Investigating fitness functions for a hyper-heuristic evolutionary algorithm in the context of balanced and imbalanced data classification

Created by W.Langdon from gp-bibliography.bib Revision:1.3963

@Article{Barros:2015:GPEM,
  author =       "Rodrigo C. Barros and Marcio P. Basgalupp and 
                 Andre C. P. L. F. {de Carvalho}",
  title =        "Investigating fitness functions for a hyper-heuristic
                 evolutionary algorithm in the context of balanced and
                 imbalanced data classification",
  journal =      "Genetic Programming and Evolvable Machines",
  year =         "2015",
  volume =       "16",
  number =       "3",
  pages =        "241--281",
  month =        sep,
  keywords =     "genetic algorithms, genetic programming,
                 Hyper-heuristics, Decision trees, Fitness function,
                 Imbalanced data",
  ISSN =         "1389-2576",
  DOI =          "doi:10.1007/s10710-014-9235-z",
  size =         "41 pages",
  abstract =     "In this paper, we analyse in detail the impact of
                 different strategies to be used as fitness function
                 during the evolutionary cycle of a hyper-heuristic
                 evolutionary algorithm that automatically designs
                 decision-tree induction algorithms (HEAD-DT). We divide
                 the experimental scheme into two distinct scenarios:
                 (1) evolving a decision-tree induction algorithm from
                 multiple balanced data sets; and (2) evolving a
                 decision-tree induction algorithm from multiple
                 imbalanced data sets. In each of these scenarios, we
                 analyse the difference in performance of well-known
                 classification performance measures such as accuracy,
                 F-Measure, AUC, recall, and also a lesser-known
                 criterion, namely the relative accuracy improvement. In
                 addition, we analyse different schemes of aggregation,
                 such as simple average, median, and harmonic mean.
                 Finally, we verify whether the best-performing fitness
                 functions are capable of providing HEAD-DT with
                 algorithms more effective than traditional
                 decision-tree induction algorithms like C4.5, CART, and
                 REPTree. Experimental results indicate that HEAD-DT is
                 a good option for generating algorithms tailored to
                 (im)balanced data, since it outperforms
                 state-of-the-art decision-tree induction algorithms
                 with statistical significance.",
  notes =        "Author Affiliations

                 1. Faculdade de Informatica (FACIN), Pontificia
                 Universidade Catolica do Rio Grande do Sul (PUCRS),
                 Porto Alegre, Brazil 2. Instituto de Ciencia e
                 Tecnologia (ICT), Universidade Federal de Sao Paulo
                 (UNIFESP), Sao Josedos Campos, Brazil 3. Instituto de
                 Ciencias Matematicas e de Computacao (ICMC),
                 Universidade de Sao Paulo (USP), Sao Carlos, Brazil

                 ",
}

Genetic Programming entries for Rodrigo C Barros Marcio Porto Basgalupp Andre Ponce de Leon F de Carvalho

Citations