On the Homogenization of Data from Two Laboratories Using Genetic Programming

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

@InProceedings{conf/iwcls/Moreno-TorresLGB09,
  title =        "On the Homogenization of Data from Two Laboratories
                 Using Genetic Programming",
  author =       "Jose Garcia Moreno-Torres and Xavier Llora and 
                 David E. Goldberg and Rohit Bhargava",
  publisher =    "Springer",
  year =         "2009",
  volume =       "6471",
  booktitle =    "Learning Classifier Systems",
  series =       "Lecture Notes in Computer Science",
  editor =       "Jaume Bacardit and Will N. Browne and 
                 Jan Drugowitsch and Ester Bernad{\'o}-Mansilla and Martin V. Butz",
  isbn13 =       "978-3-642-17507-7",
  pages =        "185--197",
  keywords =     "genetic algorithms, genetic programming",
  doi =          "doi:10.1007/978-3-642-17508-4_12",
  bibdate =      "2010-11-30",
  bibsource =    "DBLP,
                 http://dblp.uni-trier.de/db/conf/iwcls/iwlcs2009.html#Moreno-TorresLGB09",
  abstract =     "In experimental sciences, diversity tends to difficult
                 predictive models' proper generalization across data
                 provided by different laboratories. Thus, training on a
                 data set produced by one lab and testing on data
                 provided by another lab usually results in low
                 classification accuracy. Despite the fact that the same
                 protocols were followed, variability on measurements
                 can introduce unforeseen variations that affect the
                 quality of the model. This paper proposes a Genetic
                 Programming based approach, where a transformation of
                 the data from the second lab is evolved driven by
                 classifier performance. A real-world problem, prostate
                 cancer diagnosis, is presented as an example where the
                 proposed approach was capable of repairing the fracture
                 between the data of two different laboratories.",
  notes =        "booktitle IWLCS. prostate cancer. Ninety three trees
                 per individual!!! C4.5. Context free grammar but rules
                 seem to be straight forward does it add anything above
                 Lisp like tree? 'one point crossover' similar to Koza's
                 sub tree crossover? Tournament size related to log(pop
                 size). Population size proportional to number of trees.
                 \cite{harris:thesis} and \cite{bot:2001:EuroGP}.
                 Re-represent 93 attributes selected on first lab's data
                 for use by same C4.5 classifier on second lab's data.
                 (Includes attributes which are not used by the final
                 C4.5 classifier). This works.

                 Solves problem but p195 do not yet give 'any useful
                 information'. Problem to complex? Too much redundant
                 information in each of the 14Gigabytes of
                 information?

                 ",
  affiliation =  "Department of Computer Science and Artificial
                 Intelligence, Universidad de Granada, 18071 Granada,
                 Spain",
}

Genetic Programming entries for Jose Garcia Moreno-Torres Xavier Llora David E Goldberg Rohit Bhargava