Allele Gene Based Adaptive Genetic Algorithm to the Code Design
Author:
- 24 March 2011
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 59 (5) , 1253-1258
Abstract
In this work, an allele gene adaptive mutation (AGAM) and a schemata crossover (SC) operators are designed to improve the performance of the conventional genetic algorithm (GA) and applied to the code design. Specifically, the proposed AGAM exploits both global and local information of the population to maintain an appropriate level of diversity throughout the search process. The SC utilizes high-performance schemata to enhance the traditional crossover operation. The combination of the AGAM and SC achieves both goals of maintaining population diversity and simultaneously sustaining the convergence capability of the GA. As a result, the SC and AGAM based genetic algorithm alleviates the inherent premature convergence of the GA, thus significantly increasing the chance of locating the global optimal solution. The application of the proposed allele based adaptive genetic algorithm (AGAGA) to the universal mobile telecommunications system (UMTS) time-division duplex (TDD) mode leads to significant performance gains on autocorrelation (6.1 dB) and cross-correlation properties (2.0 dB) over those of the current standard.Keywords
This publication has 12 references indexed in Scilit:
- Coarse-Grained Dynamics for Generalized RecombinationIEEE Transactions on Evolutionary Computation, 2007
- Entropy-Boltzmann selection in the genetic algorithmsIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2003
- Genetic algorithms for multiuser detection in synchronous CDMA2002
- Optical orthogonal code design using genetic algorithmsElectronics Letters, 2001
- Degree of population diversity - a perspective on premature convergence in genetic algorithms and its Markov chain analysisIEEE Transactions on Neural Networks, 1997
- Adaptive probabilities of crossover and mutation in genetic algorithmsIEEE Transactions on Systems, Man, and Cybernetics, 1994
- Genetic Algorithms + Data Structures = Evolution Programs1992
- Optimization of Control Parameters for Genetic AlgorithmsIEEE Transactions on Systems, Man, and Cybernetics, 1986
- Sieves for low autocorrelation binary sequencesIEEE Transactions on Information Theory, 1977
- Lower bounds on the maximum cross correlation of signals (Corresp.)IEEE Transactions on Information Theory, 1974