Weighted operation structures to program strengths of concrete-typed specimens using genetic algorithm

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@Article{Tsai2011161,
  author =       "Hsing-Chih Tsai",
  title =        "Weighted operation structures to program strengths of
                 concrete-typed specimens using genetic algorithm",
  journal =      "Expert Systems with Applications",
  volume =       "38",
  number =       "1",
  pages =        "161--168",
  year =         "2011",
  ISSN =         "0957-4174",
  DOI =          "doi:10.1016/j.eswa.2010.06.034",
  URL =          "http://www.sciencedirect.com/science/article/pii/S0957417410005385",
  keywords =     "genetic algorithms, genetic programming, Weighted
                 formula, Prediction, Concrete strength",
  abstract =     "This study introduces weighted operation structures
                 (WOS) to program engineering problems, in which each
                 WOS adopts a fixed binary tree topology. The first WOS
                 layer serves as the parameter input entrance. The
                 target is produced at the eventual layer using both
                 values and a mathematical formula. Each WOS element is
                 operated by two front nodal inputs, an undetermined
                 function, and two undetermined weights to produce one
                 nodal output. This study proposes the novel concept of
                 introducing weights into a WOS. Doing so provides two
                 unique advantages: (1) achieving a balance between the
                 influences of two front inputs and (2) incorporating
                 weights throughout the generated formulae. Such a
                 formula is composed of a certain quantity of optimised
                 functions and weights. To determine function selections
                 and proper weights, genetic algorithm is employed for
                 optimisation. Case studies herein focused on three
                 kinds of concrete-typed specimen strengths: (1)
                 concrete compressive strength, (2) deep beam shear
                 strength, and (3) squat wall shear strength. Results
                 showed that the proposed WOS can provide accurate
                 results that nearly equal the results obtainable using
                 the familiar neural network. The weighted formula,
                 however, offers a distinct advantage in that it can be
                 programmed for practical cases.",
}

Genetic Programming entries for Hsing-Chih Tsai

Citations