Multi-objective feature selection using PSO with rough hypercuboid approach

doi:10.1016/j.asoc.2026.116524

Multi-objective feature selection using PSO with rough hypercuboid approach

2026-10-05

0

PRE

AI

DOI：10.1016/j.asoc.2026.116524

Original

Original request for help

Save

Abstract

En 中文

• Proposed RHPSON, uses PSO with an efficient RH-based fitness to optimize feature selection. • RHPSON improves accuracy and compactness by utilizing significance measure. • Introduced NSRHPSO, a multi-objective method that generates Pareto solutions via thermodynamic probability. • NSRHPSO selects gbest via thermodynamic probability, balancing convergence and diversity. • Experiments confirm that NSRHPSO significantly reduces subset size while maintaining competitive accuracy.

Keywords:

Feature selection

Multi-objective optimization

Rough hypercuboid

Particle swarm optimization

Multi-objective feature selection using PSO with rough hypercuboid approach

Abstract

Journal

Organization

Cited Papers