-01-01

Included Journals: CPCI-S

Volume: 2017-January

Page Number: 8716-8720

Key Words: multi-objective; PSO; active learning; mutation opterator; sampling

Abstract: A multi-objective particle swarm algorithm based on the active learning (MOPSAL) approach is proposed that combines a Multi-Objective particle swarm optimization (MOPSO) with an Pareto Active Learning (PAL) approach. In MOPSAL, the candidate solution set is produced by a sampling method based on mutation operator and preselected by the PAL approach. Then, the best Pareto solution from the candidate solution set is used to guide the search of MOPSO. To validate the performance of MOPSAL, the proposed algorithm compares with the standard multi-objective particle swarm algorithm (MOPSO) and the improved non-dominated sorting genetic algorithm (NSGA-II) for five widely used benchmark problems. The results show the effectiveness of the proposed MOPSAL algorithm.