Sampling Methods in Genetic Programming for Classification with Unbalanced Data

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{Hunt:2010:ACAI,
  author =       "Rachel Hunt and Mark Johnston and Will N. Browne and 
                 Mengjie Zhang",
  title =        "Sampling Methods in Genetic Programming for
                 Classification with Unbalanced Data",
  booktitle =    "Australasian Conference on Artificial Intelligence",
  year =         "2010",
  editor =       "Jiuyong Li",
  volume =       "6464",
  series =       "Lecture Notes in Computer Science",
  pages =        "273--282",
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming",
  isbn13 =       "978-3-642-17431-5",
  DOI =          "doi:10.1007/978-3-642-17432-2_28",
  size =         "10 pages",
  bibdate =      "2010-11-30",
  bibsource =    "DBLP,
                 http://dblp.uni-trier.de/db/conf/ausai/ausai2010.html#HuntJBZ10",
  abstract =     "This work investigates the use of sampling methods in
                 Genetic Programming (GP) to improve the classification
                 accuracy in binary classification problems in which the
                 datasets have a class imbalance. Class imbalance occurs
                 when there are more data instances in one class than
                 the other. As a consequence of this imbalance, when
                 overall classification rate is used as the fitness
                 function, as in standard GP approaches, the result is
                 often biased towards the majority class, at the expense
                 of poor minority class accuracy. We establish that the
                 variation in training performance introduced by
                 sampling examples from the training set is no worse
                 than the variation between GP runs already accepted.
                 Results also show that the use of sampling methods
                 during training can improve minority class
                 classification accuracy and the robustness of
                 classifiers evolved, giving performance on the test set
                 better than that of those classifiers which made up the
                 training set Pareto front.",
  affiliation =  "School of Mathematics, Statistics and Operations
                 Research, Victoria University of Wellington, P.O. Box
                 600, Wellington, New Zealand",
}

Genetic Programming entries for Rachel Hunt Mark Johnston Will N Browne Mengjie Zhang

Citations