DocumentCode
1638400
Title
On A Novel Clonal Chaos Adjustment Algorithm
Author
Lu, Hong ; Zhichun, Mu
Author_Institution
Univ. of Sci. & Technol. Beijing, Beijing
fYear
2007
Firstpage
710
Lastpage
714
Abstract
A new immune algorithm - the clonal chaos adjustment algorithm (CCAA) is proposed by integrating the chaos mechanism on the basis of the clonal selection principle and idiotypic immune network theory exhibited in biological immune system. Taking advantages of the ergodic and stochastic properties of chaos logistic equation, an adaptive chaos mutation operator is designed by the combination of prior knowledge of antibody and evolution iterations. The operator can avoid blind research and enhance the convergent speed effectively. By using stochastic processes theory as the mathematical tools, the martingale characteristic of the average fitness function of the population is analyzed and the almost sure strong convergence of CCAA is deduced. In the simulation experiments of multi-modal function optimization, the results verify that the theory convergent conclusion proven above is right, and also show that CCAA can inhibit prematurity and has preferable global convergent ability and stability.
Keywords
chaos; optimisation; stochastic processes; adaptive chaos mutation operator; average fitness function; biological immune system; chaos logistic equation; chaos mechanism; clonal chaos adjustment algorithm; clonal selection principle; ergodic properties; idiotypic immune network theory; immune algorithm; martingale characteristic; multi-modal function optimization; stochastic processes; stochastic properties; theory convergent conclusion; Chaos; Convergence; Electronic mail; Equations; Evolution (biology); Genetic mutations; Immune system; Logistics; Stability; Stochastic processes; almost sure strong convergence; chaos; clonal selection mechanism; martingale;
fLanguage
English
Publisher
ieee
Conference_Titel
Control Conference, 2007. CCC 2007. Chinese
Conference_Location
Hunan
Print_ISBN
978-7-81124-055-9
Electronic_ISBN
978-7-900719-22-5
Type
conf
DOI
10.1109/CHICC.2006.4346803
Filename
4346803
Link To Document