A hybrid approach to modeling metabolic systems using genetic algorithm and simplex method

John Yen, David Randolph, James C. Liao, Bogju Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

28 Scopus citations

Abstract

The Genetic Algorithm is applied to the parameter estimation problem to optimize a model of the glucose cycle of an E. coli cell. Since the evaleration of the model is computationally expensive, a hybrid algorithm is proposed which grafts a proposed variant of Nelder and Mead's downhill simplez-called Concurrent Simplex-with the Genetic Algorithm by using the simplez as an additional operator. The addition of the operator speeds up the rate of convergence of the Genetic Algorithm in some cases. The advantages and disadvantages of the simplez hybrid are discussed and the hybrid is tested against several diferent problem sets to verify its improvement over the generic genetic algorithm.

Original languageEnglish (US)
Title of host publicationProceedings the 11th Conference on Artificial Intelligence for Applications, CAIA 1995
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages277-283
Number of pages7
ISBN (Electronic)0818670703, 9780818670701
DOIs
StatePublished - Jan 1 1995
Event11th Conference on Artificial Intelligence for Applications, CAIA 1995 - Los Angeles, United States
Duration: Feb 20 1995Feb 23 1995

Publication series

NameProceedings the 11th Conference on Artificial Intelligence for Applications, CAIA 1995

Conference

Conference11th Conference on Artificial Intelligence for Applications, CAIA 1995
Country/TerritoryUnited States
CityLos Angeles
Period2/20/952/23/95

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'A hybrid approach to modeling metabolic systems using genetic algorithm and simplex method'. Together they form a unique fingerprint.

Cite this