Extrapolatable Analytical Functions for Tendon Excursions and Moment Arms From Sparse Datasets

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@Article{Kurse:2012:ieeeBE,
  author =       "Manish U. Kurse and Hod Lipson and 
                 Francisco J. Valero-Cuevas",
  title =        "Extrapolatable Analytical Functions for Tendon
                 Excursions and Moment Arms From Sparse Datasets",
  journal =      "IEEE Transactions on Biomedical Engineering",
  year =         "2012",
  month =        jun,
  volume =       "59",
  number =       "6",
  pages =        "1572--1582",
  size =         "11 pages",
  abstract =     "Computationally efficient modelling of complex
                 neuromuscular systems for dynamics and control
                 simulations often requires accurate analytical
                 expressions for moment arms over the entire range of
                 motion. Conventionally, polynomial expressions are
                 regressed from experimental data. But these polynomial
                 regressions can fail to extrapolate, may require large
                 datasets to train, are not robust to noise, and often
                 have numerous free parameters. We present a novel
                 method that simultaneously estimates both the form and
                 parameter values of arbitrary analytical expressions
                 for tendon excursions and moment arms over the entire
                 range of motion from sparse datasets. This symbolic
                 regression method based on genetic programming has been
                 shown to find the appropriate form of mathematical
                 expressions that capture the physics of mechanical
                 systems. We demonstrate this method by applying it to
                 1) experimental data from a physical tendon-driven
                 robotic system with arbitrarily routed multiarticular
                 tendons and 2) synthetic data from musculoskeletal
                 models. We show it outperforms polynomial regressions
                 in the amount of training data, ability to extrapolate,
                 robustness to noise, and representation containing
                 fewer parameters-all critical to realistic and
                 efficient computational modelling of complex
                 musculoskeletal systems.",
  keywords =     "genetic algorithms, genetic programming, complex
                 neuromuscular system, control simulation, dynamics
                 simulation, extrapolatable analytical function, moment
                 arms, multiarticular tendon, musculoskeletal model,
                 physical tendon-driven robotic system, sparse datasets,
                 symbolic regression method, tendon excursion, bone,
                 extrapolation, medical robotics, muscle, neuromuscular
                 stimulation, regression analysis",
  DOI =          "doi:10.1109/TBME.2012.2189771",
  ISSN =         "0018-9294",
  notes =        "Also known as \cite{6164249}",
}

Genetic Programming entries for Manish U Kurse Hod Lipson Francisco Valero-Cuevas

Citations