Managing Gene Expression in Evolutionary Algorithms with Gene Regulatory Networks
-
Michael Cilliers [1] ; Coulter, Duncan A. [1]
-
[1] University of Johannesburg
University of Johannesburg
City of Johannesburg, Sudáfrica
-
- Localización: Hybrid Artificial Intelligent Systems: 16th International Conference, HAIS 2021. Bilbao, Spain. September 22–24, 2021. Proceedings / coord. por Hugo Sanjurjo González, Iker Pastor López, Pablo García Bringas, Héctor Quintián Pardo, Emilio Santiago Corchado Rodríguez, 2021, ISBN 978-3-030-86271-8, págs. 77-87
- Idioma: inglés
- Texto completo no disponible (Saber más ...)
-
Resumen
This paper evaluates the effectiveness of using gene regulatory networks to manage gene expression in evolutionary algorithms for the purpose of balancing exploitation versus exploration. This builds on previous work that has shown that the introduction of non-coding genes can improve the ability of an evolutionary algorithm to adapt to change in the environment. As part of the paper an algorithm is developed and a prototype is implemented. The developed algorithm is compared to the standard genetic algorithm and previously developed methods for managing gene expression. Results show that the developed algorithm can outperform the standard genetic algorithm in dynamic environments. The algorithm is however not able to outperform all the other developed methods of managing gene expression and avenues for future improvement will be explored.