Title :
Organizational evolutionary applied on geometric constraints solving
Author :
Wang, Duo ; Li, Wenhui ; Yi, RongQing ; Cheng, X.
Author_Institution :
Coll. of Comput. Sci. & Technol., Jilin Univ., Changchun
Abstract :
In this paper, a new optimization method, Organizational Evolutionary Algorithm (OEA), is proposed, in which a population is made of organizations and whose evolution is led by three organizational evolutionary operators, i.e. the splitting operator, the merging operator and the cooperating operator; the splitting operator controls the size of organizations and make part of organizations enter into next generation directly, which are benefit for keeping the diversity of populations; the merging operator acts as a local searching function with taking advantage of leaders information; the cooperating operator increases the adaptability degree through the interactions of organizations. OEA is successfully applied to solve the non-linear parameterization design problems. Experiments show that OEA performs better than original Generic algorithm (GA) in this application of parameterization design.
Keywords :
evolutionary computation; mathematical operators; optimisation; search problems; cooperating operator; geometric constraints solving; local searching function; merging operator; nonlinear parameterization design problem; optimization method; organizational evolutionary algorithm; organizational evolutionary operator; splitting operator; Algorithm design and analysis; Evolutionary computation; Genetic algorithms; Machine learning; Machine learning algorithms; Merging; Neural networks; Nonlinear equations; Optimization methods; Size control;
Conference_Titel :
Cybernetic Intelligent Systems, 2008. CIS 2008. 7th IEEE International Conference on
Conference_Location :
London
Print_ISBN :
978-1-4244-2914-1
Electronic_ISBN :
978-1-4244-2915-8
DOI :
10.1109/UKRICIS.2008.4798970