Modeling Aggressive Behaviors With Evolutionary Taxonomers

Created by W.Langdon from gp-bibliography.bib Revision:1.3963

@Article{Theodoridis:2013:ieeeHMS,
  author =       "Theodoros Theodoridis and Huosheng Hu",
  title =        "Modeling Aggressive Behaviors With Evolutionary
                 Taxonomers",
  journal =      "IEEE Transactions on Human-Machine Systems",
  year =         "2013",
  volume =       "43",
  number =       "3",
  pages =        "302--313",
  month =        may,
  keywords =     "genetic algorithms, genetic programming, Action
                 recognition, Gaussian fitness models, biomechanical
                 primitives, time-series classification",
  ISSN =         "2168-2291",
  DOI =          "doi:10.1109/TSMC.2013.2252337",
  size =         "12 pages",
  abstract =     "The pivotal idea of recognising human aggressive
                 behaviours underlines how a taxonomer models such
                 actions to perform recognition. In this paper, we
                 investigate both the recognition and modelling of
                 aggressive behaviors using kinematic (3-D) and
                 electromyographic performance data. For this purpose,
                 the Gaussian ground-plan projection area model has been
                 assessed as an excellent evolutionary paradigm for the
                 multiclass action and behaviour recognition problem. In
                 fact, it has shown superior classification accuracy
                 with and without the use of ensemble models compared
                 with the standard Gaussian (distance and area) models
                 and other metrics of divergence, when dedicated groups
                 of actions (behaviors) are being modelled. Genetic
                 Programming is being employed to construct
                 behavior-based taxonomers with a biomechanical
                 primitive language. The modeling process revealed a
                 representative subset of parameters (limbs, body
                 segments, and marker coordinates) that are selected
                 through the evolutionary process.",
  notes =        "Also known as \cite{6502260}",
}

Genetic Programming entries for Theodoros Theodoridis Huosheng Hu

Citations