A comparison of binary and continuous genetic algorithm in parameter estimation of a logistic growth model

Windarto, S. W. Indratno, N. Nuraini, E. Soewono

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Citations (Scopus)

Abstract

Genetic algorithm is an optimization method based on the principles of genetics and natural selection in life organisms. The algorithm begins by defining the optimization variables, defining the cost function (in a minimization problem) or the fitness function (in a maximization problem) and selecting genetic algorithm parameters. The main procedures in genetic algorithm are generating initial population, selecting some chromosomes (individual) as parent's individual, mating, and mutation. In this paper, binary and continuous genetic algorithms were implemented to estimate growth rate and carrying capacity parameter from poultry data cited from literature. For simplicity, all genetic algorithm parameters (selection rate and mutation rate) are set to be constant along implementation of the algorithm. It was found that by selecting suitable mutation rate, both algorithms can estimate these parameters well. Suitable range for mutation rate in continuous genetic algorithm is wider than the binary one.

Original languageEnglish
Title of host publicationSymposium on Biomathematics, Symomath 2013
EditorsNuning Nuraini, Hidetaka Arimura
PublisherAmerican Institute of Physics Inc.
Pages139-142
Number of pages4
ISBN (Electronic)9780735412194
DOIs
Publication statusPublished - 2014
EventSymposium on Biomathematics, Symomath 2013 - Bandung, West Java, Indonesia
Duration: 27 Oct 201329 Oct 2013

Publication series

NameAIP Conference Proceedings
Volume1587
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616

Conference

ConferenceSymposium on Biomathematics, Symomath 2013
Country/TerritoryIndonesia
CityBandung, West Java
Period27/10/1329/10/13

Keywords

  • dynamical model
  • genetic algorithm
  • parameter estimation
  • poultry data

Fingerprint

Dive into the research topics of 'A comparison of binary and continuous genetic algorithm in parameter estimation of a logistic growth model'. Together they form a unique fingerprint.

Cite this