Unit Bit Importance Evolutionary Algorithm

Authors:
Yi Hong;Qingsheng Ren;Jin Zeng
Affiliations:
Department of Computer Science and Engineering, Shanghai Jiao tong University, 200030, Shanghai, P.R. China;Department of Computer Science and Engineering, Shanghai Jiao tong University, 200030, Shanghai, P.R. China;Department of Mathematics, Shanghai Jiao tong University, 200030, Shanghai, P.R. China
Venue:
Soft Computing - A Fusion of Foundations, Methodologies and Applications
Year:
2006

Citing 0
Cited 1

Subspace estimation of distribution algorithms: To perturb part of all variables in estimation of distribution algorithms

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In Darwinian-type binary-coded genetic algo- rithms, there exist bit importance and convergent order of bit. Inspired from this phenomenon, we propose an evolutionary algorithm called Unit Bit Importance Evolutionary Algorithm (UBIEA). Compared with Darwinian-type genetic algorithms, UBIEA completely abandons commonly used genetic operators such as mutation and crossover. Its main idea is that: detecting bit importance, speeding up the convergence of important bits and maintaining the diversity of unimportant bits. Although our theoretic analyses are based on the assumption that all bits are independent and have different salience, UBIEA perhaps is usable in a larger framework which can be verified by numerical experiments.