Training genetic programming on half a million patterns: an example from anomaly detection

Created by W.Langdon from gp-bibliography.bib Revision:1.2031

@Article{song:2005:TEC,
  author =       "Dong Song and Malcolm I. Heywood and 
                 A. Nur Zincir-Heywood",
  title =        "Training genetic programming on half a million
                 patterns: an example from anomaly detection",
  journal =      "IEEE Transactions on Evolutionary Computation",
  year =         "2005",
  volume =       "9",
  number =       "3",
  pages =        "225--239",
  month =        jun,
  ISSN =         "1089-778X",
  keywords =     "genetic algorithms, genetic programming, data mining,
                 genetic algorithms, learning (artificial intelligence),
                 security of data, anomaly detection, genetic
                 programming training, hierarchical RSS-DSS algorithm,
                 hierarchical fitness functions, large dataset dynamical
                 filtering, real-world KDD-99 intrusion detection data
                 set,Dynamic subset selection (DSS), hierarchical cost
                 function, intrusion detection, large data sets",
  doi =          "doi:10.1109/TEVC.2004.841683",
  size =         "15 pages",
  abstract =     "The hierarchical RSS-DSS algorithm is introduced for
                 dynamically filtering large datasets based on the
                 concepts of training pattern age and difficulty, while
                 using a data structure to facilitate the efficient use
                 of memory hierarchies. Such a scheme provides the basis
                 for training genetic programming (GP) on a data set of
                 half a million patterns in 15 min. The method is
                 generic, thus, not specific to a particular GP
                 structure, computing platform, or application context.
                 The method is demonstrated on the real-world KDD-99
                 intrusion detection data set, resulting in solutions
                 competitive with those identified in the original
                 KDD-99 competition, while only using a fraction of the
                 original features. Parameters of the RSS-DSS algorithm
                 are demonstrated to be effective over a wide range of
                 values. An analysis of different cost functions
                 indicates that hierarchical fitness functions provide
                 the most effective solutions.",
  notes =        "INSPEC Accession Number: 8458415

                 Quest Software Inc., Halifax, NS, Canada

                 p226 only uses {"}8 of 41 features{"}. Linear GP, L-GP.
                 p227 {"}No benefits were observed in making such a
                 mutation operator field specific{"} p235 {"}not all
                 training set patterns are equally significant{"}

                 ",
}

Genetic Programming entries for Dong Song Malcolm Heywood Nur Zincir-Heywood