Evolutionary algorithms; Evolutionary computation
A genetic algorithm (GA) is one of a number of heuristic techniques that attempt to find high-quality solutions to large and complex optimization problems. The term evolutionary algorithm is sometimes used synonymously, but is generally used to denote a rather wider class of heuristics. All such algorithms use the notion of a sequence of cycles that employ mutation of, and subsequent selection from, a population of candidate solutions. While these features are also found in a GA, its most distinctive characteristic is the use of recombination (or crossover) to generate new candidate solutions. A secondary idea found in many, but not all GAs, is the existence of an encoding function that maps the original optimization problem into a space that is hoped to be more congenial to the application of the GA operators.
The term genetic algorithm was first used by John Holland, whose book , first...
- 3.Corcoran AL, Hale J. A genetic algorithm for fragment allocation in a distributed database system. In: Proceedings of the ACM Symposium on Applied Computing; 1994. p. 247–50.Google Scholar
- 5.Flockhart IW, Radcliffe NJ. A genetic algorithm-based approach to data mining. In: Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining; 1996. p. 299–302.Google Scholar
- 8.Holland JH. Adaptation in natural and artificial systems. 2nd ed. Cambridge, MA: MIT Press; 1992.Google Scholar
- 10.Reeves CR, Rowe JE. Genetic algorithms: principles and perspectives. Dordecht: Kluwer; 2002.Google Scholar
- 12.Wang HB, Yu Y, Liu Z. SVM classifier incorporating feature selection using GA for spam detection. In: Proceedings of the International Conference on Embedded and Ubiquitous Computing; 2005. p. 1147–54.Google Scholar