Filter-based optimization techniques for selection of feature subsets in ensemble systems
作者：
Highlights：
• We analyzed optimized techniques for feature selection in ensemble systems.
• We used particle swarm optimization, ant-colony optimization and genetic algorithms.
• The feature selection process was based on two filter-based evaluation criteria.
• The evaluation criteria tried to capture the idea of individual and group diversity.
• The use of PSO with a bi-objective function will be the most promising direction.
摘要
•We analyzed optimized techniques for feature selection in ensemble systems.•We used particle swarm optimization, ant-colony optimization and genetic algorithms.•The feature selection process was based on two filter-based evaluation criteria.•The evaluation criteria tried to capture the idea of individual and group diversity.•The use of PSO with a bi-objective function will be the most promising direction.
论文关键词：Ensemble systems,Feature selection,Particle swarm optimization,Ant colony optimization,Genetic algorithms
论文评审过程：Available online 4 September 2013.
论文官网地址：https://doi.org/10.1016/j.eswa.2013.08.059
