Feature fitness evaluation for symbolic regression via genetic programming

Created by W.Langdon from gp-bibliography.bib Revision:1.8081

@InProceedings{Lu:2011:ICNC,

• author = "Qiang Lu and Bin Wang",
• title = "Feature fitness evaluation for symbolic regression via genetic programming",
• booktitle = "Seventh International Conference on Natural Computation (ICNC 2011)",
• year = "2011",
• month = "26-28 " # jul,
• volume = "2",
• pages = "1087--1091",
• address = "Shanghai",
• size = "5 pages",
• abstract = "In this paper, feature fitness evaluation method is proposed for accelerating the speed of evolution in symbolic regression. Through analysing the feature of curve or surface which train data represents, vertex and inflection points are extracted from the train data. According to the feature data and diversity of population, the test data for evolution of genetic programming (GP) are generated dynamically. The method was implemented by using GP and genetic expression programming(GEP). Results show that the method in GP, compared with classic GP and GEP, has benefits about efficient of computation, regression performance and avoiding premature convergence.",
• keywords = "genetic algorithms, genetic programming, gene expression programming, GEP, data representation, feature fitness evaluation, genetic expression programming, inflection points, symbolic regression, vertex points, regression analysis",
• DOI = "doi:10.1109/ICNC.2011.6022150",
• ISSN = "2157-9555",
• notes = "Also known as \cite{6022150}",

}

Genetic Programming entries for Qiang Lu Bin Wang

Citations