Uncertainty analysis of an evolutionary algorithm to develop remote sensing spectral indices

Created by W.Langdon from gp-bibliography.bib Revision:1.4216

  author =       "Henrique G Momm and Greg Easson and Joel Kuszmaul",
  title =        "Uncertainty analysis of an evolutionary algorithm to
                 develop remote sensing spectral indices",
  booktitle =    "Image Processing: Algorithms and Systems VI",
  year =         "2008",
  editor =       "Jaakko T. Astola and Karen O. Egiazarian and 
                 Edward R. Dougherty",
  volume =       "6812",
  pages =        "68120A.1--68120A.9",
  address =      "San Jose, California, USA",
  month =        "28 " # jan,
  publisher =    "SPIE--The International Society for Optical
  keywords =     "genetic algorithms, genetic programming",
  DOI =          "DOI:10.1117/12.766367",
  abstract =     "The need for information extracted from remotely
                 sensed data has increased in recent decades. To address
                 this issue, research is being conducted to develop a
                 complete multi-stage supervised object recognition
                 system. The first stage of this system couples genetic
                 programming with standard unsupervised clustering
                 algorithms to search for the optimal preprocessing
                 function. This manuscript addresses the quantification
                 and the characterisation of the uncertainty involved in
                 the random creation of the first set of candidate
                 solutions from which the algorithm begins. We used a
                 Monte Carlo type simulation involving 800 independent
                 realisations and then analyzed the distribution of the
                 final results. Two independent convergence approaches
                 were investigated: [1] convergence based solely on
                 genetic operations (standard) and [2] convergence based
                 on genetic operations with subsequent insertion of new
                 genetic material (restarting). Results indicate that
                 the introduction of new genetic material should be
                 incorporated into the preprocessing framework to
                 enhance convergence and to reduce variability.",

Genetic Programming entries for Henrique G Momm Greg Easson Joel S Kuszmaul