DocumentCode
3394444
Title
Fitness directed intervention crossover approaches applied to bio-scheduling problems
Author
Godley, Paul M. ; Cairns, David E. ; Cowie, Julie ; McCall, John
Author_Institution
Dept. of Comput. Sci. & Math., Univ. of Stirling, Stirling
fYear
2008
fDate
15-17 Sept. 2008
Firstpage
120
Lastpage
127
Abstract
This paper discusses the effects of using directed intervention crossover approaches with Genetic Algorithms (GA) and demonstrates their application to scheduling of bio-control agents and cancer chemotherapy treatments. Unlike traditional approaches such as Single Point Crossover (SPC) or Uniform Crossover (UC), the directed intervention techniques actively choose the intervention level based on the fitness of the parents selected for crossover. This work shows that a fitness directed intervention crossover approach leads to significant improvements over SPC and UC when applied to the two different scheduling problems.
Keywords
biology computing; cancer; genetic algorithms; genetics; patient treatment; bio-control agents; bio-scheduling problems; cancer chemotherapy; fitness directed intervention crossover approaches; genetic algorithms; single point crossover; Algorithm design and analysis; Biological cells; Biological control systems; Cancer; Crops; Drugs; Encoding; Equations; Protection; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Computational Intelligence in Bioinformatics and Computational Biology, 2008. CIBCB '08. IEEE Symposium on
Conference_Location
Sun Valley, ID
Print_ISBN
978-1-4244-1778-0
Electronic_ISBN
978-1-4244-1779-7
Type
conf
DOI
10.1109/CIBCB.2008.4675768
Filename
4675768
Link To Document