Feature Subset Selection by Neuro-rough Hybridization

摘要: Feature subset selection is of prime importance in pattern classification, machine learning and data mining applications. Though statistical techniques are well developed mathematically sound, they inappropriate for dealing real world cognitive problems containing imprecise ambiguous information. Soft computing tools like artificial neural network, genetic algorithm fuzzy logic, rough set theory their integration developing hybrid algorithms handling life recently found to be the most effective. In this worka neurorough has been proposed which concepts used finding an initial efficient features followed by a stage find out ultimate best feature subset. The reduction original results smaller structure quicker as whole seems provide better performance than any from individual paradigm evident simulation results.