Genetic Programming for Feature Ranking in Classification Problems

Created by W.Langdon from gp-bibliography.bib Revision:1.4524

  author =       "Kourosh Neshatian and Mengjie Zhang and 
                 Peter Andreae",
  title =        "Genetic Programming for Feature Ranking in
                 Classification Problems",
  booktitle =    "Proceedings of the 7th International Conference on
                 Simulated Evolution And Learning (SEAL '08)",
  year =         "2008",
  editor =       "Xiaodong Li and Michael Kirley and Mengjie Zhang and 
                 David G. Green and Victor Ciesielski and 
                 Hussein A. Abbass and Zbigniew Michalewicz and Tim Hendtlass and 
                 Kalyanmoy Deb and Kay Chen Tan and 
                 J{\"u}rgen Branke and Yuhui Shi",
  volume =       "5361",
  series =       "Lecture Notes in Computer Science",
  pages =        "544--554",
  address =      "Melbourne, Australia",
  month =        dec # " 7-10",
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming",
  isbn13 =       "978-3-540-89693-7",
  DOI =          "doi:10.1007/978-3-540-89694-4_55",
  abstract =     "Feature ranking (FR) provides a measure of usefulness
                 for the attributes of a classification task. Most
                 existing FR methods focus on the relevance of a single
                 feature to the class labels. Here, we use GP to see how
                 a set of features can contribute towards discriminating
                 different classes and then we score the participating
                 features accordingly. The scoring mechanism is based on
                 the frequency of appearance of each feature in a
                 collection of GP programs and the fitness of those
                 programs. Our results show that the proposed FR method
                 can detect important features of a problem. A variety
                 of different classifiers restricted to just a few of
                 these high-ranked features work well. The ranking
                 mechanism can also shrink the search space of size
                 O(2**n) of subsets of features to a search space of
                 size O(n) in which there are points that may improve
                 the classification performance.",
  bibsource =    "DBLP,",
  notes =        "Features selected by GP fed into: J48 (C4.5), naive
                 Bayes, SMO SVM (Weka, Java). p552 oerformance does
                 _not_ improve montonically with additional (lower
                 ranked) features.",

Genetic Programming entries for Kourosh Neshatian Mengjie Zhang Peter Andreae